{ "data": { "similar": [ { "grade": "E", "json": "https://www.anchorterminal.com/tools/parallax-agents.json", "name": "Parallax", "score": 38.1, "shared": [ "agent.multi-agent", "code.git" ], "slug": "parallax-agents" }, { "grade": "F", "json": "https://www.anchorterminal.com/tools/unstoppable.json", "name": "Unstoppable", "score": 34.7, "shared": [ "agent.multi-agent", "code.git" ], "slug": "unstoppable" }, { "grade": "AA", "json": "https://www.anchorterminal.com/tools/openai-agents-sdk.json", "name": "OpenAI Agents SDK", "score": 86.2, "shared": [ "agent.multi-agent" ], "slug": "openai-agents-sdk" }, { "grade": "A", "json": "https://www.anchorterminal.com/tools/microsoft-agent-framework.json", "name": "Microsoft Agent Framework", "score": 82.4, "shared": [ "agent.multi-agent" ], "slug": "microsoft-agent-framework" }, { "grade": "A", "json": "https://www.anchorterminal.com/tools/pydantic-ai.json", "name": "Pydantic AI", "score": 81.9, "shared": [ "agent.multi-agent" ], "slug": "pydantic-ai" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/docker-agent.json", "name": "Docker Agent", "score": 76.6, "shared": [ "agent.multi-agent" ], "slug": "docker-agent" } ], "tool": { "slug": "superpowers", "name": "Superpowers", "vendor": "Prime Radiant", "vendorUrl": "https://primeradiant.com/superpowers/", "kind": "framework", "category": "code", "summary": "Superpowers is an MIT-licensed library of 15 agent skills and a session-start bootstrap that steer coding agents through brainstorming, a design, a plan, test-driven implementation by subagents and code review. Its README gives install steps for 16 coding agents.", "url": "https://www.anchorterminal.com/tools/superpowers", "markdownUrl": "https://www.anchorterminal.com/tools/superpowers.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/superpowers.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/superpowers.json", "repo": "https://github.com/obra/superpowers", "license": "MIT (Copyright (c) 2025 Jesse Vincent)", "transports": [], "packages": [], "auth": "none", "authNotes": "No account, key or login of its own. It installs through each coding agent's plugin manager (Claude Code's official marketplace, the Codex, Cursor, Grok and Kimi marketplaces, or a git install from the repository) and runs with whatever model access and permissions that agent already has.", "pricing": "free", "pricingNotes": "Free under the MIT licence, with nothing to buy. Model usage is billed by the coding agent's provider, and the skills dispatch a subagent per task plus reviewers, which adds model calls. Prime Radiant takes enquiries for enterprise support at sales@primeradiant.com, with no published price.", "priceSummary": "Free · OSS", "where": "library", "x402": { "level": "no", "evidence": "No machine payment protocol in the repository or on primeradiant.com, read on 2026-10-30. The project sells nothing per call.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 309222, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-30" }, "docsUrl": "https://github.com/obra/superpowers#readme", "capabilities": [ "code.git", "agent.multi-agent" ], "tags": [ "open-source", "mit", "local", "free", "agent-skills", "framework", "claude-code-plugin" ], "lastRelease": "2026-10-21", "graded": true, "anchor": { "graded": true, "score": 64.5, "grade": "B", "agentReady": false, "rank": 408, "ranked": true, "rankOf": 1239, "categoryRank": 7, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 71, "maintenance": 83, "payments": 60, "reliability": 68, "schema": 71, "security": 58, "transparency": 68 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "reliability", "name": "Reliability", "weight": 16, "effectiveWeight": 20, "score": 68, "points": 13.6, "reason": "Local-package reading, as for ai-job-search and the other skill workflows. Installs through official plugin channels (Claude Code's official marketplace, the Codex, Cursor, Grok and Kimi marketplaces) or a git install in 16 coding agents, with harness versions stated for OpenCode 2.0.4 and Claude Code's hook quirks, but bash and Node needs are spread across the docs rather than stated once (17 of 20). No .github/workflows directory, so no public CI. About 60 test files in tests/ cover the hooks, plugin manifests and the visual companion server, run locally, with LLM evals in a separate repository (8 of 25). 194 issues open on 30 October 2026; 25 issues were closed between 10 and 22 October, each with a reply, while 13 of the 25 newest open issues had no comment (13 of 25). Dated release notes with Breaking Changes and Visible Changes sections and semver majors for them (15). Version 7.0.1 (15). 68 in all.", "checked": "2026-10-30" }, { "key": "performance", "name": "Performance", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes." }, { "key": "schema", "name": "Schema \u0026 documentation", "weight": 13, "effectiveWeight": 16.25, "score": 71, "points": 11.54, "reason": "Framework reading, docs a model can follow. Each skill has name and description frontmatter and every harness gets a JSON plugin manifest, but the skills are prose with no typed interface or API reference (12 of 25). All docs are Markdown in the repository, which an agent reads directly; no llms.txt (10). Every description starts with \"Use when\", using-superpowers sets skill priority and a subagent stop rule, and executing-plans says when to prefer subagent-driven development. When not to use a skill is stated in fewer places (17 of 20). Skills take no typed parameters; the helper scripts have fixed arguments and documented exit codes, such as review-package's exit 3 for an empty range (6 of 15). Worked examples in the debugging and TDD skills, troubleshooting in the OpenCode install guide and a diagnosing skill for failed sessions, with few documented error outputs (11 of 15). Semver releases and a dated RELEASE-NOTES.md (15). 71 in all.", "checked": "2026-10-30" }, { "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "effectiveWeight": 16.25, "score": 71, "points": 11.54, "reason": "Framework reading, how much a tool-calling agent has to carry. The bootstrap (3,192 bytes) is injected at every startup, clear and compaction, and 15 skill descriptions add about 2,500 characters. Bodies load on demand and long guidance moved to references/ in v7.0.1, but single skills run to 19,506 bytes and the bootstrap asks for a skill before any reply (17 of 25). The work can be sized. Brainstorming does a quick task at once and writes a design only for a project, execution can be inline (cheapest) or one subagent per task, and every dispatch must name a model (15 of 20). Implementers report DONE, DONE_WITH_CONCERNS, BLOCKED or NEEDS_CONTEXT and the controller acts on each; review-package rejects bad ranges (14 of 20). A progress ledger and task-done records let a run resume, work happens in a worktree, merges are confirmed and a discard needs the typed word (15 of 20). Skills trigger without a command and install in one step per harness; no SDK applies (10 of 15). 71 in all.", "checked": "2026-10-30" }, { "key": "security", "name": "Security \u0026 auth", "weight": 14, "effectiveWeight": 17.5, "score": 58, "points": 10.15, "reason": "Harness reading of the framework checklist, the one harness2 and agent-zero used. 30 for what leaves the machine and credentials, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. No credentials of its own and no network access in the hooks or plugins. The visual companion's logo request carries the version to primeradiant.com by default, disclosed with opt-outs, and some installs (OpenCode's git+https spec, git installs) follow main unless pinned, so new hook code runs at the next session start (22). Worktrees isolate work, reviewers are read-only, merges are confirmed, a discard needs the typed word, force pushes need the person, and issues are filed only after approval. No sandbox of its own, and plan execution runs for hours without check-ins (12). The companion has a per-session key and refuses symlinks and path escapes since 16 June 2026, the Windows hook ignores planted bash.cmd since 9 October 2026, and diagnosing-superpowers treats transcripts as evidence, not instructions. No guidance on untrusted content in repositories or fetched pages (7). Plans, briefs, reports, review diffs and a ledger are written to files, and the diagnosing skill cites path:line for each finding (11). No SECURITY.md, no security.txt and no advisories; GitHub shows a Report a vulnerability link, and both 2026 security fixes are credited in the release notes (6). 58 in all.", "checked": "2026-10-30" }, { "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "effectiveWeight": 12.5, "score": 60, "points": 7.5, "reason": "Self-hosted rule. No payment protocol (0). Free under MIT with nothing to buy (20). Free to use with no card (20). An agent can install it in its own harness with no account or sign-up (20). Model usage is billed by the coding agent's provider, and the enterprise support Prime Radiant mentions has no published price. 60 in all.", "checked": "2026-10-30" }, { "key": "tasks", "name": "Task success", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored." }, { "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7, "effectiveWeight": 8.75, "score": 83, "points": 7.26, "reason": "v7.0.1 on 21 October 2026, nine days before the check (30). Five releases in the last 90 days, v6.3.0 (12 August), v6.4.1 (18 September), v6.4.2 (25 September), v7.0.0 (10 October) and v7.0.1 (21 October) (20). 1,190 pull requests closed and 181 open; issues are triaged in batches with a reply on each closed one, but about half the newest open issues had no comment, and AGENTS.md says most PRs are rejected (15 of 25). Listed as Anthropic verified in Claude's plugin directory, read first-hand; the README also names the official Codex and Grok marketplaces, which weren't read (12 of 15). Zero dependencies by design, tests in the tree and a skill-size check, but no CI (6 of 10). 83 in all.", "checked": "2026-10-30" }, { "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "effectiveWeight": 8.75, "score": 68, "points": 5.95, "note": "editorial 77, provenance 58", "reason": "MIT, an OSI licence (30). The README and the source agree on the one outbound request and what it carries, git-ignored scratch files stay in the working tree, and diagnosing-superpowers has a written redaction policy and approval gates. Prime Radiant publishes no privacy policy covering the logo request, which reaches its site with the visitor's address (15 of 30). Breaking changes are dated in the release notes, the legacy slash commands showed deprecation notices in v5.0.0 (9 March 2026) before removal in v5.1.0 (30 April 2026), but no written deprecation policy (12 of 20). Telemetry disclosed in the README with three opt-out variables, read in server.cjs (20). 77 in all.", "checked": "2026-10-30" } ], "assessment": { "date": "2026-10-30", "basis": "public evidence", "confidence": "medium", "notes": { "ergonomics": "Framework reading, how much a tool-calling agent has to carry. The bootstrap (3,192 bytes) is injected at every startup, clear and compaction, and 15 skill descriptions add about 2,500 characters. Bodies load on demand and long guidance moved to references/ in v7.0.1, but single skills run to 19,506 bytes and the bootstrap asks for a skill before any reply (17 of 25). The work can be sized. Brainstorming does a quick task at once and writes a design only for a project, execution can be inline (cheapest) or one subagent per task, and every dispatch must name a model (15 of 20). Implementers report DONE, DONE_WITH_CONCERNS, BLOCKED or NEEDS_CONTEXT and the controller acts on each; review-package rejects bad ranges (14 of 20). A progress ledger and task-done records let a run resume, work happens in a worktree, merges are confirmed and a discard needs the typed word (15 of 20). Skills trigger without a command and install in one step per harness; no SDK applies (10 of 15). 71 in all.", "maintenance": "v7.0.1 on 21 October 2026, nine days before the check (30). Five releases in the last 90 days, v6.3.0 (12 August), v6.4.1 (18 September), v6.4.2 (25 September), v7.0.0 (10 October) and v7.0.1 (21 October) (20). 1,190 pull requests closed and 181 open; issues are triaged in batches with a reply on each closed one, but about half the newest open issues had no comment, and AGENTS.md says most PRs are rejected (15 of 25). Listed as Anthropic verified in Claude's plugin directory, read first-hand; the README also names the official Codex and Grok marketplaces, which weren't read (12 of 15). Zero dependencies by design, tests in the tree and a skill-size check, but no CI (6 of 10). 83 in all.", "payments": "Self-hosted rule. No payment protocol (0). Free under MIT with nothing to buy (20). Free to use with no card (20). An agent can install it in its own harness with no account or sign-up (20). Model usage is billed by the coding agent's provider, and the enterprise support Prime Radiant mentions has no published price. 60 in all.", "reliability": "Local-package reading, as for ai-job-search and the other skill workflows. Installs through official plugin channels (Claude Code's official marketplace, the Codex, Cursor, Grok and Kimi marketplaces) or a git install in 16 coding agents, with harness versions stated for OpenCode 2.0.4 and Claude Code's hook quirks, but bash and Node needs are spread across the docs rather than stated once (17 of 20). No .github/workflows directory, so no public CI. About 60 test files in tests/ cover the hooks, plugin manifests and the visual companion server, run locally, with LLM evals in a separate repository (8 of 25). 194 issues open on 30 October 2026; 25 issues were closed between 10 and 22 October, each with a reply, while 13 of the 25 newest open issues had no comment (13 of 25). Dated release notes with Breaking Changes and Visible Changes sections and semver majors for them (15). Version 7.0.1 (15). 68 in all.", "schema": "Framework reading, docs a model can follow. Each skill has name and description frontmatter and every harness gets a JSON plugin manifest, but the skills are prose with no typed interface or API reference (12 of 25). All docs are Markdown in the repository, which an agent reads directly; no llms.txt (10). Every description starts with \"Use when\", using-superpowers sets skill priority and a subagent stop rule, and executing-plans says when to prefer subagent-driven development. When not to use a skill is stated in fewer places (17 of 20). Skills take no typed parameters; the helper scripts have fixed arguments and documented exit codes, such as review-package's exit 3 for an empty range (6 of 15). Worked examples in the debugging and TDD skills, troubleshooting in the OpenCode install guide and a diagnosing skill for failed sessions, with few documented error outputs (11 of 15). Semver releases and a dated RELEASE-NOTES.md (15). 71 in all.", "security": "Harness reading of the framework checklist, the one harness2 and agent-zero used. 30 for what leaves the machine and credentials, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. No credentials of its own and no network access in the hooks or plugins. The visual companion's logo request carries the version to primeradiant.com by default, disclosed with opt-outs, and some installs (OpenCode's git+https spec, git installs) follow main unless pinned, so new hook code runs at the next session start (22). Worktrees isolate work, reviewers are read-only, merges are confirmed, a discard needs the typed word, force pushes need the person, and issues are filed only after approval. No sandbox of its own, and plan execution runs for hours without check-ins (12). The companion has a per-session key and refuses symlinks and path escapes since 16 June 2026, the Windows hook ignores planted bash.cmd since 9 October 2026, and diagnosing-superpowers treats transcripts as evidence, not instructions. No guidance on untrusted content in repositories or fetched pages (7). Plans, briefs, reports, review diffs and a ledger are written to files, and the diagnosing skill cites path:line for each finding (11). No SECURITY.md, no security.txt and no advisories; GitHub shows a Report a vulnerability link, and both 2026 security fixes are credited in the release notes (6). 58 in all.", "transparency": "MIT, an OSI licence (30). The README and the source agree on the one outbound request and what it carries, git-ignored scratch files stay in the working tree, and diagnosing-superpowers has a written redaction policy and approval gates. Prime Radiant publishes no privacy policy covering the logo request, which reaches its site with the visitor's address (15 of 30). Breaking changes are dated in the release notes, the legacy slash commands showed deprecation notices in v5.0.0 (9 March 2026) before removal in v5.1.0 (30 April 2026), but no written deprecation policy (12 of 20). Telemetry disclosed in the README with three opt-out variables, read in server.cjs (20). 77 in all." }, "sources": [ { "what": "repository metadata (created 2025-10-09, MIT, default branch)", "url": "https://api.github.com/repos/obra/superpowers", "seen": "2026-10-30" }, { "what": "GitHub releases", "url": "https://api.github.com/repos/obra/superpowers/releases?per_page=100", "seen": "2026-10-30" }, { "what": "tags", "url": "https://api.github.com/repos/obra/superpowers/tags?per_page=100", "seen": "2026-10-30" }, { "what": "earliest tag commit, v3.1.0", "url": "https://api.github.com/repos/obra/superpowers/commits/0bc5a5989d8cf140e9f671af14c76f6a6e6fae79", "seen": "2026-10-30" }, { "what": "file tree", "url": "https://api.github.com/repos/obra/superpowers/git/trees/main?recursive=1", "seen": "2026-10-30" }, { "what": "contributors", "url": "https://api.github.com/repos/obra/superpowers/contributors?per_page=30", "seen": "2026-10-30" }, { "what": "README", "url": "https://raw.githubusercontent.com/obra/superpowers/main/README.md", "seen": "2026-10-30" }, { "what": "release notes", "url": "https://raw.githubusercontent.com/obra/superpowers/main/RELEASE-NOTES.md", "seen": "2026-10-30" }, { "what": "LICENSE", "url": "https://raw.githubusercontent.com/obra/superpowers/main/LICENSE", "seen": "2026-10-30" }, { "what": "contributor guidelines", "url": "https://raw.githubusercontent.com/obra/superpowers/main/AGENTS.md", "seen": "2026-10-30" }, { "what": "SessionStart hook", "url": "https://raw.githubusercontent.com/obra/superpowers/main/hooks/session-start", "seen": "2026-10-30" }, { "what": "Windows hook wrapper", "url": "https://raw.githubusercontent.com/obra/superpowers/main/hooks/run-hook.cmd", "seen": "2026-10-30" }, { "what": "bootstrap skill", "url": "https://raw.githubusercontent.com/obra/superpowers/main/skills/using-superpowers/SKILL.md", "seen": "2026-10-30" }, { "what": "visual companion server", "url": "https://raw.githubusercontent.com/obra/superpowers/main/skills/brainstorming/scripts/server.cjs", "seen": "2026-10-30" }, { "what": "subagent-driven-development skill", "url": "https://raw.githubusercontent.com/obra/superpowers/main/skills/subagent-driven-development/SKILL.md", "seen": "2026-10-30" }, { "what": "finishing-a-development-branch skill", "url": "https://raw.githubusercontent.com/obra/superpowers/main/skills/finishing-a-development-branch/SKILL.md", "seen": "2026-10-30" }, { "what": "diagnosing-superpowers skill and redaction policy", "url": "https://raw.githubusercontent.com/obra/superpowers/main/skills/diagnosing-superpowers/references/redaction-policy.md", "seen": "2026-10-30" }, { "what": "OpenCode install guide", "url": "https://raw.githubusercontent.com/obra/superpowers/main/.opencode/INSTALL.md", "seen": "2026-10-30" }, { "what": "testing guide", "url": "https://raw.githubusercontent.com/obra/superpowers/main/docs/testing.md", "seen": "2026-10-30" }, { "what": "open and closed issues (numbers, dates, comment counts)", "url": "https://github.com/obra/superpowers/issues", "seen": "2026-10-30" }, { "what": "pull request counts", "url": "https://github.com/obra/superpowers/pulls", "seen": "2026-10-30" }, { "what": "security policy and advisories", "url": "https://github.com/obra/superpowers/security", "seen": "2026-10-30" }, { "what": "announcement post, 9 October 2025", "url": "https://blog.fsck.com/2025/10/09/superpowers/", "seen": "2026-10-30" }, { "what": "Prime Radiant about page", "url": "https://primeradiant.com/about/", "seen": "2026-10-30" }, { "what": "Prime Radiant post, What a year", "url": "https://blog.primeradiant.com/what-a-year/", "seen": "2026-10-30" }, { "what": "Claude plugin directory entry", "url": "https://claude.com/plugins/superpowers", "seen": "2026-10-30" } ], "openQuestions": [ "Judgement call. Listed in code because the batch suggested it and no category covers development methods; the code category's capabilities (repository, git, docs, deploy) fit only in part, so code.git and agent.multi-agent were chosen. Graded as a framework the way ai-job-search was", "firstReleased is 2025-10-09, from the announcement post on blog.fsck.com with install steps and the repository's created_at of 2025-10-09T19:45:18Z. Prime Radiant's post of 9 October 2026 says Superpowers 1.0 shipped that day. The earliest tag is v3.1.0 (17 October 2025); earlier versions have notes but no tags", "unchecked: whether the tests in tests/ pass on main. There's no CI, and we don't run vendor code", "unchecked: issue and PR reply times and text. Counts and dates were read from GitHub's issue pages with a script; no issue text was read", "unchecked: the official Codex and Grok marketplace entries the README names; only Claude's plugin directory was read", "unchecked: whether GitHub private vulnerability reporting is enabled; the security page shows a Report a vulnerability link, with no SECURITY.md", "unchecked: Prime Radiant's legal form and registration. Its pages say \"Prime Radiant\" with no Inc. or address, while its GitHub organisation is prime-radiant-inc", "Disclosure. These grades are written by agents on Anthropic's Claude models. Superpowers started as a Claude Code plugin and Claude's plugin directory marks it Anthropic verified; the checklist was applied as for any listing, and the directory's installs figure was not used", "Our own products. Superpowers is a development method for coding agents. It does neither LocalGhost's job nor letme's (choosing a tool for a job), so it was graded the normal way", "We did not install or run Superpowers, its hooks or its visual companion. Every claim about behaviour comes from the source, docs and release notes" ] }, "negative": -3, "negativeNotes": [ "-2: until v6.0.0 of 16 June 2026 the brainstorming visual companion, a local web server, had no authentication. The release notes say anyone who could reach the port on a shared or remote machine could read the session or inject events the agent treats as the person's input (issue #1014). Fixed with a per-session key and documented, with no report of exploitation found, so the deduction is small (https://github.com/obra/superpowers/blob/main/RELEASE-NOTES.md)", "-1: until v7.0.0 of 9 October 2026, run-hook.cmd on Windows could run a `bash.cmd` or `where.bat` planted in the current directory at session start, per the release notes. Fixed and documented (https://github.com/obra/superpowers/blob/main/RELEASE-NOTES.md)" ], "verdict": "Fifteen MIT-licensed skills that make a coding agent design, plan, test first and review before it finishes, with five releases in 90 days and dated release notes. It has no CI workflow or security policy, its bootstrap insists a skill be invoked before any reply, and its optional visual companion loads a logo from Prime Radiant's site unless disabled.", "bestFor": "A test-first development method for coding agents", "strengths": [ "Installs in one command or a marketplace click in 16 coding agents, including Claude Code's official marketplace, where it is marked Anthropic verified", "Five releases between 12 August and 21 October 2026, each with dated notes that name breaking changes, fixes and the reporters credited", "Discarding work needs the typed word 'discard', merges are confirmed first, and force pushes never happen on the agent's own initiative", "Plans, task briefs, review diffs and a progress ledger are written to files, so a controller that loses context can resume without redoing work", "Zero third-party dependencies by design, MIT licence, and the one outbound request is disclosed in the README with three opt-out variables" ], "weaknesses": [ "No CI workflow in the repository; the test suites in tests/ run only on a contributor's machine", "No SECURITY.md or published advisories, though two security fixes in 2026 (the visual companion key, a Windows hook path) are documented in release notes", "The bootstrap is injected on every session start and compaction and tells the model to invoke skills before any reply, including simple questions", "Skills are long Markdown instructions (subagent-driven-development is 19,506 bytes), with no typed inputs beyond the frontmatter name and description", "194 issues and 181 pull requests were open on 30 October 2026; 13 of the 25 newest open issues had no comment" ], "agentNotes": [ "Install it once per coding agent; each harness has its own install command, and the README says a second harness needs a second install.", "Expect brainstorming to start before any code on a build request. Say so plainly if your human partner wants a quick change done without a design document.", "Name a model on every subagent dispatch, as the skill asks; an unnamed subagent inherits the session's most expensive model.", "Set SUPERPOWERS_DISABLE_TELEMETRY=1 before using the visual companion if no request may leave the machine.", "Keep `.superpowers/sdd/` out of `git clean -fdx`; it holds the progress ledger a resumed run reads." ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 64.5 } ], "editorialScores": { "ergonomics": 71, "maintenance": 83, "payments": 60, "reliability": 68, "schema": 71, "security": 58, "transparency": 77 }, "provenanceScore": 58, "checked": { "categories": { "ergonomics": "2026-10-30", "maintenance": "2026-10-30", "payments": "2026-10-30", "reliability": "2026-10-30", "schema": "2026-10-30", "security": "2026-10-30", "transparency": "2026-10-30" }, "last": "2026-10-30", "oldest": "2026-10-30", "stale": false, "staleAfterDays": 90 }, "scoreHistory": [ { "date": "2026-10-30", "grade": "B", "kind": "listed", "method": "0.7", "score": 64.5 } ] }, "connect": { "claudeCode": "/plugin install superpowers@claude-plugins-official" }, "letme": { "capability": "https://letme.dev/code.git", "tool": "https://letme.dev/superpowers" }, "notable": [ "Released on 9 October 2025 with Jesse Vincent's post \"Superpowers: How I'm using coding agents in October 2025\", the day the GitHub repository was created; Prime Radiant's post of 9 October 2026 dates Superpowers 1.0 to that day (https://blog.fsck.com/2025/10/09/superpowers/)", "A SessionStart hook injects the using-superpowers skill (3,192 bytes) at startup, clear and compaction, and that skill tells the model to invoke any skill with \"even a 1% chance\" of applying before any reply (https://github.com/obra/superpowers/blob/main/hooks/session-start)", "The optional brainstorming visual companion is a local Node server on 127.0.0.1 guarded by a per-session key since v6.0.0 of 16 June 2026; before that it had no authentication, which the release notes say let anyone reaching the port read the session or inject input (https://github.com/obra/superpowers/blob/main/RELEASE-NOTES.md)", "The visual companion page loads Prime Radiant's logo from primeradiant.com with the Superpowers version in the query string, disclosed in the README as usage telemetry and turned off by SUPERPOWERS_DISABLE_TELEMETRY, DISABLE_TELEMETRY or CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC (https://github.com/obra/superpowers/blob/main/skills/brainstorming/scripts/server.cjs)", "Claude's plugin directory lists Superpowers as \"Anthropic verified\", installed with `/plugin install superpowers@claude-plugins-official` (https://claude.com/plugins/superpowers)", "16 GitHub releases from v5.0.4 (17 March 2026) to v7.0.1 (21 October 2026) and 38 tags back to v3.1.0 (17 October 2025), with a dated RELEASE-NOTES.md that names breaking changes and credits reporters (https://github.com/obra/superpowers/releases)", "The repository has no .github/workflows directory and no SECURITY.md; tests for the hooks, plugins and visual companion server live in tests/ and run locally (https://github.com/obra/superpowers/blob/main/docs/testing.md)" ], "area": "developer", "details": [ { "label": "Surface listed", "value": "The obra/superpowers repository at v7.0.1 (main, tree 2ce8aa1), read from raw.githubusercontent.com, GitHub's release, tag, issue and security pages, primeradiant.com, blog.primeradiant.com, blog.fsck.com and claude.com/plugins/superpowers on 30 October 2026. Nothing was installed or run, and no session was opened with it" }, { "label": "How an agent reaches it", "value": "As a plugin inside the coding agent, not as an endpoint. The skills sit in the agent's skill list and load on demand, and a SessionStart hook (or a plugin or extension on OpenCode, Pi and Hermes) injects the using-superpowers bootstrap. An outside agent can't call it over a network" }, { "label": "Install routes", "value": "Claude Code (official marketplace or obra/superpowers-marketplace), Antigravity, Codex app and CLI (official Codex marketplace), Cursor, Devin CLI, Factory Droid, Gemini CLI, GitHub Copilot CLI, Grok Build CLI, Kimi Code, OpenCode (git+https spec, pin a tag with #v7.0.1), Pi, Qwen Code, Hermes Agent and Muse. No install script; each harness's own plugin manager fetches the repository" }, { "label": "Skills", "value": "15 skills. brainstorming, writing-plans, subagent-driven-development, executing-plans, test-driven-development, requesting-code-review, receiving-code-review, using-git-worktrees, finishing-a-development-branch, dispatching-parallel-agents, systematic-debugging, verification-before-completion, diagnosing-superpowers, writing-skills and using-superpowers. Each description starts with \"Use when\", about 2,500 characters in all; a test fails any SKILL.md of 20,000 bytes or more" }, { "label": "What runs on the machine", "value": "The SessionStart hook is a bash script that reads one SKILL.md and prints JSON, with no network access. On Windows, run-hook.cmd finds Git Bash and, since v7.0.0, ignores bash or where in the current directory. Helper scripts for plans and reviews are bash. The visual companion is a dependency-free Node server bound to 127.0.0.1 by default, with a 4-hour idle timeout" }, { "label": "Data leaving the machine", "value": "The visual companion page requests https://primeradiant.com/brand/superpowers-visual-brainstorming-logo.png?v=\u003cversion\u003e with no referrer, which the README calls telemetry and says carries no project, prompt or agent details. diagnosing-superpowers files a GitHub issue or builds a scrubbed bundle only after the person approves the exact text. Prompts and code go to the coding agent's model provider as usual" }, { "label": "Work products", "value": "Designs and plans under docs/superpowers/, worktrees in .worktrees/ unless told otherwise, and task briefs, implementer reports, review diffs and a progress ledger in a self-ignoring .superpowers/sdd/ directory in the working tree" }, { "label": "Contributions", "value": "AGENTS.md says new skills are generally not accepted, PRs must target dev, every PR and issue must disclose the model, harness and plugins used, and agent-written PRs fixing someone else's issue are closed. It states a 94 per cent PR rejection rate, which is the project's own figure" }, { "label": "Company", "value": "The repository is under Jesse Vincent's GitHub account. The README says Superpowers is built by him and the rest of Prime Radiant, which its about page calls an AI research lab he founded" }, { "label": "Category", "value": "Listed in code, the closest category, though its capabilities are repository and documentation tools. Superpowers is a method a coding agent follows. It works through git branches and worktrees and dispatches subagents, hence code.git and agent.multi-agent" } ], "provenance": { "legalEntity": "Prime Radiant (no legal form or registration found on its pages); the MIT LICENSE names Jesse Vincent", "domain": "primeradiant.com", "domainRegistered": "2002-05-14", "endpointOnVendorDomain": false, "terms": "https://github.com/obra/superpowers/blob/main/LICENSE", "privacy": "", "statusPage": "", "changelog": "https://github.com/obra/superpowers/blob/main/RELEASE-NOTES.md", "securityTxt": "none", "checked": "2026-10-30", "notes": [ "The README says Superpowers is built by Jesse Vincent and the rest of the folks at Prime Radiant, and the plugin manifests name Jesse Vincent as author. The LICENSE reads Copyright (c) 2025 Jesse Vincent.", "RDAP for primeradiant.com gives a registration date of 2002-05-14 and a last change on 2026-06-16; the registration may predate the company.", "No terms or privacy policy on primeradiant.com (/privacy/ and /terms/ answer 404). The MIT licence stands in for terms.", "primeradiant.com/.well-known/security.txt and /security.txt answer 404. GitHub's security page for the repository says no security policy is set up and no advisories are published, and shows a Report a vulnerability link.", "The software runs inside the person's coding agent, so there is no vendor endpoint or status page.", "firstReleased is 9 October 2025, the date of the announcement post with install steps and the repository's creation date (created_at 2025-10-09T19:45:18Z). The earliest tag, v3.1.0, is dated 17 October 2025, and RELEASE-NOTES.md has v2.0.1 on 12 October 2025." ], "score": 58, "checks": [ { "check": "Legal entity named", "value": "Prime Radiant (no legal form or registration found on its pages); the MIT LICENSE names Jesse Vincent", "points": 20, "max": 20, "state": "ok" }, { "check": "Domain age", "value": "primeradiant.com, registered 2002-05-14 (24 years)", "points": 15, "max": 15, "state": "ok" }, { "check": "Endpoint on the vendor's domain", "value": " is not on primeradiant.com", "points": 0, "max": 15, "state": "no" }, { "check": "Terms of service", "value": "published, but our reader couldn't read it", "points": 7, "max": 10, "state": "part" }, { "check": "Privacy policy", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "Status page", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "Changelog", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "security.txt", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "People named", "value": "2 named with their role, 2 with a public profile", "points": 10, "max": 10, "state": "ok" }, { "check": "Support route", "value": "help pages, a community", "points": 5, "max": 5, "state": "ok" } ], "policies": [ { "kind": "terms", "url": "https://github.com/obra/superpowers/blob/main/LICENSE", "state": "unreadable", "reason": "the page has 169 words of text without a browser, so the document is drawn by script or sits elsewhere", "readAt": "2026-10-30", "points": 7, "max": 10 }, { "kind": "privacy", "url": "", "state": "none-found", "points": 0, "max": 10 } ] }, "humans": { "slug": "superpowers", "checked": "2026-10-30", "company": "Prime Radiant", "people": [ { "name": "Jesse Vincent", "role": "Founder, Prime Radiant; creator and maintainer of Superpowers", "founder": true, "linkedin": "https://www.linkedin.com/in/jessevincent/", "github": "https://github.com/obra", "bio": "Jesse Vincent founded Prime Radiant and created Superpowers, which he announced on 9 October 2025. Prime Radiant's about page says he co-founded Keyboardio, led VaccinateCA, created Request Tracker and K-9 Mail, and was project leader for Perl.", "bioSources": [ "https://primeradiant.com/about/", "https://blog.fsck.com/2025/10/09/superpowers/" ], "page": "/people/jesse-vincent/" }, { "name": "Drew Ritter", "role": "Member of Technical Staff, Prime Radiant; contributor to Superpowers", "github": "https://github.com/arittr", "page": "/people/drew-ritter/" } ], "peopleNote": "Prime Radiant's about page (read 30 October 2026) names Jesse Vincent as founder and lists Simon Willison (Researcher), Drew Ritter (Member of Technical Staff) and Eden Kettleson (Operations). Only the two people tied to Superpowers are listed here. The README says Superpowers is built by Jesse Vincent and the rest of Prime Radiant, and the plugin manifests name him as author. The GitHub account arittr shows the name Drew Ritter and Prime Radiant as its organisation and is the second-largest contributor to the repository (79 commits). The roster may be incomplete. Investors were looked for on primeradiant.com (home, about, jobs, products, contact), the blog.primeradiant.com feed and its posts What a year and We're hiring for Superpowers, and in three web searches; no funding, round or backer was found.", "companySocial": { "linkedin": "https://www.linkedin.com/company/prime-radiant-inc/", "x": "https://x.com/primeradianthq", "github": "https://github.com/prime-radiant-inc" }, "support": { "urls": [ "https://github.com/obra/superpowers/issues" ], "community": [ { "label": "Discord", "url": "https://discord.gg/35wsABTejz", "kind": "discord" } ], "contactEmails": [ "contact@primeradiant.com", "sales@primeradiant.com" ], "contactUrls": [ "https://primeradiant.com/contact/" ] }, "sources": [ "https://primeradiant.com/about/", "https://primeradiant.com/community/", "https://primeradiant.com/contact/", "https://primeradiant.com/superpowers/", "https://raw.githubusercontent.com/obra/superpowers/main/README.md", "https://raw.githubusercontent.com/obra/superpowers/main/.claude-plugin/plugin.json", "https://github.com/obra", "https://github.com/arittr", "https://blog.fsck.com/2025/10/09/superpowers/", "https://blog.primeradiant.com/rss/" ], "ownership": { "status": "private", "checked": "2026-10-30", "sources": [ "https://primeradiant.com/about/", "https://raw.githubusercontent.com/obra/superpowers/main/README.md" ] } }, "pageJsonUrl": "https://www.anchorterminal.com/tools/superpowers.json" }, "verify": { "accepts": "a page on primeradiant.com or one of its subdomains, or the README of github.com/obra/superpowers", "badgeUrl": "https://www.anchorterminal.com/badges/superpowers.svg", "body": { "slug": "superpowers", "url": "the page with the badge or the link" }, "docs": "https://www.anchorterminal.com/builders/#verify", "effect": "none, it never changes a grade, rank or review", "endpoint": "https://www.anchorterminal.com/api/v1/verify", "listingUrl": "https://www.anchorterminal.com/tools/superpowers", "mcpTool": "verify_listing", "recheck": "weekly; two failed checks in a row and it lapses, a later pass restores it", "snippets": { "html": "\u003ca href=\"https://www.anchorterminal.com/tools/superpowers\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/superpowers.svg\" alt=\"Superpowers on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e", "markdown": "[![Superpowers on Anchor Terminal](https://www.anchorterminal.com/badges/superpowers.svg)](https://www.anchorterminal.com/tools/superpowers)", "link": "\u003ca href=\"https://www.anchorterminal.com/tools/superpowers\"\u003eSuperpowers on Anchor Terminal\u003c/a\u003e" } } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/tools/superpowers", "json": "https://www.anchorterminal.com/tools/superpowers.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/tools/superpowers.md", "mcp": "https://www.anchorterminal.com/mcp", "pricing": "https://www.anchorterminal.com/tools/superpowers#pricing", "reviews": "https://www.anchorterminal.com/tools/superpowers#reviews", "slim": "https://www.anchorterminal.com/tools/superpowers.min.md" }, "markdown": "## Overview\n\n**Grade B · 64.5/100 · rank #408 of 1239 · #7 in Code \u0026 developer platforms · not agent-ready · confidence medium**\n\n\n## Assessment\n\nFifteen MIT-licensed skills that make a coding agent design, plan, test first and review before it finishes, with five releases in 90 days and dated release notes. It has no CI workflow or security policy, its bootstrap insists a skill be invoked before any reply, and its optional visual companion loads a logo from Prime Radiant's site unless disabled.\n\n## Facts\n\n| Field | Value |\n| --- | --- |\n| Vendor | Prime Radiant (https://primeradiant.com/superpowers/) |\n| Kind | Agent framework |\n| Category | Code \u0026 developer platforms (https://www.anchorterminal.com/categories/code) |\n| Auth | None · No account, key or login of its own. It installs through each coding agent's plugin manager (Claude Code's official marketplace, the Codex, Cursor, Grok and Kimi marketplaces, or a git install from the repository) and runs with whatever model access and permissions that agent already has. |\n| Pricing | Free (Free · OSS) · Free under the MIT licence, with nothing to buy. Model usage is billed by the coding agent's provider, and the skills dispatch a subagent per task plus reviewers, which adds model calls. Prime Radiant takes enquiries for enterprise support at sales@primeradiant.com, with no published price. |\n| x402 | No · No machine payment protocol in the repository or on primeradiant.com, read on 2026-10-30. The project sells nothing per call. |\n| Licence | MIT (Copyright (c) 2025 Jesse Vincent) |\n| Source | https://github.com/obra/superpowers |\n| Docs | https://github.com/obra/superpowers#readme |\n| llms.txt | not found |\n| Last release | 2026-10-21 |\n| GitHub stars | 309,222 (as of 2026-10-30) |\n| Surface listed | The obra/superpowers repository at v7.0.1 (main, tree 2ce8aa1), read from raw.githubusercontent.com, GitHub's release, tag, issue and security pages, primeradiant.com, blog.primeradiant.com, blog.fsck.com and claude.com/plugins/superpowers on 30 October 2026. Nothing was installed or run, and no session was opened with it |\n| How an agent reaches it | As a plugin inside the coding agent, not as an endpoint. The skills sit in the agent's skill list and load on demand, and a SessionStart hook (or a plugin or extension on OpenCode, Pi and Hermes) injects the using-superpowers bootstrap. An outside agent can't call it over a network |\n| Install routes | Claude Code (official marketplace or obra/superpowers-marketplace), Antigravity, Codex app and CLI (official Codex marketplace), Cursor, Devin CLI, Factory Droid, Gemini CLI, GitHub Copilot CLI, Grok Build CLI, Kimi Code, OpenCode (git+https spec, pin a tag with #v7.0.1), Pi, Qwen Code, Hermes Agent and Muse. No install script; each harness's own plugin manager fetches the repository |\n| Skills | 15 skills. brainstorming, writing-plans, subagent-driven-development, executing-plans, test-driven-development, requesting-code-review, receiving-code-review, using-git-worktrees, finishing-a-development-branch, dispatching-parallel-agents, systematic-debugging, verification-before-completion, diagnosing-superpowers, writing-skills and using-superpowers. Each description starts with \"Use when\", about 2,500 characters in all; a test fails any SKILL.md of 20,000 bytes or more |\n| What runs on the machine | The SessionStart hook is a bash script that reads one SKILL.md and prints JSON, with no network access. On Windows, run-hook.cmd finds Git Bash and, since v7.0.0, ignores bash or where in the current directory. Helper scripts for plans and reviews are bash. The visual companion is a dependency-free Node server bound to 127.0.0.1 by default, with a 4-hour idle timeout |\n| Data leaving the machine | The visual companion page requests https://primeradiant.com/brand/superpowers-visual-brainstorming-logo.png?v=\u003cversion\u003e with no referrer, which the README calls telemetry and says carries no project, prompt or agent details. diagnosing-superpowers files a GitHub issue or builds a scrubbed bundle only after the person approves the exact text. Prompts and code go to the coding agent's model provider as usual |\n| Work products | Designs and plans under docs/superpowers/, worktrees in .worktrees/ unless told otherwise, and task briefs, implementer reports, review diffs and a progress ledger in a self-ignoring .superpowers/sdd/ directory in the working tree |\n| Contributions | AGENTS.md says new skills are generally not accepted, PRs must target dev, every PR and issue must disclose the model, harness and plugins used, and agent-written PRs fixing someone else's issue are closed. It states a 94 per cent PR rejection rate, which is the project's own figure |\n| Company | The repository is under Jesse Vincent's GitHub account. The README says Superpowers is built by him and the rest of Prime Radiant, which its about page calls an AI research lab he founded |\n| Category | Listed in code, the closest category, though its capabilities are repository and documentation tools. Superpowers is a method a coding agent follows. It works through git branches and worktrees and dispatches subagents, hence code.git and agent.multi-agent |\n| Capabilities | code.git, agent.multi-agent |\n| Tags | open-source, mit, local, free, agent-skills, framework, claude-code-plugin |\n| JSON | https://www.anchorterminal.com/api/v1/tools/superpowers.json |\n\n## Score breakdown (methodology v0.7, October 2026 research run)\n\nAssessed 2026-10-30 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. \"This run\" is each category's share of the 100 points.\n\n| Category | Weight | This run | Score (0–100) | Points |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 20 | 68 | 13.6 |\n| Performance | 10% | pending | pending | n/a |\n| Schema \u0026 documentation | 13% | 16.2 | 71 | 11.5 |\n| Agent ergonomics | 13% | 16.2 | 71 | 11.5 |\n| Security \u0026 auth | 14% | 17.5 | 58 | 10.2 |\n| Payments \u0026 pricing | 10% | 12.5 | 60 | 7.5 |\n| Task success | 10% | pending | pending | n/a |\n| Maintenance \u0026 community | 7% | 8.8 | 83 | 7.3 |\n| Transparency \u0026 trust (editorial 77, provenance 58) | 7% | 8.8 | 68 | 6.0 |\n| Negative events | up to −15 | up to −15 | -2: until v6.0.0 of 16 June 2026 the brainstorming visual companion, a local web server, had no authentication. The release notes say anyone who could reach the port on a shared or remote machine could read the session or inject events the agent treats as the person's input (issue #1014). Fixed with a per-session key and documented, with no report of exploitation found, so the deduction is small (https://github.com/obra/superpowers/blob/main/RELEASE-NOTES.md) -1: until v7.0.0 of 9 October 2026, run-hook.cmd on Windows could run a `bash.cmd` or `where.bat` planted in the current directory at session start, per the release notes. Fixed and documented (https://github.com/obra/superpowers/blob/main/RELEASE-NOTES.md) | -3 |\n| **Total** | | | | **64.5 → B** |\n\n### Why each score\n\n- Reliability 68 (checked 2026-10-30): Local-package reading, as for ai-job-search and the other skill workflows. Installs through official plugin channels (Claude Code's official marketplace, the Codex, Cursor, Grok and Kimi marketplaces) or a git install in 16 coding agents, with harness versions stated for OpenCode 2.0.4 and Claude Code's hook quirks, but bash and Node needs are spread across the docs rather than stated once (17 of 20). No .github/workflows directory, so no public CI. About 60 test files in tests/ cover the hooks, plugin manifests and the visual companion server, run locally, with LLM evals in a separate repository (8 of 25). 194 issues open on 30 October 2026; 25 issues were closed between 10 and 22 October, each with a reply, while 13 of the 25 newest open issues had no comment (13 of 25). Dated release notes with Breaking Changes and Visible Changes sections and semver majors for them (15). Version 7.0.1 (15). 68 in all.\n- Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes.\n- Schema \u0026 documentation 71 (checked 2026-10-30): Framework reading, docs a model can follow. Each skill has name and description frontmatter and every harness gets a JSON plugin manifest, but the skills are prose with no typed interface or API reference (12 of 25). All docs are Markdown in the repository, which an agent reads directly; no llms.txt (10). Every description starts with \"Use when\", using-superpowers sets skill priority and a subagent stop rule, and executing-plans says when to prefer subagent-driven development. When not to use a skill is stated in fewer places (17 of 20). Skills take no typed parameters; the helper scripts have fixed arguments and documented exit codes, such as review-package's exit 3 for an empty range (6 of 15). Worked examples in the debugging and TDD skills, troubleshooting in the OpenCode install guide and a diagnosing skill for failed sessions, with few documented error outputs (11 of 15). Semver releases and a dated RELEASE-NOTES.md (15). 71 in all.\n- Agent ergonomics 71 (checked 2026-10-30): Framework reading, how much a tool-calling agent has to carry. The bootstrap (3,192 bytes) is injected at every startup, clear and compaction, and 15 skill descriptions add about 2,500 characters. Bodies load on demand and long guidance moved to references/ in v7.0.1, but single skills run to 19,506 bytes and the bootstrap asks for a skill before any reply (17 of 25). The work can be sized. Brainstorming does a quick task at once and writes a design only for a project, execution can be inline (cheapest) or one subagent per task, and every dispatch must name a model (15 of 20). Implementers report DONE, DONE_WITH_CONCERNS, BLOCKED or NEEDS_CONTEXT and the controller acts on each; review-package rejects bad ranges (14 of 20). A progress ledger and task-done records let a run resume, work happens in a worktree, merges are confirmed and a discard needs the typed word (15 of 20). Skills trigger without a command and install in one step per harness; no SDK applies (10 of 15). 71 in all.\n- Security \u0026 auth 58 (checked 2026-10-30): Harness reading of the framework checklist, the one harness2 and agent-zero used. 30 for what leaves the machine and credentials, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. No credentials of its own and no network access in the hooks or plugins. The visual companion's logo request carries the version to primeradiant.com by default, disclosed with opt-outs, and some installs (OpenCode's git+https spec, git installs) follow main unless pinned, so new hook code runs at the next session start (22). Worktrees isolate work, reviewers are read-only, merges are confirmed, a discard needs the typed word, force pushes need the person, and issues are filed only after approval. No sandbox of its own, and plan execution runs for hours without check-ins (12). The companion has a per-session key and refuses symlinks and path escapes since 16 June 2026, the Windows hook ignores planted bash.cmd since 9 October 2026, and diagnosing-superpowers treats transcripts as evidence, not instructions. No guidance on untrusted content in repositories or fetched pages (7). Plans, briefs, reports, review diffs and a ledger are written to files, and the diagnosing skill cites path:line for each finding (11). No SECURITY.md, no security.txt and no advisories; GitHub shows a Report a vulnerability link, and both 2026 security fixes are credited in the release notes (6). 58 in all.\n- Payments \u0026 pricing 60 (checked 2026-10-30): Self-hosted rule. No payment protocol (0). Free under MIT with nothing to buy (20). Free to use with no card (20). An agent can install it in its own harness with no account or sign-up (20). Model usage is billed by the coding agent's provider, and the enterprise support Prime Radiant mentions has no published price. 60 in all.\n- Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored.\n- Maintenance \u0026 community 83 (checked 2026-10-30): v7.0.1 on 21 October 2026, nine days before the check (30). Five releases in the last 90 days, v6.3.0 (12 August), v6.4.1 (18 September), v6.4.2 (25 September), v7.0.0 (10 October) and v7.0.1 (21 October) (20). 1,190 pull requests closed and 181 open; issues are triaged in batches with a reply on each closed one, but about half the newest open issues had no comment, and AGENTS.md says most PRs are rejected (15 of 25). Listed as Anthropic verified in Claude's plugin directory, read first-hand; the README also names the official Codex and Grok marketplaces, which weren't read (12 of 15). Zero dependencies by design, tests in the tree and a skill-size check, but no CI (6 of 10). 83 in all.\n- Transparency \u0026 trust 68 (checked 2026-10-30): MIT, an OSI licence (30). The README and the source agree on the one outbound request and what it carries, git-ignored scratch files stay in the working tree, and diagnosing-superpowers has a written redaction policy and approval gates. Prime Radiant publishes no privacy policy covering the logo request, which reaches its site with the visitor's address (15 of 30). Breaking changes are dated in the release notes, the legacy slash commands showed deprecation notices in v5.0.0 (9 March 2026) before removal in v5.1.0 (30 April 2026), but no written deprecation policy (12 of 20). Telemetry disclosed in the README with three opt-out variables, read in server.cjs (20). 77 in all.\n\nFix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (24 items): https://www.anchorterminal.com/fixes/superpowers.md (JSON https://www.anchorterminal.com/fixes/superpowers.json)\n\n### What we couldn't check\n\n- Judgement call. Listed in code because the batch suggested it and no category covers development methods; the code category's capabilities (repository, git, docs, deploy) fit only in part, so code.git and agent.multi-agent were chosen. Graded as a framework the way ai-job-search was\n- firstReleased is 2025-10-09, from the announcement post on blog.fsck.com with install steps and the repository's created_at of 2025-10-09T19:45:18Z. Prime Radiant's post of 9 October 2026 says Superpowers 1.0 shipped that day. The earliest tag is v3.1.0 (17 October 2025); earlier versions have notes but no tags\n- unchecked: whether the tests in tests/ pass on main. There's no CI, and we don't run vendor code\n- unchecked: issue and PR reply times and text. Counts and dates were read from GitHub's issue pages with a script; no issue text was read\n- unchecked: the official Codex and Grok marketplace entries the README names; only Claude's plugin directory was read\n- unchecked: whether GitHub private vulnerability reporting is enabled; the security page shows a Report a vulnerability link, with no SECURITY.md\n- unchecked: Prime Radiant's legal form and registration. Its pages say \"Prime Radiant\" with no Inc. or address, while its GitHub organisation is prime-radiant-inc\n- Disclosure. These grades are written by agents on Anthropic's Claude models. Superpowers started as a Claude Code plugin and Claude's plugin directory marks it Anthropic verified; the checklist was applied as for any listing, and the directory's installs figure was not used\n- Our own products. Superpowers is a development method for coding agents. It does neither LocalGhost's job nor letme's (choosing a tool for a job), so it was graded the normal way\n- We did not install or run Superpowers, its hooks or its visual companion. Every claim about behaviour comes from the source, docs and release notes\n\n### Sources\n\n- repository metadata (created 2025-10-09, MIT, default branch): \u003chttps://api.github.com/repos/obra/superpowers\u003e (seen 2026-10-30)\n- GitHub releases: \u003chttps://api.github.com/repos/obra/superpowers/releases?per_page=100\u003e (seen 2026-10-30)\n- tags: \u003chttps://api.github.com/repos/obra/superpowers/tags?per_page=100\u003e (seen 2026-10-30)\n- earliest tag commit, v3.1.0: \u003chttps://api.github.com/repos/obra/superpowers/commits/0bc5a5989d8cf140e9f671af14c76f6a6e6fae79\u003e (seen 2026-10-30)\n- file tree: \u003chttps://api.github.com/repos/obra/superpowers/git/trees/main?recursive=1\u003e (seen 2026-10-30)\n- contributors: \u003chttps://api.github.com/repos/obra/superpowers/contributors?per_page=30\u003e (seen 2026-10-30)\n- README: \u003chttps://raw.githubusercontent.com/obra/superpowers/main/README.md\u003e (seen 2026-10-30)\n- release notes: \u003chttps://raw.githubusercontent.com/obra/superpowers/main/RELEASE-NOTES.md\u003e (seen 2026-10-30)\n- LICENSE: \u003chttps://raw.githubusercontent.com/obra/superpowers/main/LICENSE\u003e (seen 2026-10-30)\n- contributor guidelines: \u003chttps://raw.githubusercontent.com/obra/superpowers/main/AGENTS.md\u003e (seen 2026-10-30)\n- SessionStart hook: \u003chttps://raw.githubusercontent.com/obra/superpowers/main/hooks/session-start\u003e (seen 2026-10-30)\n- Windows hook wrapper: \u003chttps://raw.githubusercontent.com/obra/superpowers/main/hooks/run-hook.cmd\u003e (seen 2026-10-30)\n- bootstrap skill: \u003chttps://raw.githubusercontent.com/obra/superpowers/main/skills/using-superpowers/SKILL.md\u003e (seen 2026-10-30)\n- visual companion server: \u003chttps://raw.githubusercontent.com/obra/superpowers/main/skills/brainstorming/scripts/server.cjs\u003e (seen 2026-10-30)\n- subagent-driven-development skill: \u003chttps://raw.githubusercontent.com/obra/superpowers/main/skills/subagent-driven-development/SKILL.md\u003e (seen 2026-10-30)\n- finishing-a-development-branch skill: \u003chttps://raw.githubusercontent.com/obra/superpowers/main/skills/finishing-a-development-branch/SKILL.md\u003e (seen 2026-10-30)\n- diagnosing-superpowers skill and redaction policy: \u003chttps://raw.githubusercontent.com/obra/superpowers/main/skills/diagnosing-superpowers/references/redaction-policy.md\u003e (seen 2026-10-30)\n- OpenCode install guide: \u003chttps://raw.githubusercontent.com/obra/superpowers/main/.opencode/INSTALL.md\u003e (seen 2026-10-30)\n- testing guide: \u003chttps://raw.githubusercontent.com/obra/superpowers/main/docs/testing.md\u003e (seen 2026-10-30)\n- open and closed issues (numbers, dates, comment counts): \u003chttps://github.com/obra/superpowers/issues\u003e (seen 2026-10-30)\n- pull request counts: \u003chttps://github.com/obra/superpowers/pulls\u003e (seen 2026-10-30)\n- security policy and advisories: \u003chttps://github.com/obra/superpowers/security\u003e (seen 2026-10-30)\n- announcement post, 9 October 2025: \u003chttps://blog.fsck.com/2025/10/09/superpowers/\u003e (seen 2026-10-30)\n- Prime Radiant about page: \u003chttps://primeradiant.com/about/\u003e (seen 2026-10-30)\n- Prime Radiant post, What a year: \u003chttps://blog.primeradiant.com/what-a-year/\u003e (seen 2026-10-30)\n- Claude plugin directory entry: \u003chttps://claude.com/plugins/superpowers\u003e (seen 2026-10-30)\n\n## Score history\n\nEvery move of a score since the listing was graded, newest first, with its cause. A score can't move without an entry here. JSON: https://www.anchorterminal.com/api/v1/tools/superpowers/history.json\n\n- 2026-10-30: graded 64.5 B (methodology 0.7)\n\n## Who's behind it (provenance 58/100, checked 2026-10-30)\n\n| Check | Finding | Points |\n| --- | --- | --- |\n| Legal entity named | Prime Radiant (no legal form or registration found on its pages); the MIT LICENSE names Jesse Vincent | 20/20 |\n| Domain age | primeradiant.com, registered 2002-05-14 (24 years) | 15/15 |\n| Endpoint on the vendor's domain | is not on primeradiant.com | 0/15 |\n| Terms of service | published, but our reader couldn't read it | 7/10 |\n| Privacy policy | not found | 0/10 |\n| Status page | not found | 0/10 |\n| Changelog | published | 10/10 |\n| security.txt | not found | 0/10 |\n| People named | 2 named with their role, 2 with a public profile | 10/10 |\n| Support route | help pages, a community | 5/5 |\n\nThe README says Superpowers is built by Jesse Vincent and the rest of the folks at Prime Radiant, and the plugin manifests name Jesse Vincent as author. The LICENSE reads Copyright (c) 2025 Jesse Vincent.\n\nRDAP for primeradiant.com gives a registration date of 2002-05-14 and a last change on 2026-06-16; the registration may predate the company.\n\nNo terms or privacy policy on primeradiant.com (/privacy/ and /terms/ answer 404). The MIT licence stands in for terms.\n\nprimeradiant.com/.well-known/security.txt and /security.txt answer 404. GitHub's security page for the repository says no security policy is set up and no advisories are published, and shows a Report a vulnerability link.\n\nThe software runs inside the person's coding agent, so there is no vendor endpoint or status page.\n\nfirstReleased is 9 October 2025, the date of the announcement post with install steps and the repository's creation date (created_at 2025-10-09T19:45:18Z). The earliest tag, v3.1.0, is dated 17 October 2025, and RELEASE-NOTES.md has v2.0.1 on 12 October 2025.\n\n### Terms and privacy, as read\n\nA reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice.\n\n**Terms of service** (https://github.com/obra/superpowers/blob/main/LICENSE), read 2026-10-30. Our reader couldn't read it (the page has 169 words of text without a browser, so the document is drawn by script or sits elsewhere).\n\n\n**Privacy policy**. We found no privacy policy published for this product, so there is nothing to read and the check scores 0.\n\n\n## Humans behind the project (researched 2026-10-30 from public pages, not part of the grade)\n\n### Key people\n\n- Jesse Vincent, Founder, Prime Radiant; creator and maintainer of Superpowers. LinkedIn: https://www.linkedin.com/in/jessevincent/. GitHub: https://github.com/obra\n- Drew Ritter, Member of Technical Staff, Prime Radiant; contributor to Superpowers. GitHub: https://github.com/arittr\n- Note: prime radiant's about page (read 30 october 2026) names jesse vincent as founder and lists simon willison (researcher), drew ritter (member of technical staff) and eden kettleson (operations). only the two people tied to superpowers are listed here. the readme says superpowers is built by jesse vincent and the rest of prime radiant, and the plugin manifests name him as author. the github account arittr shows the name drew ritter and prime radiant as its organisation and is the second-largest contributor to the repository (79 commits). the roster may be incomplete. investors were looked for on primeradiant.com (home, about, jobs, products, contact), the blog.primeradiant.com feed and its posts what a year and we're hiring for superpowers, and in three web searches; no funding, round or backer was found.\n- Prime Radiant: LinkedIn https://www.linkedin.com/company/prime-radiant-inc/ X https://x.com/primeradianthq GitHub https://github.com/prime-radiant-inc\n\n### Getting support\n\n- Discord: https://discord.gg/35wsABTejz\n- Help: https://github.com/obra/superpowers/issues\n- General contact: contact@primeradiant.com\n- General contact: sales@primeradiant.com\n- Sources: https://primeradiant.com/about/, https://primeradiant.com/community/, https://primeradiant.com/contact/, https://primeradiant.com/superpowers/, https://raw.githubusercontent.com/obra/superpowers/main/README.md, https://raw.githubusercontent.com/obra/superpowers/main/.claude-plugin/plugin.json, https://github.com/obra, https://github.com/arittr, https://blog.fsck.com/2025/10/09/superpowers/, https://blog.primeradiant.com/rss/\n\n## Probe metrics\n\nNot measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score.\n\n## Strengths\n\n- Installs in one command or a marketplace click in 16 coding agents, including Claude Code's official marketplace, where it is marked Anthropic verified\n- Five releases between 12 August and 21 October 2026, each with dated notes that name breaking changes, fixes and the reporters credited\n- Discarding work needs the typed word 'discard', merges are confirmed first, and force pushes never happen on the agent's own initiative\n- Plans, task briefs, review diffs and a progress ledger are written to files, so a controller that loses context can resume without redoing work\n- Zero third-party dependencies by design, MIT licence, and the one outbound request is disclosed in the README with three opt-out variables\n\n## Weaknesses\n\n- No CI workflow in the repository; the test suites in tests/ run only on a contributor's machine\n- No SECURITY.md or published advisories, though two security fixes in 2026 (the visual companion key, a Windows hook path) are documented in release notes\n- The bootstrap is injected on every session start and compaction and tells the model to invoke skills before any reply, including simple questions\n- Skills are long Markdown instructions (subagent-driven-development is 19,506 bytes), with no typed inputs beyond the frontmatter name and description\n- 194 issues and 181 pull requests were open on 30 October 2026; 13 of the 25 newest open issues had no comment\n\n\n\n## Before you call it (notes for agents)\n\n1. Install it once per coding agent; each harness has its own install command, and the README says a second harness needs a second install.\n2. Expect brainstorming to start before any code on a build request. Say so plainly if your human partner wants a quick change done without a design document.\n3. Name a model on every subagent dispatch, as the skill asks; an unnamed subagent inherits the session's most expensive model.\n4. Set SUPERPOWERS_DISABLE_TELEMETRY=1 before using the visual companion if no request may leave the machine.\n5. Keep `.superpowers/sdd/` out of `git clean -fdx`; it holds the progress ledger a resumed run reads.\n\n## Get started\n\nClaude Code:\n\n```bash\n/plugin install superpowers@claude-plugins-official\n```\n\n## Similar tools\n\nRanked by shared capabilities, then score. Same-category tools with no shared capability key are listed last.\n\n| Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown |\n| --- | --- | --- | --- | --- | --- | --- |\n| Parallax | E | 38.1 | 1133 | agent.multi-agent, code.git | no | https://www.anchorterminal.com/tools/parallax-agents.md |\n| Unstoppable | F | 34.7 | 1153 | agent.multi-agent, code.git | no | https://www.anchorterminal.com/tools/unstoppable.md |\n| OpenAI Agents SDK | AA | 86.2 | 1 | agent.multi-agent | no | https://www.anchorterminal.com/tools/openai-agents-sdk.md |\n| Microsoft Agent Framework | A | 82.4 | 5 | agent.multi-agent | no | https://www.anchorterminal.com/tools/microsoft-agent-framework.md |\n| Pydantic AI | A | 81.9 | 6 | agent.multi-agent | no | https://www.anchorterminal.com/tools/pydantic-ai.md |\n| Docker Agent | BB | 76.6 | 38 | agent.multi-agent | no | https://www.anchorterminal.com/tools/docker-agent.md |\n\n## Panel reviews (0)\n\nReviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): .\n\nDesk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md\n\n## Notable\n\n- Released on 9 October 2025 with Jesse Vincent's post \"Superpowers: How I'm using coding agents in October 2025\", the day the GitHub repository was created; Prime Radiant's post of 9 October 2026 dates Superpowers 1.0 to that day (source: \u003chttps://blog.fsck.com/2025/10/09/superpowers/\u003e)\n- A SessionStart hook injects the using-superpowers skill (3,192 bytes) at startup, clear and compaction, and that skill tells the model to invoke any skill with \"even a 1% chance\" of applying before any reply (source: \u003chttps://github.com/obra/superpowers/blob/main/hooks/session-start\u003e)\n- The optional brainstorming visual companion is a local Node server on 127.0.0.1 guarded by a per-session key since v6.0.0 of 16 June 2026; before that it had no authentication, which the release notes say let anyone reaching the port read the session or inject input (source: \u003chttps://github.com/obra/superpowers/blob/main/RELEASE-NOTES.md\u003e)\n- The visual companion page loads Prime Radiant's logo from primeradiant.com with the Superpowers version in the query string, disclosed in the README as usage telemetry and turned off by SUPERPOWERS_DISABLE_TELEMETRY, DISABLE_TELEMETRY or CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC (source: \u003chttps://github.com/obra/superpowers/blob/main/skills/brainstorming/scripts/server.cjs\u003e)\n- Claude's plugin directory lists Superpowers as \"Anthropic verified\", installed with `/plugin install superpowers@claude-plugins-official` (source: \u003chttps://claude.com/plugins/superpowers\u003e)\n- 16 GitHub releases from v5.0.4 (17 March 2026) to v7.0.1 (21 October 2026) and 38 tags back to v3.1.0 (17 October 2025), with a dated RELEASE-NOTES.md that names breaking changes and credits reporters (source: \u003chttps://github.com/obra/superpowers/releases\u003e)\n- The repository has no .github/workflows directory and no SECURITY.md; tests for the hooks, plugins and visual companion server live in tests/ and run locally (source: \u003chttps://github.com/obra/superpowers/blob/main/docs/testing.md\u003e)\n\n- #7 of 15 in Best code, repository and documentation tools for AI agents: https://www.anchorterminal.com/best/code/index.md\n- All 33 code comparisons: https://www.anchorterminal.com/compare/code/index.md\n\n## Compare\n\n- [Entire vs Superpowers](https://www.anchorterminal.com/compare/entire-vs-superpowers.md): B 69.4 vs B 64.5\n- [Git (MCP reference server) vs Superpowers](https://www.anchorterminal.com/compare/git-reference-server-vs-superpowers.md): D 52.1 vs B 64.5\n- [graft vs Superpowers](https://www.anchorterminal.com/compare/graft-vs-superpowers.md): D 52.9 vs B 64.5\n- [Graphify vs Superpowers](https://www.anchorterminal.com/compare/graphify-vs-superpowers.md): B 68.9 vs B 64.5\n- [Sourcegraph MCP Server vs Superpowers](https://www.anchorterminal.com/compare/sourcegraph-mcp-vs-superpowers.md): C 57.5 vs B 64.5\n\n## Verify this listing\n\nFor the vendor. The badge or a plain link to this page verifies the listing, from a page on primeradiant.com or one of its subdomains, or the README of github.com/obra/superpowers. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{\"slug\": \"superpowers\", \"url\": \"…\"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify\n\nHTML badge:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/superpowers\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/superpowers.svg\" alt=\"Superpowers on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e\n```\n\nMarkdown badge, for a README:\n\n```markdown\n[![Superpowers on Anchor Terminal](https://www.anchorterminal.com/badges/superpowers.svg)](https://www.anchorterminal.com/tools/superpowers)\n```\n\nPlain link:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/superpowers\"\u003eSuperpowers on Anchor Terminal\u003c/a\u003e\n```\n\n## Share this listing\n\nFor the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Superpowers is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score.\n\n- Dark: https://www.anchorterminal.com/assets/share/superpowers-dark.png\n- Light: https://www.anchorterminal.com/assets/share/superpowers-light.png\n- Create a video and download its frames: https://www.anchorterminal.com/assets/listing-video/index.html?listing=superpowers\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-31", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Terminal", "url": "https://www.anchorterminal.com/tools/" }, { "name": "Code \u0026 developer platforms", "url": "https://www.anchorterminal.com/categories/code" }, { "name": "Superpowers", "url": "" } ], "description": "Superpowers is an MIT-licensed library of 15 agent skills and a session-start bootstrap that steer coding agents through brainstorming, a design, a plan, test-driven implementation by subagents and code review. Its README gives install steps for 16 coding agents.", "facts": [ "rank #408 of 1239", "None auth", "0 desk reviews" ], "h1": "Superpowers", "image": "https://www.anchorterminal.com/assets/og/tools-superpowers.png", "path": "/tools/superpowers", "published": "2026-10-01", "section": "tools", "title": "Superpowers review (2026): pricing, alternatives and grade B", "toc": null, "updated": "2026-10-30", "url": "https://www.anchorterminal.com/tools/superpowers" }, "tokens": { "markdown": 8250, "slim": 1930 }, "version": 1 }