OpenCode by Anomaly

# Fix list: OpenCode

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/opencode, the October 2026 research run, assessed 1 October 2026. Grade B, 68 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on OpenCode: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Security & auth, 60 out of 100, up to 7 more on the total

Why it scored 60: Harness reading of the framework checklist, used for all five harnesses in this batch. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. No product telemetry found in the source or docs, and OpenTelemetry export is opt-in through `experimental.openTelemetry`. It fetches the model list from models.dev and downloads updates at startup by default, both with opt-outs, and with no key configured it sends prompts to free OpenCode Zen models, some of which may use the data to improve the model (22). Allow, ask or deny per tool with glob patterns, `.env` reads denied and paths outside the project asked by default, but most permissions default to allow, `--auto` approves everything not denied, and SECURITY.md says the permission system is not a sandbox (9). SECURITY.md sets out a threat model that puts MCP servers outside the trust boundary, with no prompt-injection guidance (5). Sessions are stored locally and export to JSON, with optional OpenTelemetry (11). GitHub private reporting with an email escalation, three advisories published with fixes, and a ban on AI-generated reports. No security.txt (13).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 2. Reliability, 68 out of 100, up to 6.4 more on the total

Why it scored 68: Read as a local package. `opencode-ai` on npm with native binaries for macOS, Linux and Windows on x64 and arm64, plus Homebrew, Scoop, Chocolatey, Nix and an install script (20). A test workflow runs on the dev branch. The Actions page we loaded showed only passing runs, but from an older release (1.3.10), so the current state is unconfirmed (18). About 4,700 open issues and 1,600 open pull requests, handled mostly by scripts that close stale issues daily and flag duplicates (8). Releases come almost daily with notes on GitHub and a changelog page, but we found no breaking-change convention, and a separate 2.0 line has been tagged since 11 September beside the 1.18 line on npm (7). 1.18, stable (15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 3. Payments & pricing, 60 out of 100, up to 5 more on the total

Why it scored 60: No payment protocol (0). Scored on OpenCode Zen and Go. Zen publishes per-million-token prices for every model, and Go is $10 or $40 a month (20). The MIT package and the free Zen models need no card (20). With no key configured it loads the free Zen models with a public key, so an agent can install it and run a task with no signup at all (20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 4. Agent ergonomics, 79 out of 100, up to 3.4 more on the total

Why it scored 79: Harness reading of the framework line, scored on what an agent or pipeline driving it has to supply. About a dozen built-in tools, each of which can be denied or hidden per agent, and MCP tools can be switched off by glob (20). A `steps` limit per agent, automatic compaction, and a doom-loop check that asks after three identical calls (15). `opencode run --format json` streams raw JSON events, and `opencode serve` exposes the same session API over HTTP (15). Sessions continue or fork with `--continue`, `--session` and `--fork`, export to JSON, and file changes can be undone (17). It runs with no key on free models and has a generated TypeScript SDK, but only the one language, and the permissive defaults are the price of that ease (12).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 5. Transparency & trust, 71 out of 100, up to 2.5 more on the total

Made of editorial 82, provenance 59.

Why it scored 71: MIT (30). A privacy policy (effective 6 March 2026) and terms (15 August 2026) from Anomaly Innovations, Inc., plus a Zen privacy section saying models are hosted in the US, providers keep nothing and don't train except on named free models, and OpenAI and Anthropic keep requests for 30 days. The general retention line is as long as necessary (22). Zen lists each retired model with its date, and the docs mark deprecated config keys (15). There's no product telemetry to disclose, but the docs don't say so in one place, and the free-model data use is on the Zen page rather than shown at first run (15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- Domain age: opencode.ai, no registry record we could read (0 of 15)
- Status page: not found (0 of 10)
- security.txt: not found (0 of 10)

## 6. Schema & documentation, 88 out of 100, up to 2 more on the total

Why it scored 88: A JSON Schema for the config file at opencode.ai/config.json, and an OpenAPI 3.1 spec for the server (162 paths) from which the TypeScript SDK is generated (25). The docs site serves a Markdown version of each page, per its source (10). Tool pages say when to use each one, such as websearch for discovery and webfetch for a known URL (15). Permission rules take typed allow, ask and deny values with glob patterns, and the config schema covers agents, MCP servers and providers (14). Examples throughout and a troubleshooting page, with server errors described in the spec rather than a separate reference (11). A dated changelog at opencode.ai/changelog and GitHub releases (13).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 7. Maintenance & community, 81 out of 100, up to 1.7 more on the total

Why it scored 81: 1.18.34 on npm on 2026-09-30, and a 2.0.22 tag on 2026-10-02 (30). 35 releases on the 1.18 line since 2026-07-14 (20). About 4,700 open issues and 1,600 open pull requests, triaged by scripts and an agent workflow, and we couldn't see reply times (10). npm, Homebrew, Scoop, Chocolatey and Nix builds track releases, and npm publishes through GitHub OIDC (14). Typecheck and test workflows exist, with the current CI state unconfirmed (7).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## Deductions

Each comes off the total. A fixed and documented problem counts for less at the next check.

- 2026-01-12. GHSA-vxw4-wv6m-9hhh (CVE-2026-22812, 8.8), the HTTP server the TUI started had no authentication, so local processes could run shell commands as the user, fixed in 1.0.216. GHSA-c83v-7274-4vgp (CVE-2026-22813), unsanitised Markdown in the web UI let a malicious page run commands on the machine, fixed in 1.1.10. Fixed, published and more than six months old, -1 each. https://github.com/anomalyco/opencode/security/advisories
- 2026-09-24. GHSA-632h-h47v-g4x4 (7.5, no CVE). The server's `/global/upgrade` endpoint accepted any package specifier without checking where the request came from, so a web page could make `opencode serve` install an attacker's npm package and run its scripts. Fixed in 1.18.22. Inside six months, -2. https://github.com/anomalyco/opencode/security/advisories/GHSA-632h-h47v-g4x4

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- The Actions page we loaded showed runs from an older release (1.3.10), so whether tests pass on dev today is unconfirmed
- What the 2.0 line tagged since 11 September 2026 is, and when npm's latest tag moves to it
- Which model a keyless run picks by default, and whether it's one of the free models that may train on prompts
- Unchecked: a status page for OpenCode Zen and the domain's registration date
- Reply times on issues weren't visible

## Weaknesses

- Most permissions default to allow, and SECURITY.md says the permission system is not a sandbox
- Updates download and install at startup unless `autoupdate` is off
- Keyless runs send prompts to free models, some of which may use them for training
- Three advisories in 2026 against its local HTTP server and web UI
- About 4,700 open issues and 1,600 open pull requests

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Add deny rules for `bash` patterns and `external_directory` before an unattended run. Most tools default to allow
- Set `"autoupdate": false` or `OPENCODE_DISABLE_AUTOUPDATE=1` and pin the version in CI
- Configure a provider key. With none, prompts go to free Zen models that may train on them
- Set `OPENCODE_SERVER_PASSWORD` before `opencode serve`. Without it the server runs unauthenticated
- Use `opencode run --format json` and read the event stream rather than the formatted output

## What the review panel asked for

- auto-update off by default
- a dated 2.0 plan
- server password by default
- ask before shell commands

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.