{
  "fixes": {
    "slug": "cline",
    "name": "Cline",
    "listing": "https://www.anchorterminal.com/tools/cline",
    "markdown": "# Fix list: Cline\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/cline, the October 2026 research run, assessed 1 October 2026. Grade C, 60.8 out of 100.\n\nThis 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.\n\nFor a coding agent working on Cline: 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.\n\n## 1. Security \u0026 auth, 57 out of 100, up to 7.5 more on the total\n\nWhy it scored 57: 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. The extension sends usage and error events to PostHog unless the user unticks 'Allow error and usage reporting' or turns off VS Code telemetry. The CLI is built with a telemetry key and an enable flag from repository secrets and its reference lists no telemetry setting, so its default is unconfirmed (15). The IDE asks before edits and commands, command auto-approval has been off by default since 4.0.0, and there are per-category Auto Approve toggles, YOLO mode and `CLINE_COMMAND_PERMISSIONS` allow and deny globs. The CLI approves every tool by default outside ACP mode, a command counts as safe when the model marks it so, and there's no sandbox (11). No prompt-injection guidance found in the docs (4). Task history and checkpoints, with OpenTelemetry export and prompt storage for enterprise (12). A valid security.txt (expires 2027-12-31), a Bugcrowd disclosure programme and three advisories published with CVEs, two of which list no patched version (15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-security):\n\n- 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.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 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.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.\n\nModels 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.\n\n## 2. Payments \u0026 pricing, 50 out of 100, up to 6.3 more on the total\n\nWhy it scored 50: No payment protocol (0). Scored on Cline's paid options. ClinePass is $9.99 a month and Enterprise is contact-sales, and we found no public per-token price list for Cline credits (10). The open-source extension and CLI need no card (20). Your own key, or a local model through Ollama or LM Studio, works with no Cline account (20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):\n\nThe published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).\n\n- 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.\n- 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.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).\n\nPayment 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.\n\nOpen-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.\n\n## 3. Agent ergonomics, 67 out of 100, up to 5.4 more on the total\n\nWhy it scored 67: Harness reading of the framework line, scored on what an agent or pipeline driving it has to supply. Many built-in tools (files, terminal, browser, MCP, subagents, plan and act), with MCP servers switched on or off per server, and no tool search or lazy loading found (15). `--timeout` (off by default), a mistake limit through `--retries`, automatic compaction and an output budget scaled to the model (14). `--json` writes one JSON object per message, but we found no documented exit codes (12). Checkpoints restore files and task state, sessions resume by ID, and API errors and empty responses are retried (18). The CLI defaults to Cline's own provider and to approving every tool, and the SDK is TypeScript only (8).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 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).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels 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.\n\n## 4. Reliability, 80 out of 100, up to 4 more on the total\n\nWhy it scored 80: Read as a local package. The `cline` CLI on npm (Node 22 or later), the VS Code extension (VS Code 1.101 or later), a JetBrains plugin and desktop builds (20). The VS Code test workflow passed on every main run we loaded, including the 1 October CLI and SDK releases (25). 645 to 730 open issues and 525 open pull requests, a stale bot that closes issues after 74 quiet days, and open crash reports such as #12493, where aborting a turn can crash the hub daemon (13). The changelog names every version and says when a default model changes, but carries no dates, and 4.0.0 listed its removals (Explain Changes, subagents for a time) under Changed rather than a breaking section (9). Extension 4.1 and CLI 3.0 are past 1.0, while the SDK (0.0.90) and desktop app (0.0.42) aren't (13).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):\n\nHosted APIs, MCP servers, models and platforms.\n\n- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 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.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.\n\nLocal packages, SDKs, frameworks and stdio MCP servers.\n\n- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.\n\nProtocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.\n\n## 5. Schema \u0026 documentation, 77 out of 100, up to 3.7 more on the total\n\nWhy it scored 77: A typed TypeScript SDK with a reference section, a documented one-object-per-line format for `--json`, and an errors page for the Cline API, but no machine-readable spec for the CLI or its config (18). llms.txt at docs.cline.bot, listing a Markdown version of every page (10). Feature pages say when to use each setting, such as the recommended Auto Approve setup (14). `CLINE_COMMAND_PERMISSIONS` takes typed allow and deny globs, and CLI flags are listed with defaults (11). CLI samples, SDK examples and the API errors page (13). A versioned changelog without dates, with dated tags on GitHub (11).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):\n\nAPIs and MCP servers.\n\n- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 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.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.\n\nModels 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.\n\n## 6. Transparency \u0026 trust, 66 out of 100, up to 3 more on the total\n\nMade of editorial 60, provenance 71.\n\nWhy it scored 66: Apache-2.0 (30). The privacy policy at cline.bot/privacy renders only with JavaScript and we couldn't read it. The docs say code stays on the machine apart from model calls and list what telemetry never includes, without retention periods or subprocessors (10). Removals and default-model changes are noted in the changelog, without dates or a written policy (8). The extension's telemetry and its toggle are documented and VS Code's setting is honoured, but the CLI's telemetry isn't documented (12).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):\n\n- 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.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).\n\nThe other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.\n\nProvenance checks not met in full (half of this category, computed from checked facts):\n\n- Domain age: cline.bot, no registry record we could read (0 of 15)\n- Status page: not found (0 of 10)\n\n## 7. Maintenance \u0026 community, 85 out of 100, up to 1.3 more on the total\n\nWhy it scored 85: CLI 3.0.68 on 2026-10-01 and extension 4.1.22 on 2026-09-29 (30). 29 extension releases and 34 CLI releases since 2026-07-03 (20). Issues get platform labels, but about 700 open issues and 525 open pull requests sit beside a stale bot, and the newest issue we could see was from 23 July, so we couldn't judge reply times (13). VS Code Marketplace, JetBrains, npm and desktop builds are current, while the SDK packages are 0.0.x (13). CI passes, Dependabot runs, and npm publishing moved to OIDC trusted publishing after the February token compromise (9).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):\n\n- 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.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 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.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.\n\nModels are read for deprecation notice periods and model churn rather than release counts.\n\n## Deductions\n\nEach comes off the total. A fixed and documented problem counts for less at the next check.\n\n- 2026-02-17. GHSA-9ppg-jx86-fqw7. An attacker used a compromised npm publish token to release cline@2.3.0 with a postinstall script that ran `npm install -g openclaw@latest`. It was live for about eight hours before 2.4.0 and a deprecation, the token was revoked and publishing moved to OIDC. A supply-chain incident that reached users, fixed and documented and seven months old, -4. https://github.com/cline/cline/security/advisories/GHSA-9ppg-jx86-fqw7\n- 2026-05-08. GHSA-5c57-rqjx-35g2 (CVE-2026-44211, 9.6). The kanban server the CLI uses accepted WebSocket connections on 127.0.0.1:3484 without checking Origin, so any website could read workspace data and inject commands. Affects kanban before 2.13.0. Inside six months, -2. https://github.com/cline/cline/security/advisories/GHSA-5c57-rqjx-35g2\n- 2026-06-23. GHSA-3cj3-hqcr-g934 (CVE-2026-59723, 8.8). The Cline Hub dashboard's `/browser` WebSocket accepted cross-origin connections when ROOM_SECRET was unset, the local default, letting a website add MCP servers to the settings file and run commands. NVD lists versions before 3.0.30 as affected. Inside six months, -2. https://github.com/cline/cline/security/advisories/GHSA-3cj3-hqcr-g934\n\n## What we couldn't check\n\nWhat 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.\n\n- Unchecked: the privacy policy and terms at cline.bot, which need JavaScript to render\n- Whether the published CLI sends telemetry by default. It's built with a telemetry key and flag from repository secrets\n- The per-token price of Cline credits\n- The issues page we loaded showed nothing newer than 23 July 2026 while pull requests are numbered past 14,700, so we couldn't judge reply times\n- Two advisories (GHSA-5c57-rqjx-35g2, GHSA-3cj3-hqcr-g934) list no patched version. NVD gives 3.0.30 as the fix for the hub flaw\n- Unchecked: a status page and the domain's registration date\n\n## Weaknesses\n\n- The CLI approves every tool by default outside ACP mode and starts on Cline's own provider\n- Extension telemetry on by default, and the CLI's telemetry undocumented\n- A compromised npm token shipped cline@2.3.0 with an unwanted global install in February 2026\n- Two cross-origin WebSocket flaws in its local servers in May and June 2026\n- About 700 open issues and 525 open pull requests\n\n## What costs an agent a turn today\n\nThe notes we give agents before they call it. Each one is a workaround an agent shouldn't need.\n\n- Set `CLINE_COMMAND_PERMISSIONS` with allow and deny globs before a headless run. The CLI approves every tool by default\n- Pick a provider with `-P` and a key, or run `cline auth`. The default provider needs a Cline sign-in\n- Untick 'Allow error and usage reporting', or turn off VS Code telemetry, before the first task\n- Pin the CLI version. 2.3.0 was a malicious publish\n- Keep the hub on 127.0.0.1 or set ROOM_SECRET, and run 3.0.30 or later\n\n## What the review panel asked for\n\n- dates in the changelog\n- breaking-change section\n- CLI approval by default\n- patched versions in advisories\n\n## When it's done\n\nSend 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.\n",
    "grade": "C",
    "score": 60.8,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 57,
        "maxGain": 7.5,
        "reason": "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. The extension sends usage and error events to PostHog unless the user unticks 'Allow error and usage reporting' or turns off VS Code telemetry. The CLI is built with a telemetry key and an enable flag from repository secrets and its reference lists no telemetry setting, so its default is unconfirmed (15). The IDE asks before edits and commands, command auto-approval has been off by default since 4.0.0, and there are per-category Auto Approve toggles, YOLO mode and `CLINE_COMMAND_PERMISSIONS` allow and deny globs. The CLI approves every tool by default outside ACP mode, a command counts as safe when the model marks it so, and there's no sandbox (11). No prompt-injection guidance found in the docs (4). Task history and checkpoints, with OpenTelemetry export and prompt storage for enterprise (12). A valid security.txt (expires 2027-12-31), a Bugcrowd disclosure programme and three advisories published with CVEs, two of which list no patched version (15).",
        "checklist": [
          "- 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.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 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.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-security"
      },
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 50,
        "maxGain": 6.3,
        "reason": "No payment protocol (0). Scored on Cline's paid options. ClinePass is $9.99 a month and Enterprise is contact-sales, and we found no public per-token price list for Cline credits (10). The open-source extension and CLI need no card (20). Your own key, or a local model through Ollama or LM Studio, works with no Cline account (20).",
        "checklist": [
          "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.\n- 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.\n- 20, a free tier or trial that doesn't need a card.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-payments"
      },
      {
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "score": 67,
        "maxGain": 5.4,
        "reason": "Harness reading of the framework line, scored on what an agent or pipeline driving it has to supply. Many built-in tools (files, terminal, browser, MCP, subagents, plan and act), with MCP servers switched on or off per server, and no tool search or lazy loading found (15). `--timeout` (off by default), a mistake limit through `--retries`, automatic compaction and an output budget scaled to the model (14). `--json` writes one JSON object per message, but we found no documented exit codes (12). Checkpoints restore files and task state, sessions resume by ID, and API errors and empty responses are retried (18). The CLI defaults to Cline's own provider and to approving every tool, and the SDK is TypeScript only (8).",
        "checklist": [
          "- 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).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-ergonomics"
      },
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 80,
        "maxGain": 4,
        "reason": "Read as a local package. The `cline` CLI on npm (Node 22 or later), the VS Code extension (VS Code 1.101 or later), a JetBrains plugin and desktop builds (20). The VS Code test workflow passed on every main run we loaded, including the 1 October CLI and SDK releases (25). 645 to 730 open issues and 525 open pull requests, a stale bot that closes issues after 74 quiet days, and open crash reports such as #12493, where aborting a turn can crash the hub daemon (13). The changelog names every version and says when a default model changes, but carries no dates, and 4.0.0 listed its removals (Explain Changes, subagents for a time) under Changed rather than a breaking section (9). Extension 4.1 and CLI 3.0 are past 1.0, while the SDK (0.0.90) and desktop app (0.0.42) aren't (13).",
        "checklist": [
          "Hosted APIs, MCP servers, models and platforms.",
          "- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 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.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 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.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-reliability"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 77,
        "maxGain": 3.7,
        "reason": "A typed TypeScript SDK with a reference section, a documented one-object-per-line format for `--json`, and an errors page for the Cline API, but no machine-readable spec for the CLI or its config (18). llms.txt at docs.cline.bot, listing a Markdown version of every page (10). Feature pages say when to use each setting, such as the recommended Auto Approve setup (14). `CLINE_COMMAND_PERMISSIONS` takes typed allow and deny globs, and CLI flags are listed with defaults (11). CLI samples, SDK examples and the API errors page (13). A versioned changelog without dates, with dated tags on GitHub (11).",
        "checklist": [
          "APIs and MCP servers.",
          "- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 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.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-schema"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 66,
        "maxGain": 3,
        "reason": "Apache-2.0 (30). The privacy policy at cline.bot/privacy renders only with JavaScript and we couldn't read it. The docs say code stays on the machine apart from model calls and list what telemetry never includes, without retention periods or subprocessors (10). Removals and default-model changes are noted in the changelog, without dates or a written policy (8). The extension's telemetry and its toggle are documented and VS Code's setting is honoured, but the CLI's telemetry isn't documented (12).",
        "blend": "editorial 60, provenance 71",
        "checklist": [
          "- 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.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-transparency"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 85,
        "maxGain": 1.3,
        "reason": "CLI 3.0.68 on 2026-10-01 and extension 4.1.22 on 2026-09-29 (30). 29 extension releases and 34 CLI releases since 2026-07-03 (20). Issues get platform labels, but about 700 open issues and 525 open pull requests sit beside a stale bot, and the newest issue we could see was from 23 July, so we couldn't judge reply times (13). VS Code Marketplace, JetBrains, npm and desktop builds are current, while the SDK packages are 0.0.x (13). CI passes, Dependabot runs, and npm publishing moved to OIDC trusted publishing after the February token compromise (9).",
        "checklist": [
          "- 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.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 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.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.",
          "Models are read for deprecation notice periods and model churn rather than release counts."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-maintenance"
      }
    ],
    "provenance": [
      {
        "label": "Domain age",
        "value": "cline.bot, no registry record we could read",
        "points": 0,
        "max": 15
      },
      {
        "label": "Status page",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "deductions": [
      "2026-02-17. GHSA-9ppg-jx86-fqw7. An attacker used a compromised npm publish token to release cline@2.3.0 with a postinstall script that ran `npm install -g openclaw@latest`. It was live for about eight hours before 2.4.0 and a deprecation, the token was revoked and publishing moved to OIDC. A supply-chain incident that reached users, fixed and documented and seven months old, -4. https://github.com/cline/cline/security/advisories/GHSA-9ppg-jx86-fqw7",
      "2026-05-08. GHSA-5c57-rqjx-35g2 (CVE-2026-44211, 9.6). The kanban server the CLI uses accepted WebSocket connections on 127.0.0.1:3484 without checking Origin, so any website could read workspace data and inject commands. Affects kanban before 2.13.0. Inside six months, -2. https://github.com/cline/cline/security/advisories/GHSA-5c57-rqjx-35g2",
      "2026-06-23. GHSA-3cj3-hqcr-g934 (CVE-2026-59723, 8.8). The Cline Hub dashboard's `/browser` WebSocket accepted cross-origin connections when ROOM_SECRET was unset, the local default, letting a website add MCP servers to the settings file and run commands. NVD lists versions before 3.0.30 as affected. Inside six months, -2. https://github.com/cline/cline/security/advisories/GHSA-3cj3-hqcr-g934"
    ],
    "unchecked": [
      "Unchecked: the privacy policy and terms at cline.bot, which need JavaScript to render",
      "Whether the published CLI sends telemetry by default. It's built with a telemetry key and flag from repository secrets",
      "The per-token price of Cline credits",
      "The issues page we loaded showed nothing newer than 23 July 2026 while pull requests are numbered past 14,700, so we couldn't judge reply times",
      "Two advisories (GHSA-5c57-rqjx-35g2, GHSA-3cj3-hqcr-g934) list no patched version. NVD gives 3.0.30 as the fix for the hub flaw",
      "Unchecked: a status page and the domain's registration date"
    ],
    "weaknesses": [
      "The CLI approves every tool by default outside ACP mode and starts on Cline's own provider",
      "Extension telemetry on by default, and the CLI's telemetry undocumented",
      "A compromised npm token shipped cline@2.3.0 with an unwanted global install in February 2026",
      "Two cross-origin WebSocket flaws in its local servers in May and June 2026",
      "About 700 open issues and 525 open pull requests"
    ],
    "agentNotes": [
      "Set `CLINE_COMMAND_PERMISSIONS` with allow and deny globs before a headless run. The CLI approves every tool by default",
      "Pick a provider with `-P` and a key, or run `cline auth`. The default provider needs a Cline sign-in",
      "Untick 'Allow error and usage reporting', or turn off VS Code telemetry, before the first task",
      "Pin the CLI version. 2.3.0 was a malicious publish",
      "Keep the hub on 127.0.0.1 or set ROOM_SECRET, and run 3.0.30 or later"
    ],
    "requests": [
      {
        "text": "dates in the changelog",
        "reviews": 1
      },
      {
        "text": "breaking-change section",
        "reviews": 1
      },
      {
        "text": "CLI approval by default",
        "reviews": 1
      },
      {
        "text": "patched versions in advisories",
        "reviews": 1
      }
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-04",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.3",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}