[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-plugin-backnotprop-copilot-zh-CN":3,"guides-for-backnotprop-copilot":463,"similar-k171yzq9hxjb9wvqtnkgfjw43186nra6-zh-CN":464},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":14,"identity":255,"isFallback":237,"parentExtension":261,"providers":262,"relations":267,"repo":269,"tags":460,"workflow":461},1778682919003.7273,"k171yzq9hxjb9wvqtnkgfjw43186nra6",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":12,"sourceUrl":13},"Interactive Plan & Code Review for GitHub Copilot CLI. Visual annotations, team sharing, structured feedback.",{"claudeCode":12},"plannotator-copilot","https://github.com/backnotprop/plannotator",{"_creationTime":15,"_id":16,"extensionId":5,"locale":17,"result":18,"trustSignals":235,"workflow":253},1778682992590.0535,"kn7a505bc7d0h8gc84g1y2hq0d86m9sj","en",{"checks":19,"evaluatedAt":204,"extensionSummary":205,"features":206,"nonGoals":212,"promptVersionExtension":216,"promptVersionScoring":217,"purpose":218,"rationale":219,"score":220,"summary":221,"tags":222,"targetMarket":228,"tier":229,"useCases":230},[20,25,28,31,35,38,42,46,49,52,56,60,63,67,70,73,76,79,82,85,89,93,97,101,105,108,112,116,120,123,126,129,132,135,138,142,145,149,152,156,159,162,165,168,171,174,177,180,183,186,190,193,196,200],{"category":21,"check":22,"severity":23,"summary":24},"Practical Utility","Problem relevance","pass","The description clearly names the problem of interactive plan and code review for GitHub Copilot CLI users.",{"category":21,"check":26,"severity":23,"summary":27},"Unique selling proposition","The extension offers visual annotations, team sharing, and structured feedback, providing value beyond basic Copilot CLI functionality.",{"category":21,"check":29,"severity":23,"summary":30},"Production readiness","The plugin appears production-ready, integrating with Copilot CLI's plan mode and offering commands for review and annotation, covering the full lifecycle of review.",{"category":32,"check":33,"severity":23,"summary":34},"Scope","Single responsibility principle","The plugin focuses on enhancing Copilot CLI's review capabilities, including plan review, code review, and markdown annotation, which is a coherent domain.",{"category":32,"check":36,"severity":23,"summary":37},"Description quality","The displayed description accurately reflects the plugin's capabilities for interactive plan and code review with visual annotations and team sharing.",{"category":39,"check":40,"severity":23,"summary":41},"Invocation","Scoped tools","The plugin exposes specific, scoped tools like `plannotator-review`, `plannotator-annotate`, and `plannotator-last`, which are well-defined verb-noun actions.",{"category":43,"check":44,"severity":23,"summary":45},"Documentation","Configuration & parameter reference","Environment variables for controlling remote mode, port, browser, and sharing are documented, with clear descriptions.",{"category":32,"check":47,"severity":23,"summary":48},"Tool naming","Tool names such as `plannotator-review`, `plannotator-annotate`, and `plannotator-last` are descriptive and follow the verb-noun convention.",{"category":32,"check":50,"severity":23,"summary":51},"Minimal I/O surface","The tool parameters are straightforward (e.g., file paths, PR URLs) and the output schema for decisions (approved, dismissed, annotated) is minimal and clear.",{"category":53,"check":54,"severity":23,"summary":55},"License","License usability","The plugin is licensed under MIT OR Apache-2.0, declared in the manifest and README, which are permissive open-source licenses.",{"category":57,"check":58,"severity":23,"summary":59},"Maintenance","Commit recency","The plugin was last committed to on 2026-05-13, well within the last 3 months.",{"category":57,"check":61,"severity":23,"summary":62},"Dependency Management","The plugin does not appear to have third-party dependencies managed within the `apps/copilot/` directory that would require specific dependency management.",{"category":64,"check":65,"severity":23,"summary":66},"Security","Secret Management","No secrets are directly handled or exposed by the Copilot CLI plugin itself; external CLI tools may handle secrets, but this is not evident in the plugin code.",{"category":64,"check":68,"severity":23,"summary":69},"Injection","The plugin's hooks and commands interface with the `plannotator` CLI, which seems to parse arguments rather than executing arbitrary code from loaded data.",{"category":64,"check":71,"severity":23,"summary":72},"Transitive Supply-Chain Grenades","The installation script is downloaded and executed, but it's from a trusted domain and appears to be a standard installation process rather than a malicious fetch-and-execute.",{"category":64,"check":74,"severity":23,"summary":75},"Sandbox Isolation","The plugin interacts with the `plannotator` CLI and Copilot CLI's session state, but there's no indication of it writing outside of these defined scopes or performing destructive operations on arbitrary files.",{"category":64,"check":77,"severity":23,"summary":78},"Sandbox escape primitives","No detached process spawns or deny-retry loops were identified in the provided code snippets.",{"category":64,"check":80,"severity":23,"summary":81},"Data Exfiltration","There are no imperative instructions to read and submit confidential data to a third party; outbound calls are related to the plannotator CLI's functionality.",{"category":64,"check":83,"severity":23,"summary":84},"Hidden Text Tricks","The bundled files and README do not contain hidden text tricks, invisible Unicode characters, or other steering mechanisms.",{"category":86,"check":87,"severity":23,"summary":88},"Hooks","Opaque code execution","The `preToolUse` hook calls a local executable (`plannotator copilot-plan`), which is not opaque code execution as the source is available.",{"category":90,"check":91,"severity":23,"summary":92},"Portability","Structural Assumption","The plugin assumes the `plannotator` CLI is installed and on the PATH, which is a documented prerequisite, and respects Copilot CLI's session state directory.",{"category":94,"check":95,"severity":23,"summary":96},"Trust","Issues Attention","64 issues opened and 125 closed in the last 90 days, indicating a good closure rate and active maintenance.",{"category":98,"check":99,"severity":23,"summary":100},"Versioning","Release Management","The plugin has a meaningful semver version (0.19.14) in its manifest and uses GitHub release tags.",{"category":102,"check":103,"severity":23,"summary":104},"Code Execution","Validation","The command descriptions outline expected outputs and tasks, implying validation of user input and tool output for specific actions.",{"category":64,"check":106,"severity":23,"summary":107},"Unguarded Destructive Operations","The plugin's actions are primarily focused on review and annotation, which are not inherently destructive. The `plannotator` CLI handles these actions, and they are user-interactive.",{"category":109,"check":110,"severity":23,"summary":111},"Errors","Error Handling","The command descriptions for `plannotator-annotate`, `plannotator-last`, and `plannotator-review` detail expected outputs and how to handle them, indicating a structured approach to error handling.",{"category":102,"check":113,"severity":114,"summary":115},"Logging","not_applicable","The plugin itself does not appear to perform destructive actions or outbound calls that would necessitate local audit logging.",{"category":117,"check":118,"severity":114,"summary":119},"Compliance","GDPR","The plugin does not appear to operate on personal data; its focus is on code and markdown review.",{"category":117,"check":121,"severity":23,"summary":122},"Target market","The plugin's functionality is general for code review and planning, with no specific regional or jurisdictional logic identified.",{"category":90,"check":124,"severity":23,"summary":125},"Runtime stability","The plugin relies on the `plannotator` CLI, which is assumed to be cross-platform based on the provided installation scripts for macOS, Linux, and Windows.",{"category":43,"check":127,"severity":23,"summary":128},"README","The README file exists, is comprehensive, and clearly states the extension's purpose and installation instructions.",{"category":32,"check":130,"severity":23,"summary":131},"Tool surface size","The plugin exposes 3 main commands (`/plannotator-review`, `/plannotator-annotate`, `/plannotator-last`), which is within the ideal range.",{"category":39,"check":133,"severity":23,"summary":134},"Overlapping near-synonym tools","The exposed tools (`review`, `annotate`, `last`) cover distinct functionalities and do not appear to be near-synonyms.",{"category":43,"check":136,"severity":23,"summary":137},"Phantom features","All advertised features like plan mode integration, review commands, and annotation are implemented and accessible via the plugin.",{"category":139,"check":140,"severity":23,"summary":141},"Install","Installation instruction","The README provides clear installation instructions for the `plannotator` CLI and the plugin itself, including copy-pasteable commands and verification steps.",{"category":109,"check":143,"severity":23,"summary":144},"Actionable error messages","The command descriptions for the review and annotation tools specify expected outputs and how to handle them, providing clear guidance for user interaction and feedback.",{"category":146,"check":147,"severity":114,"summary":148},"Execution","Pinned dependencies","The plugin itself does not appear to manage direct third-party dependencies within its `apps/copilot/` directory that would require pinning.",{"category":32,"check":150,"severity":114,"summary":151},"Dry-run preview","The plugin's core functions are interactive review and annotation, which do not involve state-changing operations that would benefit from a dry-run mode.",{"category":153,"check":154,"severity":23,"summary":155},"Protocol","Idempotent retry & timeouts","The plugin's interactions are primarily user-driven through interactive tools, and the `preToolUse` hook has a generous timeout, but no explicit retry logic is evident for mutations.",{"category":117,"check":157,"severity":23,"summary":158},"Telemetry opt-in","No telemetry is evident in the plugin's code or configuration, thus no opt-in/out mechanism is required.",{"category":39,"check":160,"severity":23,"summary":161},"Name collisions","The plugin commands (`plannotator-review`, etc.) are distinct and do not appear to collide with Copilot CLI built-ins or other common commands.",{"category":39,"check":163,"severity":114,"summary":164},"Hooks-off mechanism","There is no explicit documented 'hooks-off' mechanism provided for this plugin; disabling would likely require uninstalling the plugin.",{"category":39,"check":166,"severity":23,"summary":167},"Hook matcher tightness","The `preToolUse` hook is specifically configured to intercept `exit_plan_mode` events, indicating a tight matcher.",{"category":64,"check":169,"severity":23,"summary":170},"Hook security","The `preToolUse` hook intercepts plan mode exit to open a UI, which is not a destructive or network-touching operation, and has no obvious security risks.",{"category":86,"check":172,"severity":114,"summary":173},"Silent prompt rewriting","The plugin does not appear to have a `UserPromptSubmit` hook that would rewrite prompts.",{"category":64,"check":175,"severity":114,"summary":176},"Permission Hook","There are no `PermissionRequest` hooks present in this plugin.",{"category":117,"check":178,"severity":23,"summary":179},"Hook privacy","The plugin's hooks do not appear to send data to any external services; the `preToolUse` hook interacts locally with the `plannotator` CLI.",{"category":102,"check":181,"severity":23,"summary":182},"Hook dependency","The hook is a simple bash/powershell command calling a local executable, which is readable and not opaque.",{"category":43,"check":184,"severity":23,"summary":185},"Feature Transparency","The README clearly explains the installation, how the plan mode integration works, and lists the available commands.",{"category":187,"check":188,"severity":23,"summary":189},"Convention","Layout convention adherence","The plugin follows standard conventions with `plugin.json` in `.claude-plugin/` and commands organized in a `commands/` directory, with README documentation.",{"category":187,"check":191,"severity":114,"summary":192},"Plugin state","This plugin does not appear to maintain persistent state that would require management under `${CLAUDE_PLUGIN_DATA}`.",{"category":64,"check":194,"severity":114,"summary":195},"Keychain-stored secrets","The plugin does not appear to handle any secrets that would need to be routed through `userConfig`.",{"category":197,"check":198,"severity":23,"summary":199},"Dependencies","Tagged release sourcing","The plugin's `plugin.json` points to its GitHub repository and has a defined version, implying it's sourced from tagged releases.",{"category":201,"check":202,"severity":23,"summary":203},"Installation","Clean uninstall","The plugin's operations are session-scoped and integrated with Copilot CLI's lifecycle, with no indication of background daemons or services that would survive an uninstall.",1778682992482,"This plugin integrates with GitHub Copilot CLI to provide interactive plan and code review functionality. It enables visual annotations, team sharing, and structured feedback through specific commands and a plan mode hook.",[207,208,209,210,211],"Interactive plan review","Visual code review","Markdown file annotation","Team sharing of feedback","Integration with Copilot CLI plan mode",[213,214,215],"Replacing the core Copilot CLI functionality","Providing general-purpose code editing tools","Managing GitHub repositories or issues directly","3.0.0","4.4.0","To empower developers using GitHub Copilot CLI with advanced tools for reviewing plans and code, fostering better collaboration and code quality.","The plugin demonstrates excellent adherence to all evaluated checks, with no critical or warning findings. The `hooks-off mechanism` and `Plugin state` checks were marked not applicable, and `Logging` was also not applicable as the plugin's function does not involve destructive actions or outbound calls requiring audit logs.",99,"High-quality plugin enhancing Copilot CLI with interactive review and annotation capabilities.",[223,224,225,226,227],"review","code-review","plan","annotation","github-copilot","global","verified",[231,232,233,234],"Reviewing generated plans before execution","Annotating markdown files for clarity","Collaborating on code reviews with team members","Enhancing feedback on assistant messages",{"codeQuality":236,"collectedAt":238,"documentation":239,"maintenance":242,"security":249,"testCoverage":252},{"hasLockfile":237},true,1778682964185,{"descriptionLength":240,"readmeSize":241},109,8992,{"closedIssues90d":243,"forks":244,"hasChangelog":237,"manifestVersion":245,"openIssues90d":246,"pushedAt":247,"stars":248},125,363,"0.19.14",64,1778682278000,5267,{"hasNpmPackage":250,"license":251,"smitheryVerified":250},false,"MIT OR Apache-2.0",{"hasCi":237,"hasTests":237},{"updatedAt":254},1778682992590,{"basePath":256,"githubOwner":257,"githubRepo":258,"locale":17,"slug":259,"type":260},"apps/copilot","backnotprop","plannotator","copilot","plugin",null,{"evaluate":263,"extract":265},{"promptVersionExtension":216,"promptVersionScoring":217,"score":220,"tags":264,"targetMarket":228,"tier":229},[223,224,225,226,227],{"commitSha":266,"license":251},"HEAD",{"repoId":268},"kd78wavmsqx3xwvse964rbj4d986m9r5",{"_creationTime":270,"_id":268,"identity":271,"providers":272,"workflow":456},1778682913452.569,{"githubOwner":257,"githubRepo":258,"sourceUrl":13},{"classify":273,"discover":440,"github":443},{"commitSha":266,"extensions":274},[275,291,310,322,332,347,355,363,371,386,394,402,412,428],{"basePath":276,"displayName":258,"installMethods":277,"rationale":279,"selectedPaths":280,"source":289,"sourceLanguage":17,"type":290},"",{"claudeCode":278},"backnotprop/plannotator","marketplace.json at .claude-plugin/marketplace.json (coalesced with duplicate marketplace at .github/plugin)",[281,284,286],{"path":282,"priority":283},".claude-plugin/marketplace.json","mandatory",{"path":285,"priority":283},"README.md",{"path":287,"priority":288},"LICENSE-APACHE","high","rule","marketplace",{"basePath":292,"description":293,"displayName":258,"installMethods":294,"rationale":295,"selectedPaths":296,"source":289,"sourceLanguage":17,"type":260},"apps/hook","Interactive Plan Review: Mark up and refine your plans using a UI, easily share for team collaboration, automatically integrates with plan mode hooks.",{"claudeCode":258},"plugin manifest at apps/hook/.claude-plugin/plugin.json",[297,299,300,302,304,306,308],{"path":298,"priority":283},".claude-plugin/plugin.json",{"path":285,"priority":283},{"path":301,"priority":288},"commands/plannotator-annotate.md",{"path":303,"priority":288},"commands/plannotator-archive.md",{"path":305,"priority":288},"commands/plannotator-last.md",{"path":307,"priority":288},"commands/plannotator-review.md",{"path":309,"priority":288},"hooks/hooks.json",{"basePath":256,"description":10,"displayName":12,"installMethods":311,"license":251,"rationale":312,"selectedPaths":313,"source":289,"sourceLanguage":17,"type":260},{"claudeCode":12},"plugin manifest at apps/copilot/plugin.json",[314,316,317,318,319,320],{"path":315,"priority":283},"plugin.json",{"path":285,"priority":283},{"path":301,"priority":288},{"path":305,"priority":288},{"path":307,"priority":288},{"path":321,"priority":283},"hooks.json",{"basePath":323,"description":324,"displayName":325,"installMethods":326,"rationale":327,"selectedPaths":328,"source":289,"sourceLanguage":17,"type":331},".agents/skills/pierre-guard","Guard against breaking the @pierre/diffs integration in Plannotator's code review UI. Use this skill whenever modifying DiffViewer.tsx, upgrading the @pierre/diffs package, changing unsafeCSS injection, adding new props to FileDiff, or touching shadow DOM selectors or CSS variables that cross into Pierre's shadow boundary. Also trigger when someone asks \"will this break the diff viewer\", \"is this safe to change\", or when reviewing PRs that touch the review-editor package.","pierre-guard",{"claudeCode":278},"SKILL.md frontmatter at .agents/skills/pierre-guard/SKILL.md",[329],{"path":330,"priority":283},"SKILL.md","skill",{"basePath":333,"description":334,"displayName":335,"installMethods":336,"rationale":337,"selectedPaths":338,"source":289,"sourceLanguage":17,"type":331},".agents/skills/release","Prepare and execute a Plannotator release — draft release notes with full contributor credit, bump versions across all package files, build in dependency order, and kick off the tag-driven release pipeline. Use this skill whenever the user mentions preparing a release, bumping versions, writing release notes, tagging a release, or publishing. Also trigger when the user says things like \"let's ship\", \"prep a release\", \"what's changed since last release\", or \"time to cut a new version\".","release-plannotator",{"claudeCode":278},"SKILL.md frontmatter at .agents/skills/release/SKILL.md",[339,340,343,345],{"path":330,"priority":283},{"path":341,"priority":342},"references/release-notes-v0.12.0.md","medium",{"path":344,"priority":342},"references/release-notes-v0.13.0.md",{"path":346,"priority":342},"references/release-notes-v0.13.1.md",{"basePath":348,"description":349,"displayName":350,"installMethods":351,"rationale":352,"selectedPaths":353,"source":289,"sourceLanguage":17,"type":331},".agents/skills/review-renovate","Review Renovate bot PRs that update GitHub Actions dependencies. Verifies supply chain integrity by checking pinned commit SHAs against upstream tagged releases, reviews changelogs for breaking changes, and confirms compatibility with existing workflow configurations. Use when a Renovate PR updates GitHub Actions in .github/workflows/.","review-renovate",{"claudeCode":278},"SKILL.md frontmatter at .agents/skills/review-renovate/SKILL.md",[354],{"path":330,"priority":283},{"basePath":356,"description":357,"displayName":358,"installMethods":359,"rationale":360,"selectedPaths":361,"source":289,"sourceLanguage":17,"type":331},".agents/skills/update-deps","Audit and update npm/Bun dependencies with supply chain integrity checks — verifies maintainers, publish age, tarball diffs, and provenance before bumping. Defers risky packages to ~/.supply-chain/notes/.","update-deps",{"claudeCode":278},"SKILL.md frontmatter at .agents/skills/update-deps/SKILL.md",[362],{"path":330,"priority":283},{"basePath":364,"description":365,"displayName":366,"installMethods":367,"rationale":368,"selectedPaths":369,"source":289,"sourceLanguage":17,"type":331},"apps/skills/plannotator-annotate","Open Plannotator's annotation UI for a markdown file, converted HTML file, URL, or folder and then respond to the returned annotations.","plannotator-annotate",{"claudeCode":278},"SKILL.md frontmatter at apps/skills/plannotator-annotate/SKILL.md",[370],{"path":330,"priority":283},{"basePath":372,"description":373,"displayName":374,"installMethods":375,"rationale":376,"selectedPaths":377,"source":289,"sourceLanguage":17,"type":331},"apps/skills/plannotator-compound","Analyze a user's Plannotator plan archive to extract denial patterns, feedback taxonomy, evolution over time, and actionable prompt improvements — then produce a polished HTML dashboard report. Falls back to Claude Code ExitPlanMode denial reasons when Plannotator data is unavailable.\n","plannotator-compound",{"claudeCode":278},"SKILL.md frontmatter at apps/skills/plannotator-compound/SKILL.md",[378,379,382,384],{"path":330,"priority":283},{"path":380,"priority":381},"assets/report-template.html","low",{"path":383,"priority":342},"references/claude-code-fallback.md",{"path":385,"priority":381},"scripts/extract_exit_plan_mode_outcomes.py",{"basePath":387,"description":388,"displayName":389,"installMethods":390,"rationale":391,"selectedPaths":392,"source":289,"sourceLanguage":17,"type":331},"apps/skills/plannotator-last","Open Plannotator on the latest rendered assistant message and use the returned annotations to revise that message or continue.","plannotator-last",{"claudeCode":278},"SKILL.md frontmatter at apps/skills/plannotator-last/SKILL.md",[393],{"path":330,"priority":283},{"basePath":395,"description":396,"displayName":397,"installMethods":398,"rationale":399,"selectedPaths":400,"source":289,"sourceLanguage":17,"type":331},"apps/skills/plannotator-review","Open Plannotator's browser-based code review UI for the current worktree or a pull request URL, then act on the feedback that comes back.","plannotator-review",{"claudeCode":278},"SKILL.md frontmatter at apps/skills/plannotator-review/SKILL.md",[401],{"path":330,"priority":283},{"basePath":403,"description":404,"displayName":405,"installMethods":406,"rationale":407,"selectedPaths":408,"source":289,"sourceLanguage":17,"type":331},"apps/skills/plannotator-setup-goal","Create reviewed Codex goal setup packages for long-running /goal work. Use when the user wants to turn an idea, backlog, project mission, or vague objective into durable goal files under a project goals slug folder, with Plannotator review gates for brief, narrative plan with acceptance criteria, verification, blockers, and the final /goal prompt.","plannotator-setup-goal",{"claudeCode":278},"SKILL.md frontmatter at apps/skills/plannotator-setup-goal/SKILL.md",[409,410],{"path":330,"priority":283},{"path":411,"priority":381},"scripts/scaffold_goal.py",{"basePath":413,"description":414,"displayName":415,"installMethods":416,"rationale":417,"selectedPaths":418,"source":289,"sourceLanguage":17,"type":331},"apps/skills/plannotator-visual-explainer","Generate self-contained HTML visualizations with Plannotator theming. Use for implementation plans, PR explainers, architecture diagrams, data tables, slide decks, and any visual explanation of technical concepts. Plans and PR explainers follow Plannotator's prescriptive approach; all other visual content delegates to nicobailon/visual-explainer.\n","plannotator-visual-explainer",{"claudeCode":278},"SKILL.md frontmatter at apps/skills/plannotator-visual-explainer/SKILL.md",[419,420,422,424,426],{"path":330,"priority":283},{"path":421,"priority":342},"references/design-system.md",{"path":423,"priority":342},"references/pr-components.md",{"path":425,"priority":342},"references/svg-patterns.md",{"path":427,"priority":342},"references/theme-override.md",{"basePath":276,"description":429,"displayName":258,"installMethods":430,"license":251,"rationale":431,"selectedPaths":432,"source":289,"sourceLanguage":17,"type":439},"Interactive Plan Review for Claude Code - annotate plans visually, share with team, automatically send feedback",{"npm":258},"cli ecosystem detected at /",[433,435,436,437],{"path":434,"priority":283},"package.json",{"path":285,"priority":283},{"path":287,"priority":288},{"path":438,"priority":342},"bin/plannotator.js","cli",{"sources":441},[442],"manual",{"closedIssues90d":243,"description":444,"forks":244,"homepage":445,"license":446,"openIssues90d":246,"pushedAt":247,"readmeSize":241,"stars":248,"topics":447},"Annotate and review coding agent plans and code diffs visually, share with your team, send feedback to agents with one click.","https://plannotator.ai","Apache-2.0",[448,449,450,451,452,453,454,224,455],"claude-code","opencode","obsidian","pi-mono","plan-mode","codex","agents","skills",{"classifiedAt":457,"discoverAt":458,"extractAt":459,"githubAt":459,"updatedAt":457},1778682918806,1778682913452,1778682916808,[226,224,227,225,223],{"evaluatedAt":254,"extractAt":462,"updatedAt":254},1778682919003,[],[465,498,528,556,577,598],{"_creationTime":466,"_id":467,"community":468,"display":469,"identity":474,"providers":478,"relations":491,"tags":494,"workflow":495},1778675056600.2068,"k178z532bm8n047nxsbbprw3fd86mj5a",{"reviewCount":8},{"description":470,"installMethods":471,"name":472,"sourceUrl":473},"Active coding discipline enforcer based on Karpathy's 4 principles: surface assumptions, keep it simple, make surgical changes, define verifiable goals. Ships 4 Python tools (complexity_checker, diff_surgeon, assumption_linter, goal_verifier), a review agent, /karpathy-check slash command, and a pre-commit hook. All tools stdlib-only.",{"claudeCode":472},"karpathy-coder","https://github.com/alirezarezvani/claude-skills",{"basePath":475,"githubOwner":476,"githubRepo":477,"locale":17,"slug":472,"type":260},"engineering/karpathy-coder","alirezarezvani","claude-skills",{"evaluate":479,"extract":486},{"promptVersionExtension":216,"promptVersionScoring":217,"score":480,"tags":481,"targetMarket":228,"tier":229},100,[482,483,484,223,485],"code-quality","developer-tools","linting","python",{"commitSha":266,"license":487,"plugin":488},"MIT",{"mcpCount":8,"provider":489,"skillCount":490},"classify",1,{"parentExtensionId":492,"repoId":493},"k17dce6sbramb6sxm7ksr3928x86ncfs","kd7ff9s1w43mfyy1n7hf87816186m6px",[482,483,484,485,223],{"evaluatedAt":496,"extractAt":497,"updatedAt":496},1778675717756,1778675056600,{"_creationTime":499,"_id":500,"community":501,"display":502,"identity":507,"providers":510,"relations":521,"tags":524,"workflow":525},1778698175626.3186,"k178w69vcq5ktp47kejp29xfss86m4vp",{"reviewCount":8},{"description":503,"installMethods":504,"name":505,"sourceUrl":506},"Annotates codebases with dimensional analysis comments documenting units, dimensions, and decimal scaling. Use when someone asks to annotate units in a codebase, perform a dimensional analysis, or find vulnerabilities in a DeFi protocol. Prevents dimensional mismatches and catches formula bugs early.",{"claudeCode":505},"dimensional-analysis","https://github.com/trailofbits/skills",{"basePath":508,"githubOwner":509,"githubRepo":455,"locale":17,"slug":505,"type":260},"plugins/dimensional-analysis","trailofbits",{"evaluate":511,"extract":519},{"promptVersionExtension":216,"promptVersionScoring":217,"score":220,"tags":512,"targetMarket":228,"tier":229},[513,483,514,515,226,516,517,518],"code-analysis","units","dimensions","refactoring","security","defi",{"commitSha":266,"plugin":520},{"mcpCount":8,"provider":489,"skillCount":490},{"parentExtensionId":522,"repoId":523},"k17550d1ve8ghfmwc58xs69e3s86mn86","kd7d5sbrd9m157hjv9c7v4wfyn86mk2f",[226,513,518,483,515,516,517,514],{"evaluatedAt":526,"extractAt":527,"updatedAt":526},1778698831069,1778698175626,{"_creationTime":529,"_id":530,"community":531,"display":532,"identity":537,"providers":540,"relations":549,"tags":552,"workflow":553},1778699018122.7852,"k17ctxt5vn6b49n72hqfjs9tes86mrfw",{"reviewCount":8},{"description":533,"installMethods":534,"name":535,"sourceUrl":536},"Require a human approval signal before an AI agent can post PR reviews, comments, merges, or writes to CI config. Cedar-gated, receipt-signed, designed for the Hermes-style failure mode where a review bot posts without oversight.",{"claudeCode":535},"review-agent-governance","https://github.com/wshobson/agents",{"basePath":538,"githubOwner":539,"githubRepo":454,"locale":17,"slug":535,"type":260},"plugins/review-agent-governance","wshobson",{"evaluate":541,"extract":547},{"promptVersionExtension":216,"promptVersionScoring":217,"score":220,"tags":542,"targetMarket":228,"tier":229},[543,517,544,224,545,546],"governance","policy","compliance","auditing",{"commitSha":266,"license":487,"plugin":548},{"mcpCount":8,"provider":489,"skillCount":490},{"parentExtensionId":550,"repoId":551},"k17cywe30jfsfw3cdpncjfn8y186nvyw","kd74de64zj0axtg5b8t7eqqe2x86nske",[546,224,545,543,544,517],{"evaluatedAt":554,"extractAt":555,"updatedAt":554},1778700330078,1778699018122,{"_creationTime":557,"_id":558,"community":559,"display":560,"identity":564,"providers":566,"relations":573,"tags":574,"workflow":575},1778699018122.7732,"k17a0wf6mk0f48w5xah6yx5dts86n1xj",{"reviewCount":8},{"description":561,"installMethods":562,"name":563,"sourceUrl":536},"Performance analysis, test coverage review, and AI-powered code quality assessment",{"claudeCode":563},"performance-testing-review",{"basePath":565,"githubOwner":539,"githubRepo":454,"locale":17,"slug":563,"type":260},"plugins/performance-testing-review",{"evaluate":567,"extract":572},{"promptVersionExtension":216,"promptVersionScoring":217,"score":220,"tags":568,"targetMarket":228,"tier":229},[482,569,570,224,571],"performance-analysis","testing","ai",{"commitSha":266,"license":487},{"parentExtensionId":550,"repoId":551},[571,482,224,569,570],{"evaluatedAt":576,"extractAt":555,"updatedAt":576},1778699546351,{"_creationTime":578,"_id":579,"community":580,"display":581,"identity":585,"providers":587,"relations":594,"tags":595,"workflow":596},1778699018122.773,"k17ahpwbnf28cr714efke539nn86m1zb",{"reviewCount":8},{"description":582,"installMethods":583,"name":584,"sourceUrl":536},"Multi-perspective code analysis covering architecture, security, and best practices",{"claudeCode":584},"comprehensive-review",{"basePath":586,"githubOwner":539,"githubRepo":454,"locale":17,"slug":584,"type":260},"plugins/comprehensive-review",{"evaluate":588,"extract":593},{"promptVersionExtension":216,"promptVersionScoring":217,"score":220,"tags":589,"targetMarket":228,"tier":229},[224,517,590,591,592,260],"architecture","devops","automation",{"commitSha":266,"license":487},{"parentExtensionId":550,"repoId":551},[590,592,224,591,260,517],{"evaluatedAt":597,"extractAt":555,"updatedAt":597},1778699531123,{"_creationTime":599,"_id":600,"community":601,"display":602,"identity":606,"providers":608,"relations":614,"tags":615,"workflow":616},1778698175626.318,"k172f98zkg85jhx9cvbvmcxyds86nnms",{"reviewCount":8},{"description":603,"installMethods":604,"name":605,"sourceUrl":506},"Automatically reviews and fixes Claude Code skills through iterative refinement until they meet quality standards. Requires plugin-dev plugin.",{"claudeCode":605},"skill-improver",{"basePath":607,"githubOwner":509,"githubRepo":455,"locale":17,"slug":605,"type":260},"plugins/skill-improver",{"evaluate":609,"extract":612},{"promptVersionExtension":216,"promptVersionScoring":217,"score":220,"tags":610,"targetMarket":228,"tier":229},[611,482,592,224],"skill-improvement",{"commitSha":266,"plugin":613},{"mcpCount":8,"provider":489,"skillCount":490},{"parentExtensionId":522,"repoId":523},[592,482,224,611],{"evaluatedAt":617,"extractAt":527,"updatedAt":617},1778698798527]