[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77XDTDKEYR6G7T8YF66AWVB":3,"skill-same:01M77XDTDKEYR6G7T8YF66AWVB":49},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M77XDTDKEYR6G7T8YF66AWVB","codehealth-mcp",null,"Real-time structural Code Health via CodeScene MCP — review before edits, verify score deltas after changes, gate commits and PRs. Use when reviewing code quality, refactoring, checking if AI changes degraded a file, or before commit\u002FPR.","503496348-ops\u002Fmischief-production","503496348-ops","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F266905914?v=4","01M77X5J7XQWWZGT8998HDGXQM","AtomCollide","01M77X5J8V78Y3NXMY6BBC75X9",2,"MIT","https:\u002F\u002Fgithub.com\u002F503496348-ops\u002Fmischief-production\u002Fblob\u002Fmain\u002Fskills\u002Fecc-codehealth-mcp\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: codehealth-mcp\ndescription: Real-time structural Code Health via CodeScene MCP — review before edits, verify score deltas after changes, gate commits and PRs. Use when reviewing code quality, refactoring, checking if AI changes degraded a file, or before commit\u002FPR.\nmetadata:\n  origin: community\n---\n\n# Code Health MCP (CodeScene)\n\nStructural maintainability feedback for AI-assisted coding. Complements style\u002Flint skills (`coding-standards`, `plankton-code-quality`) with **design-level** health scores and regression gates.\n\n**Upstream:** [codescene-oss\u002Fcodescene-mcp-server](https:\u002F\u002Fgithub.com\u002Fcodescene-oss\u002Fcodescene-mcp-server)\n**Package:** `@codescene\u002Fcodehealth-mcp` (stdio via npx)\n\n## Security and boundaries\n\n**Opt-in (HCP):** The `codescene` block in `mcp-configs\u002Fmcp-servers.json` is a template only. HCP plugin installs do not auto-enable bundled MCP servers. Copy the entry into your config only if you want it. You can exclude it during HCP install\u002Fsync with `ECC_DISABLED_MCPS=codescene,...`.\n\n**Credentials:** No bundled token. Set `CS_ACCESS_TOKEN` yourself (see [getting-a-personal-access-token.md](https:\u002F\u002Fgithub.com\u002Fcodescene-oss\u002Fcodescene-mcp-server\u002Fblob\u002Fmain\u002Fdocs\u002Fgetting-a-personal-access-token.md) in the upstream repo). Never commit tokens to the repo.\n\n**What the tools read:** When invoked, tools analyze files and git state **in the local repository** you point them at (paths you pass, plus branch context for `analyze_change_set`). They do not run by themselves. For standalone mode, follow upstream privacy docs: [codescene-mcp-server README](https:\u002F\u002Fgithub.com\u002Fcodescene-oss\u002Fcodescene-mcp-server#frequently-asked-questions) and [CodeScene policies](https:\u002F\u002Fcodescene.com\u002Fpolicies). Do not use this skill for secrets, credentials, or paths you do not want analyzed.\n\n**If the MCP is unavailable (offline, bad token, server crash):** Do not invent Code Health scores. Tell the user the check was skipped. Continue only with explicit user approval. Prefer lint\u002Ftests\u002Fverification-loop for gating when MCP is down. Re-enable checks once the server connects.\n\n## When to Use\n\n- User asks to **review code quality**, **refactor** a file, or check if **AI changes degraded** maintainability\n- Before editing a **hotspot**, legacy module, or unfamiliar file\n- Before **commit** or **pull request** when you need a maintainability safeguard\n- After a large agent-written diff — verify Code Health did not regress\n- Pair with `verification-loop`, `tdd-workflow`, or `\u002Fquality-gate` as a structural check (not a replacement for tests\u002Flint)\n\n## When to Activate\n\nSame triggers as **When to Use** above — this heading is what HCP uses for skill auto-activation.\n\n## How It Works\n\n### 1. Connect the MCP server\n\nCopy the `codescene` entry from `mcp-configs\u002Fmcp-servers.json` into your harness MCP config.\n\n**Claude Code** (`~\u002F.claude.json` → `mcpServers`):\n\n```json\n\"codescene\": {\n  \"command\": \"npx\",\n  \"args\": [\"-y\", \"@codescene\u002Fcodehealth-mcp\"],\n  \"env\": {\n    \"CS_ACCESS_TOKEN\": \"YOUR_CS_ACCESS_TOKEN_HERE\"\n  }\n}\n```\n\n**Project-scoped:** merge the same block into `.mcp.json` at the repo root.\n\nToken setup is documented in the upstream repo (link above). Standalone mode does not require a paid CodeScene platform account for the four tools listed below. Restart the session and confirm the `codescene` server is connected before relying on scores.\n\n### 2. Call standalone tools only\n\n| Tool | When to use |\n|------|-------------|\n| `code_health_review` | Full structural analysis **before** modifying a file |\n| `code_health_score` | Quick numeric score after each change (delta check) |\n| `pre_commit_code_health_safeguard` | Block commits that introduce Code Health regressions |\n| `analyze_change_set` | Branch-level check **before** opening a PR |\n\nDo **not** call platform-only tools (e.g. repository-wide technical debt hotspot lists). Do **not** reference `delta_analysis` — not available on standalone.\n\n### 3. Interpret scores (1–10)\n\n| Range | Meaning | Agent behavior |\n|-------|---------|----------------|\n| **9.0–10.0** | Green — healthy | Safer to extend; still prefer vertical slices |\n| **4.0–8.9** | Yellow — debt | Tread carefully; no drive-by refactors |\n| **1.0–3.9** | Red — severe debt | Narrow scope only |\n\n### 4. Run the feedback loop\n\n**Before touching a file**\n\n1. Run `code_health_review` on the target path.\n2. Record baseline score and listed code smells.\n3. Plan the smallest change that addresses the task.\n\nScope by score: **below 5** — minimal diff only; **5–7** — no broad refactors; **above 7** — safer to refactor, still verify after each edit.\n\n**After each change**\n\n1. Run `code_health_score` on the same file.\n2. Compare to the baseline from `code_health_review`.\n3. If the score **regressed**, fix before continuing. Never mark the task done while the score is lower than when you started.\n\n**Before every commit** — run `pre_commit_code_health_safeguard` on the repository path.\n\n**Before a PR** — run `analyze_change_set` against the base branch (e.g. `main`).\n\n## Examples\n\n### Example: Flask maintainability improvement\n\nOn `pallets\u002Fflask`, an agent loop using only standalone tools:\n\n1. `code_health_review` on a target module (baseline **4.82**)\n2. Targeted refactor addressing listed smells\n3. `code_health_score` after each edit\n4. `pre_commit_code_health_safeguard` before commit\n5. `analyze_change_set` before PR\n\nResult: Code Health **4.82 → 9.1** (free standalone token only).\n\n### Example: AGENTS.md enforcement block\n\nPaste into the project `AGENTS.md` or `CLAUDE.md`:\n\n```md\n## Code Health (CodeScene MCP)\n\nBefore modifying any file: run `code_health_review`, note score and issues.\n\n- Score below 5: problematic range — scope changes narrowly.\n- Score 5–7: warning range — no broad refactors.\n\nAfter each change: run `code_health_score` to verify delta.\n\n- If score regressed: fix before continuing; never declare done if score dropped.\n\nBefore every commit: run `pre_commit_code_health_safeguard`.\n\nBefore PR: run `analyze_change_set`.\n```\n\n### Example: anti-patterns vs correct loop\n\n```markdown\n# BAD: Edit first, check later\n[large refactor without code_health_review]\n\n# BAD: Ignore score drop\n\"Tests pass\" → mark task done while Code Health decreased\n\n# BAD: Broad refactor on red-score file (below 5)\nDrive-by cleanup across the module\n\n# GOOD: review → small change → score → commit safeguard → analyze_change_set\n```\n\n## Pairing with HCP\n\n| HCP skill \u002F flow | Code Health MCP role |\n|------------------|----------------------|\n| `coding-standards` | Style\u002Fnaming; Code Health = structure\u002Fcomplexity |\n| `plankton-code-quality` | Write-time lint\u002Fformat; Code Health = pre\u002Fpost edit structural gate |\n| `verification-loop` \u002F `\u002Fquality-gate` | Add structural regression check before \"done\" |\n| `security-review` | Security vs maintainability — use both when relevant |\n| `tdd-workflow` | Tests pass ≠ healthy design — check score after refactors |\n\n**Context tip:** HCP recommends keeping MCP count low. Enable `codescene` when doing substantive edits; disable when not needed.\n\n## Related Skills\n\n- `coding-standards` — baseline conventions\n- `plankton-code-quality` — write-time lint\u002Fformat hooks\n- `verification-loop` — build\u002Ftest\u002Flint gate\n- `tdd-workflow` — test-first development\n- `security-review` — security checklist\n- `documentation-lookup` — library docs via Context7 (orthogonal)\n","# Code Health MCP (CodeScene)\n\nStructural maintainability feedback for AI-assisted coding. Complements style\u002Flint skills (`coding-standards`, `plankton-code-quality`) with **design-level** health scores and regression gates.\n\n**Upstream:** [codescene-oss\u002Fcodescene-mcp-server](https:\u002F\u002Fgithub.com\u002Fcodescene-oss\u002Fcodescene-mcp-server)\n**Package:** `@codescene\u002Fcodehealth-mcp` (stdio via npx)\n\n## Security and boundaries\n\n**Opt-in (HCP):** The `codescene` block in `mcp-configs\u002Fmcp-servers.json` is a template only. HCP plugin installs do not auto-enable bundled MCP servers. Copy the entry into your config only if you want it. You can exclude it during HCP install\u002Fsync with `ECC_DISABLED_MCPS=codescene,...`.\n\n**Credentials:** No bundled token. Set `CS_ACCESS_TOKEN` yourself (see [getting-a-personal-access-token.md](https:\u002F\u002Fgithub.com\u002Fcodescene-oss\u002Fcodescene-mcp-server\u002Fblob\u002Fmain\u002Fdocs\u002Fgetting-a-personal-access-token.md) in the upstream repo). Never commit tokens to the repo.\n\n**What the tools read:** When invoked, tools analyze files and git state **in the local repository** you point them at (paths you pass, plus branch context for `analyze_change_set`). They do not run by themselves. For standalone mode, follow upstream privacy docs: [codescene-mcp-server README](https:\u002F\u002Fgithub.com\u002Fcodescene-oss\u002Fcodescene-mcp-server#frequently-asked-questions) and [CodeScene policies](https:\u002F\u002Fcodescene.com\u002Fpolicies). Do not use this skill for secrets, credentials, or paths you do not want analyzed.\n\n**If the MCP is unavailable (offline, bad token, server crash):** Do not invent Code Health scores. Tell the user the check was skipped. Continue only with explicit user approval. Prefer lint\u002Ftests\u002Fverification-loop for gating when MCP is down. Re-enable checks once the server connects.\n\n## When to Use\n\n- User asks to **review code quality**, **refactor** a file, or check if **AI changes degraded** maintainability\n- Before editing a **hotspot**, legacy module, or unfamiliar file\n- Before **commit** or **pull request** when you need a maintainability safeguard\n- After a large agent-written diff — verify Code Health did not regress\n- Pair with `verification-loop`, `tdd-workflow`, or `\u002Fquality-gate` as a structural check (not a replacement for tests\u002Flint)\n\n## When to Activate\n\nSame triggers as **When to Use** above — this heading is what HCP uses for skill auto-activation.\n\n## How It Works\n\n### 1. Connect the MCP server\n\nCopy the `codescene` entry from `mcp-configs\u002Fmcp-servers.json` into your harness MCP config.\n\n**Claude Code** (`~\u002F.claude.json` → `mcpServers`):\n\n```json\n\"codescene\": {\n  \"command\": \"npx\",\n  \"args\": [\"-y\", \"@codescene\u002Fcodehealth-mcp\"],\n  \"env\": {\n    \"CS_ACCESS_TOKEN\": \"YOUR_CS_ACCESS_TOKEN_HERE\"\n  }\n}\n```\n\n**Project-scoped:** merge the same block into `.mcp.json` at the repo root.\n\nToken setup is documented in the upstream repo (link above). Standalone mode does not require a paid CodeScene platform account for the four tools listed below. Restart the session and confirm the `codescene` server is connected before relying on scores.\n\n### 2. Call standalone tools only\n\n| Tool | When to use |\n|------|-------------|\n| `code_health_review` | Full structural analysis **before** modifying a file |\n| `code_health_score` | Quick numeric score after each change (delta check) |\n| `pre_commit_code_health_safeguard` | Block commits that introduce Code Health regressions |\n| `analyze_change_set` | Branch-level check **before** opening a PR |\n\nDo **not** call platform-only tools (e.g. repository-wide technical debt hotspot lists). Do **not** reference `delta_analysis` — not available on standalone.\n\n### 3. Interpret scores (1–10)\n\n| Range | Meaning | Agent behavior |\n|-------|---------|----------------|\n| **9.0–10.0** | Green — healthy | Safer to extend; still prefer vertical slices |\n| **4.0–8.9** | Yellow — debt | Tread carefully; no drive-by refactors |\n| **1.0–3.9** | Red — severe debt | Narrow scope only |\n\n### 4. Run the feedback loop\n\n**Before touching a file**\n\n1. Run `code_health_review` on the target path.\n2. Record baseline score and listed code smells.\n3. Plan the smallest change that addresses the task.\n\nScope by score: **below 5** — minimal diff only; **5–7** — no broad refactors; **above 7** — safer to refactor, still verify after each edit.\n\n**After each change**\n\n1. Run `code_health_score` on the same file.\n2. Compare to the baseline from `code_health_review`.\n3. If the score **regressed**, fix before continuing. Never mark the task done while the score is lower than when you started.\n\n**Before every commit** — run `pre_commit_code_health_safeguard` on the repository path.\n\n**Before a PR** — run `analyze_change_set` against the base branch (e.g. `main`).\n\n## Examples\n\n### Example: Flask maintainability improvement\n\nOn `pallets\u002Fflask`, an agent loop using only standalone tools:\n\n1. `code_health_review` on a target module (baseline **4.82**)\n2. Targeted refactor addressing listed smells\n3. `code_health_score` after each edit\n4. `pre_commit_code_health_safeguard` before commit\n5. `analyze_change_set` before PR\n\nResult: Code Health **4.82 → 9.1** (free standalone token only).\n\n### Example: AGENTS.md enforcement block\n\nPaste into the project `AGENTS.md` or `CLAUDE.md`:\n\n```md\n## Code Health (CodeScene MCP)\n\nBefore modifying any file: run `code_health_review`, note score and issues.\n\n- Score below 5: problematic range — scope changes narrowly.\n- Score 5–7: warning range — no broad refactors.\n\nAfter each change: run `code_health_score` to verify delta.\n\n- If score regressed: fix before continuing; never declare done if score dropped.\n\nBefore every commit: run `pre_commit_code_health_safeguard`.\n\nBefore PR: run `analyze_change_set`.\n```\n\n### Example: anti-patterns vs correct loop\n\n```markdown\n# BAD: Edit first, check later\n[large refactor without code_health_review]\n\n# BAD: Ignore score drop\n\"Tests pass\" → mark task done while Code Health decreased\n\n# BAD: Broad refactor on red-score file (below 5)\nDrive-by cleanup across the module\n\n# GOOD: review → small change → score → commit safeguard → analyze_change_set\n```\n\n## Pairing with HCP\n\n| HCP skill \u002F flow | Code Health MCP role |\n|------------------|----------------------|\n| `coding-standards` | Style\u002Fnaming; Code Health = structure\u002Fcomplexity |\n| `plankton-code-quality` | Write-time lint\u002Fformat; Code Health = pre\u002Fpost edit structural gate |\n| `verification-loop` \u002F `\u002Fquality-gate` | Add structural regression check before \"done\" |\n| `security-review` | Security vs maintainability — use both when relevant |\n| `tdd-workflow` | Tests pass ≠ healthy design — check score after refactors |\n\n**Context tip:** HCP recommends keeping MCP count low. Enable `codescene` when doing substantive edits; disable when not needed.\n\n## Related Skills\n\n- `coding-standards` — baseline conventions\n- `plankton-code-quality` — write-time lint\u002Fformat hooks\n- `verification-loop` — build\u002Ftest\u002Flint gate\n- `tdd-workflow` — test-first development\n- `security-review` — security checklist\n- `documentation-lookup` — library docs via Context7 (orthogonal)\n",{"name":5,"metadata":24,"description":7},{"origin":25},"community","main","c9103dbad48ef3005f163584d0f2abd4591217f6","skills\u002Fecc-codehealth-mcp",1,"https:\u002F\u002Fgithub.com\u002F503496348-ops\u002Fmischief-production","https:\u002F\u002Fgithub.com\u002F503496348-ops","https:\u002F\u002F503496348-ops.github.io\u002Fatomcollide-product-matrix\u002F#tree","元素碰撞-AtomCollide-AI 智能体实验室 测试人专属成长社群 正式招募\r\n我们的目标很纯粹：连接每一位测试工程师\u002FAI使用探索与爱好者，让你在这里既能扎实打磨技术硬实力，也能打通职业晋升的新通路，这是一个专注于AI领域的开源组","2026-07-30 00:35:42",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add 503496348-ops\u002Fmischief-production --skill codehealth-mcp",{"tool":41,"command":42},"bunx","bunx skills add 503496348-ops\u002Fmischief-production --skill codehealth-mcp",{"tool":44,"command":45},"pnpm","pnpm dlx skills add 503496348-ops\u002Fmischief-production --skill codehealth-mcp","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F503496348-ops\u002Fmischief-production\u002Fblob\u002Fmain\u002Fskills\u002Fecc-codehealth-mcp\u002FSKILL.md",true,[],[50,57,64,71,78,85],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M77YG7NPZHE751W9QGK3H9ED","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002F503496348-ops\u002Fmischief-production\u002Fblob\u002Fmain\u002Fskills\u002Fsp-writing-skills\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M77YG4HPYH0GJP974DZ6KCPQ","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002F503496348-ops\u002Fmischief-production\u002Fblob\u002Fmain\u002Fskills\u002Fsp-writing-plans\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M77YFZW1FZ1GVC5C89NPE5M8","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002F503496348-ops\u002Fmischief-production\u002Fblob\u002Fmain\u002Fskills\u002Fsp-verification-before-completion\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M77YFVPWANT5VE5GWBTKHPA2","using-智械工程","Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions","https:\u002F\u002Fgithub.com\u002F503496348-ops\u002Fmischief-production\u002Fblob\u002Fmain\u002Fskills\u002Fsp-using-superpowers\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M77YFQJAW5PX3QYSBCD3B24S","using-git-worktrees","Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback","https:\u002F\u002Fgithub.com\u002F503496348-ops\u002Fmischief-production\u002Fblob\u002Fmain\u002Fskills\u002Fsp-using-git-worktrees\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M77YFMSTB70VX8W2QHNJWYB0","test-driven-development","Use when implementing any feature or bugfix, before writing implementation code","https:\u002F\u002Fgithub.com\u002F503496348-ops\u002Fmischief-production\u002Fblob\u002Fmain\u002Fskills\u002Fsp-test-driven-development\u002FSKILL.md",[],[]]