[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F2TFZVYAYXS2YV02386KBC":3,"skill-same:01M7F2TFZVYAYXS2YV02386KBC":48},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":12,"updatedAt":34,"install":35,"resources":47},"01M7F2TFZVYAYXS2YV02386KBC","audit-codebase",null,"Codebase health audit scoring 7 categories with progression plan","313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace","313DEVGRP","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F34762848?v=4","01M7F2M535Z5X8XGHYD8TDVAB3","A-RMS by 313DEVGRP","01M7F2M54CR0P3631F4YM0D014",0,"MIT","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Faudit-codebase\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: audit-codebase\ndescription: Codebase health audit scoring 7 categories with progression plan\nargument-hint: \"[path] [--focus security|performance|quality]\"\neffort: medium\ndisable-model-invocation: true\n---\n\n# Codebase health audit\n\nScore your codebase across 7 health categories, identify weak spots, and get a prioritized progression plan. Each category is scored 1-10 with specific, actionable findings.\n\n**Time**: 3-8 minutes depending on codebase size | **Scope**: Full project\n\n## Instructions\n\nYou are a senior engineering consultant performing a codebase health assessment. Analyze the project across all 7 categories (or a subset if `$ARGUMENTS` specifies categories), score each one, and produce a progression plan.\n\nIf `$ARGUMENTS` contains category names (e.g., \"secrets security tests\"), only audit those categories. Otherwise, audit all 7.\n\n---\n\n### Category 1: Secrets (weight: 15%)\n\nScan for hardcoded credentials, API keys, and sensitive data in code.\n\n```bash\n# API keys and tokens in code\ngrep -rn --include=\"*.{js,ts,py,go,java,rb,php,yaml,yml,json,toml,env,cfg,ini,conf}\" \\\n  -E '(?i)(api[_-]?key|apikey|secret[_-]?key|password|passwd|token|bearer)\\s*[=:]\\s*[\"'\\''\"][^\"'\\'']{8,}' \\\n  --exclude-dir={node_modules,vendor,.git,dist,build,target,__pycache__,.venv} . 2>\u002Fdev\u002Fnull | head -20\n\n# Known provider patterns\ngrep -rn -E 'sk-[a-zA-Z0-9]{20,}|ghp_[a-zA-Z0-9]{36}|AKIA[A-Z0-9]{16}|xox[bps]-[a-zA-Z0-9\\-]{20,}' \\\n  --exclude-dir={node_modules,vendor,.git,dist,build,target} . 2>\u002Fdev\u002Fnull | head -10\n\n# .env files committed\nfind . -name \".env*\" -not -name \".env.example\" -not -path \"*\u002Fnode_modules\u002F*\" -not -path \"*\u002F.git\u002F*\" -type f 2>\u002Fdev\u002Fnull\n\n# .gitignore coverage\n[ -f \".gitignore\" ] && {\n  for pattern in \".env\" \"*.pem\" \"*.key\" \"*.p12\"; do\n    grep -q \"$pattern\" .gitignore 2>\u002Fdev\u002Fnull && echo \"OK: $pattern in .gitignore\" || echo \"MISSING: $pattern not in .gitignore\"\n  done\n}\n```\n\n**Scoring:**\n- 10: Zero secrets, .gitignore covers all sensitive patterns, .env.example exists\n- 7-9: No secrets in code, minor .gitignore gaps\n- 4-6: 1-3 potential secrets found (may be false positives), or .env committed\n- 1-3: Multiple secrets in code, private keys committed, no .gitignore protection\n\n---\n\n### Category 2: Security (weight: 15%)\n\nCheck for OWASP-style vulnerabilities and unsafe patterns.\n\n```bash\n# SQL injection patterns\ngrep -rn --include=\"*.{js,ts,py,java,go,rb,php}\" \\\n  -E '(query|execute|exec)\\s*\\(\\s*[`\"'\\''\"].*\\+|\\$\\{|%s|\\.format\\(' \\\n  --exclude-dir={node_modules,vendor,.git,dist,build,target,test,__test__} . 2>\u002Fdev\u002Fnull | head -15\n\n# eval\u002Fexec usage\ngrep -rn -E '\\b(eval|exec|execSync|Function\\(|setTimeout\\([^,]*[+`]|setInterval\\([^,]*[+`])' \\\n  --include=\"*.{js,ts,py}\" --exclude-dir={node_modules,vendor,.git,dist} . 2>\u002Fdev\u002Fnull | head -10\n\n# Unsafe deserialization\ngrep -rn -E '(pickle\\.loads|yaml\\.load\\(|JSON\\.parse\\(.*user|unserialize\\()' \\\n  --exclude-dir={node_modules,vendor,.git,dist} . 2>\u002Fdev\u002Fnull | head -10\n\n# Missing input validation on routes\u002Fendpoints\ngrep -rn -E '(app\\.(get|post|put|delete|patch)|router\\.(get|post|put|delete))' \\\n  --include=\"*.{js,ts}\" --exclude-dir={node_modules,.git,dist} . 2>\u002Fdev\u002Fnull | wc -l\n```\n\n**Scoring:**\n- 10: No injection patterns, no eval\u002Fexec, input validation on all endpoints, CSP headers\n- 7-9: Minor issues (1-2 eval usages in non-user-facing code)\n- 4-6: Some injection patterns, missing validation on several endpoints\n- 1-3: Active SQL injection risk, eval with user input, no input sanitization\n\n---\n\n### Category 3: Dependencies (weight: 15%)\n\nAudit package health, known CVEs, and freshness.\n\n```bash\n# Node.js audit\n[ -f \"package-lock.json\" ] && npm audit --json 2>\u002Fdev\u002Fnull | jq '.metadata.vulnerabilities' 2>\u002Fdev\u002Fnull\n[ -f \"package.json\" ] && npx npm-check 2>\u002Fdev\u002Fnull | tail -20\n\n# Python\n[ -f \"requirements.txt\" ] && pip-audit -r requirements.txt 2>\u002Fdev\u002Fnull | tail -20\n[ -f \"pyproject.toml\" ] && pip-audit 2>\u002Fdev\u002Fnull | tail -20\n\n# Rust\n[ -f \"Cargo.toml\" ] && cargo audit 2>\u002Fdev\u002Fnull | tail -20\n\n# Go\n[ -f \"go.mod\" ] && govulncheck .\u002F... 2>\u002Fdev\u002Fnull | tail -20\n\n# Lockfile presence\nfor lockfile in package-lock.json yarn.lock pnpm-lock.yaml Cargo.lock go.sum poetry.lock; do\n  [ -f \"$lockfile\" ] && echo \"OK: $lockfile exists\"\ndone\n[ ! -f \"package-lock.json\" ] && [ ! -f \"yarn.lock\" ] && [ ! -f \"pnpm-lock.yaml\" ] && [ -f \"package.json\" ] && echo \"MISSING: No lockfile for Node.js project\"\n```\n\n**Scoring:**\n- 10: Zero CVEs, lockfile present, all dependencies \u003C6 months old\n- 7-9: No critical\u002Fhigh CVEs, minor outdated packages\n- 4-6: 1-3 high CVEs, or >50% dependencies outdated by a year+\n- 1-3: Critical CVEs, no lockfile, abandoned dependencies\n\n---\n\n### Category 4: Structure (weight: 10%)\n\nEvaluate file organization, naming conventions, and module boundaries.\n\n```bash\n# File count per top-level directory\nfor dir in *\u002F; do\n  [ -d \"$dir\" ] && [ \"$dir\" != \"node_modules\u002F\" ] && [ \"$dir\" != \".git\u002F\" ] && [ \"$dir\" != \"vendor\u002F\" ] && \\\n    echo \"$dir: $(find \"$dir\" -type f -not -path \"*\u002Fnode_modules\u002F*\" -not -path \"*\u002F.git\u002F*\" 2>\u002Fdev\u002Fnull | wc -l) files\"\ndone\n\n# Deeply nested files (complexity indicator)\nfind . -type f -not -path \"*\u002Fnode_modules\u002F*\" -not -path \"*\u002F.git\u002F*\" -not -path \"*\u002Fvendor\u002F*\" -mindepth 6 2>\u002Fdev\u002Fnull | head -10\n\n# Mixed naming conventions\nfind . -type f -name \"*_*\" -not -path \"*\u002Fnode_modules\u002F*\" -not -path \"*\u002F.git\u002F*\" 2>\u002Fdev\u002Fnull | head -5\nfind . -type f -name \"*-*\" -not -path \"*\u002Fnode_modules\u002F*\" -not -path \"*\u002F.git\u002F*\" 2>\u002Fdev\u002Fnull | head -5\n\n# Circular dependency indicators (for JS\u002FTS projects)\n[ -f \"package.json\" ] && npx madge --circular --extensions ts,js src\u002F 2>\u002Fdev\u002Fnull | head -20\n```\n\n**Scoring:**\n- 10: Clear module boundaries, consistent naming, no circular deps, flat hierarchy\n- 7-9: Good structure with minor inconsistencies\n- 4-6: Mixed conventions, some circular deps, unclear module boundaries\n- 1-3: No clear structure, deeply nested files, widespread circular deps\n\n---\n\n### Category 5: Tests (weight: 15%)\n\nAssess test coverage, test quality, and testing practices.\n\n```bash\n# Test file count vs source file count\nTEST_COUNT=$(find . -type f \\( -name \"*.test.*\" -o -name \"*.spec.*\" -o -name \"test_*\" -o -path \"*\u002Ftest\u002F*\" -o -path \"*\u002F__tests__\u002F*\" \\) \\\n  -not -path \"*\u002Fnode_modules\u002F*\" -not -path \"*\u002F.git\u002F*\" 2>\u002Fdev\u002Fnull | wc -l)\nSRC_COUNT=$(find . -type f \\( -name \"*.ts\" -o -name \"*.js\" -o -name \"*.py\" -o -name \"*.go\" -o -name \"*.java\" \\) \\\n  -not -name \"*.test.*\" -not -name \"*.spec.*\" -not -name \"test_*\" \\\n  -not -path \"*\u002Fnode_modules\u002F*\" -not -path \"*\u002F.git\u002F*\" -not -path \"*\u002Fdist\u002F*\" 2>\u002Fdev\u002Fnull | wc -l)\necho \"Test files: $TEST_COUNT | Source files: $SRC_COUNT | Ratio: $(echo \"scale=2; $TEST_COUNT \u002F ($SRC_COUNT + 1)\" | bc)\"\n\n# Coverage config presence\nfor cfg in jest.config.* vitest.config.* .nycrc .coveragerc pytest.ini setup.cfg; do\n  [ -f \"$cfg\" ] && echo \"OK: $cfg exists\"\ndone\n\n# Coverage report (if available)\n[ -d \"coverage\" ] && [ -f \"coverage\u002Fcoverage-summary.json\" ] && cat coverage\u002Fcoverage-summary.json | jq '.total' 2>\u002Fdev\u002Fnull\n\n# Snapshot test count (potential maintenance burden)\nfind . -name \"*.snap\" -not -path \"*\u002Fnode_modules\u002F*\" 2>\u002Fdev\u002Fnull | wc -l\n```\n\n**Scoring:**\n- 10: >0.8 test ratio, coverage >80%, CI runs tests, no stale snapshots\n- 7-9: >0.5 test ratio, coverage >60%, coverage config present\n- 4-6: Some tests exist but gaps are obvious, no coverage tracking\n- 1-3: \u003C0.2 test ratio or no tests at all\n\n---\n\n### Category 6: Imports (weight: 10%)\n\nCheck for unused imports, circular dependencies, and type coverage.\n\n```bash\n# Unused imports (TypeScript\u002FJavaScript)\n[ -f \"tsconfig.json\" ] && npx tsc --noEmit 2>&1 | grep -c \"declared but\" 2>\u002Fdev\u002Fnull\n[ -f \"tsconfig.json\" ] && npx tsc --noEmit 2>&1 | grep \"declared but\" | head -10\n\n# TypeScript strict mode\n[ -f \"tsconfig.json\" ] && grep -E '\"strict\"|\"noImplicitAny\"|\"strictNullChecks\"' tsconfig.json 2>\u002Fdev\u002Fnull\n\n# Python unused imports\n[ -f \"pyproject.toml\" ] || [ -f \"setup.py\" ] && python -m pyflakes . 2>\u002Fdev\u002Fnull | grep \"imported but unused\" | head -10\n\n# Wildcard imports (code smell)\ngrep -rn 'import \\*' --include=\"*.{py,ts,js}\" --exclude-dir={node_modules,vendor,.git} . 2>\u002Fdev\u002Fnull | head -10\n```\n\n**Scoring:**\n- 10: Zero unused imports, TypeScript strict mode, no wildcard imports\n- 7-9: \u003C5 unused imports, strict mode enabled with minor gaps\n- 4-6: 5-20 unused imports, no strict mode, some wildcard imports\n- 1-3: >20 unused imports, widespread wildcard imports, no type checking\n\n---\n\n### Category 7: AI patterns (weight: 20%)\n\nEvaluate Claude Code configuration maturity and AI-assisted development readiness.\n\n```bash\n# CLAUDE.md presence and quality\n[ -f \"CLAUDE.md\" ] && echo \"OK: CLAUDE.md exists ($(wc -l \u003C CLAUDE.md) lines)\" || echo \"MISSING: No CLAUDE.md\"\n[ -f \".claude\u002Fsettings.json\" ] && echo \"OK: .claude\u002Fsettings.json exists\" || echo \"MISSING: No .claude\u002Fsettings.json\"\n\n# Custom commands\nCOMMANDS=$(find .claude\u002Fcommands -name \"*.md\" 2>\u002Fdev\u002Fnull | wc -l)\necho \"Custom commands: $COMMANDS\"\n\n# Hooks\nHOOKS_CFG=$(grep -c \"hooks\" .claude\u002Fsettings.json 2>\u002Fdev\u002Fnull || echo \"0\")\necho \"Hook configurations: $HOOKS_CFG\"\n\n# Rules files\nRULES=$(find .claude\u002Frules -name \"*.md\" 2>\u002Fdev\u002Fnull | wc -l)\necho \"Rule files: $RULES\"\n\n# Agents\nAGENTS=$(find .claude\u002Fagents -name \"*.md\" 2>\u002Fdev\u002Fnull | wc -l)\necho \"Agent definitions: $AGENTS\"\n\n# Skills\nSKILLS=$(find .claude\u002Fskills -name \"*.md\" 2>\u002Fdev\u002Fnull | wc -l)\necho \"Skills: $SKILLS\"\n\n# .gitignore for AI artifacts\ngrep -q \"claude\" .gitignore 2>\u002Fdev\u002Fnull && echo \"OK: Claude patterns in .gitignore\" || echo \"INFO: No Claude patterns in .gitignore\"\n```\n\n**Scoring:**\n- 10: CLAUDE.md with conventions, hooks configured, custom commands, rules, agents\n- 7-9: CLAUDE.md exists with project context, some commands or rules\n- 4-6: Basic CLAUDE.md, no hooks or commands\n- 1-3: No CLAUDE.md or empty CLAUDE.md\n\n---\n\n## Scoring & report\n\n### Overall score calculation\n\n```\nOverall = (Secrets * 0.15) + (Security * 0.15) + (Dependencies * 0.15) +\n          (Structure * 0.10) + (Tests * 0.15) + (Imports * 0.10) +\n          (AI Patterns * 0.20)\n```\n\nRound to one decimal place.\n\n### Output format\n\n```markdown\n## Codebase Health Audit\n\n**Project**: [directory name]\n**Date**: [timestamp]\n**Categories audited**: [all 7 or filtered subset]\n\n### Overall Score: [X.X] \u002F 10\n\n| Category | Score | Weight | Weighted | Key Finding |\n|----------|-------|--------|----------|-------------|\n| Secrets | X\u002F10 | 15% | X.XX | [one-line summary] |\n| Security | X\u002F10 | 15% | X.XX | [one-line summary] |\n| Dependencies | X\u002F10 | 15% | X.XX | [one-line summary] |\n| Structure | X\u002F10 | 10% | X.XX | [one-line summary] |\n| Tests | X\u002F10 | 15% | X.XX | [one-line summary] |\n| Imports | X\u002F10 | 10% | X.XX | [one-line summary] |\n| AI Patterns | X\u002F10 | 20% | X.XX | [one-line summary] |\n| **Overall** | | **100%** | **X.XX** | |\n\n### Detailed Findings\n\n#### 🔴 Critical (fix immediately)\n- [Finding with file:line reference and concrete fix]\n\n#### 🟡 Warning (fix this week)\n- [Finding with context and suggested approach]\n\n#### 🟢 Info (nice to improve)\n- [Observation with optional suggestion]\n\n### Progression Plan\n\n[Based on overall score, show the appropriate tier]\n\n#### Tier 1: Foundation (current score \u003C5, target: 5)\nFocus on eliminating critical risks before anything else.\n\n| Priority | Action | Category | Impact | Effort |\n|----------|--------|----------|--------|--------|\n| 1 | [specific action] | [category] | [score gain] | [time estimate] |\n| 2 | [specific action] | [category] | [score gain] | [time estimate] |\n| ... | | | | |\n\n#### Tier 2: Solid (current score 5-7, target: 8)\nBuild reliable practices on top of the foundation.\n\n| Priority | Action | Category | Impact | Effort |\n|----------|--------|----------|--------|--------|\n| 1 | [specific action] | [category] | [score gain] | [time estimate] |\n| ... | | | | |\n\n#### Tier 3: Excellent (current score 8+, target: 10)\nPolish and optimize for maximum team velocity.\n\n| Priority | Action | Category | Impact | Effort |\n|----------|--------|----------|--------|--------|\n| 1 | [specific action] | [category] | [score gain] | [time estimate] |\n| ... | | | | |\n\n### Quick Wins (\u003C 30 minutes each)\n1. [Action that improves score with minimal effort]\n2. [...]\n3. [...]\n```\n\n### Severity split\n\nApproximately 70% of findings should be automatable (scripts, linters, CI checks can detect them). Flag the remaining 30% as requiring human judgment, and explain why automation falls short for those cases.\n\n---\n\n**Sources**:\n- Variant Systems codebase analyzer plugin (variantsystems.io, Feb 2026): 7-category analysis framework\n- OWASP Top 10 (2021): Security category patterns\n- Claude Code Security Hardening Guide: AI Patterns category baseline\n\n$ARGUMENTS\n","# Codebase health audit\n\nScore your codebase across 7 health categories, identify weak spots, and get a prioritized progression plan. Each category is scored 1-10 with specific, actionable findings.\n\n**Time**: 3-8 minutes depending on codebase size | **Scope**: Full project\n\n## Instructions\n\nYou are a senior engineering consultant performing a codebase health assessment. Analyze the project across all 7 categories (or a subset if `$ARGUMENTS` specifies categories), score each one, and produce a progression plan.\n\nIf `$ARGUMENTS` contains category names (e.g., \"secrets security tests\"), only audit those categories. Otherwise, audit all 7.\n\n---\n\n### Category 1: Secrets (weight: 15%)\n\nScan for hardcoded credentials, API keys, and sensitive data in code.\n\n```bash\n# API keys and tokens in code\ngrep -rn --include=\"*.{js,ts,py,go,java,rb,php,yaml,yml,json,toml,env,cfg,ini,conf}\" \\\n  -E '(?i)(api[_-]?key|apikey|secret[_-]?key|password|passwd|token|bearer)\\s*[=:]\\s*[\"'\\''\"][^\"'\\'']{8,}' \\\n  --exclude-dir={node_modules,vendor,.git,dist,build,target,__pycache__,.venv} . 2>\u002Fdev\u002Fnull | head -20\n\n# Known provider patterns\ngrep -rn -E 'sk-[a-zA-Z0-9]{20,}|ghp_[a-zA-Z0-9]{36}|AKIA[A-Z0-9]{16}|xox[bps]-[a-zA-Z0-9\\-]{20,}' \\\n  --exclude-dir={node_modules,vendor,.git,dist,build,target} . 2>\u002Fdev\u002Fnull | head -10\n\n# .env files committed\nfind . -name \".env*\" -not -name \".env.example\" -not -path \"*\u002Fnode_modules\u002F*\" -not -path \"*\u002F.git\u002F*\" -type f 2>\u002Fdev\u002Fnull\n\n# .gitignore coverage\n[ -f \".gitignore\" ] && {\n  for pattern in \".env\" \"*.pem\" \"*.key\" \"*.p12\"; do\n    grep -q \"$pattern\" .gitignore 2>\u002Fdev\u002Fnull && echo \"OK: $pattern in .gitignore\" || echo \"MISSING: $pattern not in .gitignore\"\n  done\n}\n```\n\n**Scoring:**\n- 10: Zero secrets, .gitignore covers all sensitive patterns, .env.example exists\n- 7-9: No secrets in code, minor .gitignore gaps\n- 4-6: 1-3 potential secrets found (may be false positives), or .env committed\n- 1-3: Multiple secrets in code, private keys committed, no .gitignore protection\n\n---\n\n### Category 2: Security (weight: 15%)\n\nCheck for OWASP-style vulnerabilities and unsafe patterns.\n\n```bash\n# SQL injection patterns\ngrep -rn --include=\"*.{js,ts,py,java,go,rb,php}\" \\\n  -E '(query|execute|exec)\\s*\\(\\s*[`\"'\\''\"].*\\+|\\$\\{|%s|\\.format\\(' \\\n  --exclude-dir={node_modules,vendor,.git,dist,build,target,test,__test__} . 2>\u002Fdev\u002Fnull | head -15\n\n# eval\u002Fexec usage\ngrep -rn -E '\\b(eval|exec|execSync|Function\\(|setTimeout\\([^,]*[+`]|setInterval\\([^,]*[+`])' \\\n  --include=\"*.{js,ts,py}\" --exclude-dir={node_modules,vendor,.git,dist} . 2>\u002Fdev\u002Fnull | head -10\n\n# Unsafe deserialization\ngrep -rn -E '(pickle\\.loads|yaml\\.load\\(|JSON\\.parse\\(.*user|unserialize\\()' \\\n  --exclude-dir={node_modules,vendor,.git,dist} . 2>\u002Fdev\u002Fnull | head -10\n\n# Missing input validation on routes\u002Fendpoints\ngrep -rn -E '(app\\.(get|post|put|delete|patch)|router\\.(get|post|put|delete))' \\\n  --include=\"*.{js,ts}\" --exclude-dir={node_modules,.git,dist} . 2>\u002Fdev\u002Fnull | wc -l\n```\n\n**Scoring:**\n- 10: No injection patterns, no eval\u002Fexec, input validation on all endpoints, CSP headers\n- 7-9: Minor issues (1-2 eval usages in non-user-facing code)\n- 4-6: Some injection patterns, missing validation on several endpoints\n- 1-3: Active SQL injection risk, eval with user input, no input sanitization\n\n---\n\n### Category 3: Dependencies (weight: 15%)\n\nAudit package health, known CVEs, and freshness.\n\n```bash\n# Node.js audit\n[ -f \"package-lock.json\" ] && npm audit --json 2>\u002Fdev\u002Fnull | jq '.metadata.vulnerabilities' 2>\u002Fdev\u002Fnull\n[ -f \"package.json\" ] && npx npm-check 2>\u002Fdev\u002Fnull | tail -20\n\n# Python\n[ -f \"requirements.txt\" ] && pip-audit -r requirements.txt 2>\u002Fdev\u002Fnull | tail -20\n[ -f \"pyproject.toml\" ] && pip-audit 2>\u002Fdev\u002Fnull | tail -20\n\n# Rust\n[ -f \"Cargo.toml\" ] && cargo audit 2>\u002Fdev\u002Fnull | tail -20\n\n# Go\n[ -f \"go.mod\" ] && govulncheck .\u002F... 2>\u002Fdev\u002Fnull | tail -20\n\n# Lockfile presence\nfor lockfile in package-lock.json yarn.lock pnpm-lock.yaml Cargo.lock go.sum poetry.lock; do\n  [ -f \"$lockfile\" ] && echo \"OK: $lockfile exists\"\ndone\n[ ! -f \"package-lock.json\" ] && [ ! -f \"yarn.lock\" ] && [ ! -f \"pnpm-lock.yaml\" ] && [ -f \"package.json\" ] && echo \"MISSING: No lockfile for Node.js project\"\n```\n\n**Scoring:**\n- 10: Zero CVEs, lockfile present, all dependencies \u003C6 months old\n- 7-9: No critical\u002Fhigh CVEs, minor outdated packages\n- 4-6: 1-3 high CVEs, or >50% dependencies outdated by a year+\n- 1-3: Critical CVEs, no lockfile, abandoned dependencies\n\n---\n\n### Category 4: Structure (weight: 10%)\n\nEvaluate file organization, naming conventions, and module boundaries.\n\n```bash\n# File count per top-level directory\nfor dir in *\u002F; do\n  [ -d \"$dir\" ] && [ \"$dir\" != \"node_modules\u002F\" ] && [ \"$dir\" != \".git\u002F\" ] && [ \"$dir\" != \"vendor\u002F\" ] && \\\n    echo \"$dir: $(find \"$dir\" -type f -not -path \"*\u002Fnode_modules\u002F*\" -not -path \"*\u002F.git\u002F*\" 2>\u002Fdev\u002Fnull | wc -l) files\"\ndone\n\n# Deeply nested files (complexity indicator)\nfind . -type f -not -path \"*\u002Fnode_modules\u002F*\" -not -path \"*\u002F.git\u002F*\" -not -path \"*\u002Fvendor\u002F*\" -mindepth 6 2>\u002Fdev\u002Fnull | head -10\n\n# Mixed naming conventions\nfind . -type f -name \"*_*\" -not -path \"*\u002Fnode_modules\u002F*\" -not -path \"*\u002F.git\u002F*\" 2>\u002Fdev\u002Fnull | head -5\nfind . -type f -name \"*-*\" -not -path \"*\u002Fnode_modules\u002F*\" -not -path \"*\u002F.git\u002F*\" 2>\u002Fdev\u002Fnull | head -5\n\n# Circular dependency indicators (for JS\u002FTS projects)\n[ -f \"package.json\" ] && npx madge --circular --extensions ts,js src\u002F 2>\u002Fdev\u002Fnull | head -20\n```\n\n**Scoring:**\n- 10: Clear module boundaries, consistent naming, no circular deps, flat hierarchy\n- 7-9: Good structure with minor inconsistencies\n- 4-6: Mixed conventions, some circular deps, unclear module boundaries\n- 1-3: No clear structure, deeply nested files, widespread circular deps\n\n---\n\n### Category 5: Tests (weight: 15%)\n\nAssess test coverage, test quality, and testing practices.\n\n```bash\n# Test file count vs source file count\nTEST_COUNT=$(find . -type f \\( -name \"*.test.*\" -o -name \"*.spec.*\" -o -name \"test_*\" -o -path \"*\u002Ftest\u002F*\" -o -path \"*\u002F__tests__\u002F*\" \\) \\\n  -not -path \"*\u002Fnode_modules\u002F*\" -not -path \"*\u002F.git\u002F*\" 2>\u002Fdev\u002Fnull | wc -l)\nSRC_COUNT=$(find . -type f \\( -name \"*.ts\" -o -name \"*.js\" -o -name \"*.py\" -o -name \"*.go\" -o -name \"*.java\" \\) \\\n  -not -name \"*.test.*\" -not -name \"*.spec.*\" -not -name \"test_*\" \\\n  -not -path \"*\u002Fnode_modules\u002F*\" -not -path \"*\u002F.git\u002F*\" -not -path \"*\u002Fdist\u002F*\" 2>\u002Fdev\u002Fnull | wc -l)\necho \"Test files: $TEST_COUNT | Source files: $SRC_COUNT | Ratio: $(echo \"scale=2; $TEST_COUNT \u002F ($SRC_COUNT + 1)\" | bc)\"\n\n# Coverage config presence\nfor cfg in jest.config.* vitest.config.* .nycrc .coveragerc pytest.ini setup.cfg; do\n  [ -f \"$cfg\" ] && echo \"OK: $cfg exists\"\ndone\n\n# Coverage report (if available)\n[ -d \"coverage\" ] && [ -f \"coverage\u002Fcoverage-summary.json\" ] && cat coverage\u002Fcoverage-summary.json | jq '.total' 2>\u002Fdev\u002Fnull\n\n# Snapshot test count (potential maintenance burden)\nfind . -name \"*.snap\" -not -path \"*\u002Fnode_modules\u002F*\" 2>\u002Fdev\u002Fnull | wc -l\n```\n\n**Scoring:**\n- 10: >0.8 test ratio, coverage >80%, CI runs tests, no stale snapshots\n- 7-9: >0.5 test ratio, coverage >60%, coverage config present\n- 4-6: Some tests exist but gaps are obvious, no coverage tracking\n- 1-3: \u003C0.2 test ratio or no tests at all\n\n---\n\n### Category 6: Imports (weight: 10%)\n\nCheck for unused imports, circular dependencies, and type coverage.\n\n```bash\n# Unused imports (TypeScript\u002FJavaScript)\n[ -f \"tsconfig.json\" ] && npx tsc --noEmit 2>&1 | grep -c \"declared but\" 2>\u002Fdev\u002Fnull\n[ -f \"tsconfig.json\" ] && npx tsc --noEmit 2>&1 | grep \"declared but\" | head -10\n\n# TypeScript strict mode\n[ -f \"tsconfig.json\" ] && grep -E '\"strict\"|\"noImplicitAny\"|\"strictNullChecks\"' tsconfig.json 2>\u002Fdev\u002Fnull\n\n# Python unused imports\n[ -f \"pyproject.toml\" ] || [ -f \"setup.py\" ] && python -m pyflakes . 2>\u002Fdev\u002Fnull | grep \"imported but unused\" | head -10\n\n# Wildcard imports (code smell)\ngrep -rn 'import \\*' --include=\"*.{py,ts,js}\" --exclude-dir={node_modules,vendor,.git} . 2>\u002Fdev\u002Fnull | head -10\n```\n\n**Scoring:**\n- 10: Zero unused imports, TypeScript strict mode, no wildcard imports\n- 7-9: \u003C5 unused imports, strict mode enabled with minor gaps\n- 4-6: 5-20 unused imports, no strict mode, some wildcard imports\n- 1-3: >20 unused imports, widespread wildcard imports, no type checking\n\n---\n\n### Category 7: AI patterns (weight: 20%)\n\nEvaluate Claude Code configuration maturity and AI-assisted development readiness.\n\n```bash\n# CLAUDE.md presence and quality\n[ -f \"CLAUDE.md\" ] && echo \"OK: CLAUDE.md exists ($(wc -l \u003C CLAUDE.md) lines)\" || echo \"MISSING: No CLAUDE.md\"\n[ -f \".claude\u002Fsettings.json\" ] && echo \"OK: .claude\u002Fsettings.json exists\" || echo \"MISSING: No .claude\u002Fsettings.json\"\n\n# Custom commands\nCOMMANDS=$(find .claude\u002Fcommands -name \"*.md\" 2>\u002Fdev\u002Fnull | wc -l)\necho \"Custom commands: $COMMANDS\"\n\n# Hooks\nHOOKS_CFG=$(grep -c \"hooks\" .claude\u002Fsettings.json 2>\u002Fdev\u002Fnull || echo \"0\")\necho \"Hook configurations: $HOOKS_CFG\"\n\n# Rules files\nRULES=$(find .claude\u002Frules -name \"*.md\" 2>\u002Fdev\u002Fnull | wc -l)\necho \"Rule files: $RULES\"\n\n# Agents\nAGENTS=$(find .claude\u002Fagents -name \"*.md\" 2>\u002Fdev\u002Fnull | wc -l)\necho \"Agent definitions: $AGENTS\"\n\n# Skills\nSKILLS=$(find .claude\u002Fskills -name \"*.md\" 2>\u002Fdev\u002Fnull | wc -l)\necho \"Skills: $SKILLS\"\n\n# .gitignore for AI artifacts\ngrep -q \"claude\" .gitignore 2>\u002Fdev\u002Fnull && echo \"OK: Claude patterns in .gitignore\" || echo \"INFO: No Claude patterns in .gitignore\"\n```\n\n**Scoring:**\n- 10: CLAUDE.md with conventions, hooks configured, custom commands, rules, agents\n- 7-9: CLAUDE.md exists with project context, some commands or rules\n- 4-6: Basic CLAUDE.md, no hooks or commands\n- 1-3: No CLAUDE.md or empty CLAUDE.md\n\n---\n\n## Scoring & report\n\n### Overall score calculation\n\n```\nOverall = (Secrets * 0.15) + (Security * 0.15) + (Dependencies * 0.15) +\n          (Structure * 0.10) + (Tests * 0.15) + (Imports * 0.10) +\n          (AI Patterns * 0.20)\n```\n\nRound to one decimal place.\n\n### Output format\n\n```markdown\n## Codebase Health Audit\n\n**Project**: [directory name]\n**Date**: [timestamp]\n**Categories audited**: [all 7 or filtered subset]\n\n### Overall Score: [X.X] \u002F 10\n\n| Category | Score | Weight | Weighted | Key Finding |\n|----------|-------|--------|----------|-------------|\n| Secrets | X\u002F10 | 15% | X.XX | [one-line summary] |\n| Security | X\u002F10 | 15% | X.XX | [one-line summary] |\n| Dependencies | X\u002F10 | 15% | X.XX | [one-line summary] |\n| Structure | X\u002F10 | 10% | X.XX | [one-line summary] |\n| Tests | X\u002F10 | 15% | X.XX | [one-line summary] |\n| Imports | X\u002F10 | 10% | X.XX | [one-line summary] |\n| AI Patterns | X\u002F10 | 20% | X.XX | [one-line summary] |\n| **Overall** | | **100%** | **X.XX** | |\n\n### Detailed Findings\n\n#### 🔴 Critical (fix immediately)\n- [Finding with file:line reference and concrete fix]\n\n#### 🟡 Warning (fix this week)\n- [Finding with context and suggested approach]\n\n#### 🟢 Info (nice to improve)\n- [Observation with optional suggestion]\n\n### Progression Plan\n\n[Based on overall score, show the appropriate tier]\n\n#### Tier 1: Foundation (current score \u003C5, target: 5)\nFocus on eliminating critical risks before anything else.\n\n| Priority | Action | Category | Impact | Effort |\n|----------|--------|----------|--------|--------|\n| 1 | [specific action] | [category] | [score gain] | [time estimate] |\n| 2 | [specific action] | [category] | [score gain] | [time estimate] |\n| ... | | | | |\n\n#### Tier 2: Solid (current score 5-7, target: 8)\nBuild reliable practices on top of the foundation.\n\n| Priority | Action | Category | Impact | Effort |\n|----------|--------|----------|--------|--------|\n| 1 | [specific action] | [category] | [score gain] | [time estimate] |\n| ... | | | | |\n\n#### Tier 3: Excellent (current score 8+, target: 10)\nPolish and optimize for maximum team velocity.\n\n| Priority | Action | Category | Impact | Effort |\n|----------|--------|----------|--------|--------|\n| 1 | [specific action] | [category] | [score gain] | [time estimate] |\n| ... | | | | |\n\n### Quick Wins (\u003C 30 minutes each)\n1. [Action that improves score with minimal effort]\n2. [...]\n3. [...]\n```\n\n### Severity split\n\nApproximately 70% of findings should be automatable (scripts, linters, CI checks can detect them). Flag the remaining 30% as requiring human judgment, and explain why automation falls short for those cases.\n\n---\n\n**Sources**:\n- Variant Systems codebase analyzer plugin (variantsystems.io, Feb 2026): 7-category analysis framework\n- OWASP Top 10 (2021): Security category patterns\n- Claude Code Security Hardening Guide: AI Patterns category baseline\n\n$ARGUMENTS\n",{"name":5,"effort":24,"description":7,"argument-hint":25,"disable-model-invocation":26},"medium","[path] [--focus security|performance|quality]",true,"main","f2cc95bc769ca4c3a398965b767dfb41cdf8d698","reference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Faudit-codebase",2,"https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace","https:\u002F\u002Fgithub.com\u002F313DEVGRP","https:\u002F\u002Fwww.a-rms.net","2026-10-18 12:48:10",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":26},[37,40,43],{"tool":38,"command":39},"npx","npx skills add 313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace --skill audit-codebase",{"tool":41,"command":42},"bunx","bunx skills add 313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace --skill audit-codebase",{"tool":44,"command":45},"pnpm","pnpm dlx skills add 313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace --skill audit-codebase","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Faudit-codebase\u002FSKILL.md",[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7F343WNVHZWWYJDD77QEJ7J","voice-refine","Transform verbose voice input into structured, token-efficient Claude prompts. Use when cleaning up voice memos, dictation output, or speech-to-text transcriptions that contain filler words, repetitions, and unstructured thoughts.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fvoice-refine\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7F3417SNXASFTDA1B2X4XYZ","validate-changes","Evaluate staged changes using LLM-as-a-Judge before committing","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fvalidate-changes\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7F33YN9QK88H2B81PVHMNG1","update-threat-db","Delegate threat-intelligence research and updates to AgentSec, then validate the guide and landing mirrors.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fupdate-threat-db\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7F33SXQ57G2FVFK094T4584","token-audit","Audit Claude Code configuration to measure fixed-context token overhead and produce a prioritized action plan. Use when hitting rate limits, experiencing early context compression, or after adding significant config files.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Ftoken-audit\u002Fskill.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7F33NAWXFPHW59CF52EAGGK","talk-stage6-revision","Produces revision sheets with quick navigation by act, a master concept-to-URL table, Q&A cheat-sheet with 6-10 anticipated questions, glossary, and external resources list. Use when preparing for a talk with Q&A, creating shareable reference material for attendees, or building a safety-net glossary for live delivery.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Ftalk-pipeline\u002Fstage-6-revision\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7F33G9V96HVZKAGZ84J4EBR","talk-stage5-script","Produces a complete 5-act pitch with speaker notes, a slide-by-slide specification, and a ready-to-paste Kimi prompt for AI slide generation. Requires validated angle and title from Stage 4. Use when you have a confirmed talk angle and need the full script, slide spec, and AI-generated presentation prompt.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Ftalk-pipeline\u002Fstage-5-script\u002FSKILL.md",[],[]]