health
Skill2 starsChanged 9 months agoMITView on GitHub
Use when assessing overall project quality, onboarding onto a new codebase, or before major refactoring to establish a baseline.
55 other projects use a version of this.
Adopted by
Most recently taken up by
- veraetogrex-portfolio/solo-sddtheir own version, first seen Nov 15, 2026
- 5uck1ess/devkittheir own version, first seen Nov 15, 2026
- KadirHarmanc/nazar-skilltheir own version, first seen Nov 8, 2026
- timurgaleev/vibestacktheir own version, first seen Nov 8, 2026
- buildomator/buildomatortheir own version, first seen Nov 4, 2026
- trungtm78/ClaudeSkillstheir own version, first seen Oct 25, 2026
Used with
Projects with it also use plan-tune, ios-clean and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
ShreyRaviSkillplan-tune
Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). Review which AskUserQuestion prompts fire across gstack skills, set per-question preferences (never-ask / always-ask / ask-only-for-one-way), inspect the dual-track profile (what you declared vs what your behavior suggests), and enable/disable question tuning. Conversational interface — no CLI syntax required.
Also in 9 projects that use this
Saqlain-811Skillios-clean
Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)
Also in 5 projects that use this
Saqlain-811Skillios-fix
Autonomous iOS bug fixer. (gstack)
Also in 5 projects that use this
seek888Skillpair-agent
Pair a remote AI agent with your browser. One command generates a setup key and prints instructions the other agent can follow to connect. Works with OpenClaw, Hermes, Codex, Cursor, or any agent that can make HTTP requests. The remote agent gets its own tab with scoped access (read+write by default, admin on request). Use when asked to "pair agent", "connect agent", "share browser", "remote browser", "let another agent use my browser", or "give browser access". (gstack) Voice triggers (speech-to-text aliases): "pair agent", "connect agent", "share my browser", "remote browser access".
Also in 11 projects that use this
ShreyRaviSkilllanding-report
Read-only queue dashboard for workspace-aware ship. Shows which VERSION slots are currently claimed by open PRs, which sibling Conductor workspaces have WIP work likely to ship soon, and what slot /ship would pick next. No mutations — just a snapshot. Use when asked to "landing report", "what's in the queue", "show me open PRs", or "which version do I claim next". (gstack)
Also in 8 projects that use this
timurgaleevSkilldocument-generate
Generate missing docs for a feature, module or project as tutorials, how-tos, reference and explanation.
Also in 7 projects that use this
- +1 more from Saqlain-811
- +2 more from ShreyRavi
Other versions55 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 55
- garrytan/gstack★ 142ksame name
- tw93/Waza★ 7.6ksame name
- tw93/claude-health★ 7.5ksame name
- agenticnotetaking/arscontexta★ 3.5ksame name
- kellyvv/PhoneClaw★ 1.3ksame name
- ninehills/skills★ 280same name
- kv0906/pm-kit★ 138same name
- buildomator/buildomator★ 102same name
- priyanshuchaudhary53/naval-skills★ 19same name
- JaimeGBA/Ion★ 9same name
45 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository22 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- auditSkill
- brainstormSkill
- checkpointSkill
- codereviewSkill
- commitSkill
- debugSkill
- estimateSkill
- finishSkill
- learnSkill
- lintSkill
- migrate-architectureSkill
- migrate-frameworkSkill
- onboardSkill
- planSkill
- recallSkill
- rememberSkill
- tddSkill
- tutorialSkill
- verifySkill
- worktreeSkill
- write-skillSkill
The file
Files
/health - Project Health Score
Generate a comprehensive health score for your project or a specific module.
Scope: $ARGUMENTS (default: full project)
Scoring Categories
| Category | Weight | What it measures |
| Architecture | 25% | ARCHITECTURE.md conformance |
| Tests | 20% | Coverage, test presence |
| Security | 20% | OWASP compliance, secrets |
| Performance | 15% | Bundle size, caching |
| Maintainability | 20% | Code complexity, docs |
Workflow
Step 1: Gather Metrics
# File counts
find src -name "*.ts" -o -name "*.tsx" | wc -l
find src -name "*.test.ts" -o -name "*.spec.ts" | wc -l
# TypeScript check
npx tsc --noEmit 2>&1 | grep -c "error"
# Test coverage (if available)
npm test -- --coverage --json 2>/dev/null
# Bundle analysis
npm run build 2>&1 | grep -E "size|chunk"
# Security checks
grep -rn "dangerouslySetInnerHTML\|v-html\|eval(" src/ 2>/dev/null | wc -l
grep -rn "password\|secret\|token" src/ --include="*.ts" 2>/dev/null | wc -lStep 2: Calculate Scores
Architecture Score (25 points)
+5 ARCHITECTURE.md exists
+5 Module structure follows patterns
+5 No cross-module imports
+5 Correct layer usage (service→adapter→hook→component)
+5 Naming conventions followedTest Score (20 points)
+5 Test files exist
+5 Coverage > 50%
+5 Coverage > 70%
+5 Coverage > 80%
+5 All tests passing
-2 Each failing testSecurity Score (20 points)
+5 No hardcoded secrets
+5 No dangerous HTML methods
+5 Input validation present
+5 Auth implementation exists
+5 Secure headers configured
-5 Each critical vulnerabilityPerformance Score (15 points)
+5 Lazy loading implemented
+5 Query caching present (staleTime)
+5 Bundle < 500KB
+5 No N+1 queries detected
-3 Each performance warningMaintainability Score (20 points)
+5 README.md exists
+5 Files < 200 lines (average)
+5 Low cyclomatic complexity
+5 TypeScript strict mode
+5 No 'any' types
-2 Each 'any' type foundStep 3: Generate Report
Output Format
═══════════════════════════════════════════════════════════════
PROJECT HEALTH REPORT
═══════════════════════════════════════════════════════════════
██████████████████████████████████████░░░░░░░░ 78/100
═══════════════════════════════════════════════════════════════
CATEGORY BREAKDOWN
───────────────────────────────────────────────────────────────
Architecture ████████████████████░░░░░ 20/25
✓ ARCHITECTURE.md exists
✓ Module structure correct
✗ Cross-module imports found (3 violations)
✓ Layer usage correct
✓ Naming conventions followed
Tests ████████████████░░░░░░░░░ 16/20
✓ Test files exist (42 specs)
✓ Coverage: 72%
✗ Coverage < 80% target
✓ All tests passing
Security █████████████████████████ 20/20
✓ No hardcoded secrets
✓ No dangerous HTML methods
✓ Input validation present
✓ Auth implementation exists
✓ Secure headers configured
Performance █████████████░░░░░░░░░░░░ 10/15
✓ Lazy loading implemented
✗ Missing staleTime in 5 queries
✓ Bundle: 320KB
✗ Potential N+1 in user.service.ts
Maintainability ████████████░░░░░░░░░░░░░ 12/20
✓ README.md exists
✗ 3 files > 200 lines
✓ Low complexity
✓ TypeScript strict mode
✗ 12 'any' types found
═══════════════════════════════════════════════════════════════
TOP ISSUES TO FIX (by impact)
───────────────────────────────────────────────────────────────
1. 🔴 [Architecture] Cross-module imports
Files: src/modules/orders/components/UserCard.tsx
Fix: Move shared components to src/shared/
2. 🟡 [Performance] Missing staleTime in queries
Files: src/modules/*/hooks/use*.ts (5 files)
Fix: Add staleTime to all useQuery calls
3. 🟡 [Maintainability] Files exceeding 200 lines
Files: src/modules/auth/components/LoginForm.tsx (284 lines)
Fix: Split into smaller components
4. 🟡 [Tests] Coverage below 80%
Current: 72%
Fix: Add tests for uncovered modules
═══════════════════════════════════════════════════════════════
TREND (if previous scans exist)
───────────────────────────────────────────────────────────────
Previous: 71/100 (2024-01-10)
Current: 78/100 (2024-01-20)
Change: +7 points ↑
═══════════════════════════════════════════════════════════════
RECOMMENDATIONS
───────────────────────────────────────────────────────────────
@reviewer - Run /review-fix-violations to auto-fix
@tester - Add tests for auth module
@builder - Refactor LoginForm.tsx
═══════════════════════════════════════════════════════════════
Generated: 2024-01-20 14:30 | Scan time: 12s
═══════════════════════════════════════════════════════════════Score Interpretation
| Score | Grade | Status |
| 90-100 | A | Excellent |
| 80-89 | B | Good |
| 70-79 | C | Acceptable |
| 60-69 | D | Needs Work |
| 0-59 | F | Critical |
Save History
Save scan to .claude/health-history.json:
{
"scans": [
{
"date": "2024-01-20T14:30:00Z",
"score": 78,
"categories": {
"architecture": 20,
"tests": 16,
"security": 20,
"performance": 10,
"maintainability": 12
}
}
]
}Quick Mode
For fast feedback (< 5 seconds):
/health quickOnly checks:
- TypeScript errors
- Test status
- File count
Anti-Rationalization
| Excuse | Reality |
| "The score doesn't matter, the app works" | Working today doesn't mean maintainable tomorrow. The score measures long-term health. |
| "We'll improve the score after the deadline" | After the deadline there's another deadline. Measure now, fix incrementally. |
| "80% coverage is overkill" | 80% is the baseline. Below that, regressions hide in untested code. |
| "Security checks are paranoid" | One vulnerability costs more than 100 health scans. Paranoia is appropriate. |
Rules
- Be objective - Numbers, not opinions
- Prioritize issues - Most impactful first
- Show trends - Compare to previous scans
- Actionable - Suggest specific fixes
- Save history - Track progress over time
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

