kit-health
Skill16 starsChanged 7 months agoMITView on GitHub
Confirms the Clankbrain install worked. Run this right after setup or anytime you suspect something is broken. Triggers on "kit health", "is the kit installed", "kit check", "did install work", "verify kit", "health check kit".
In this repository45 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/agents.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- actSkill
- security-checkSkill
- environment-checkSkill
- run-verificationSkill
- refactorSkill
- debug-session-archivedSkill
- generate-guardsSkill
- check-anthropicSkill
- code-reviewerSkill
- code-reviewSkill
- debug-sessionSkill
- end-sessionSkill
- evolve-checkSkill
- evolveSkill
- fix-bugSkill
- forgetSkill
- frontend-designSkill
- guardSkill
- learnSkill
- map-codebaseSkill
- modeSkill
- parallel-prototypesSkill
- planSkill
- powershell-safeSkill
- product-riskSkill
- progress-reportSkill
- prototype-hypothesisSkill
- recallSkill
- refactoring-uiSkill
- scan-codebaseSkill
- scan-conventionsSkill
- search-firstSkill
- search-memorySkill
- shadow-codeSkill
- skill-creatorSkill
- smart-resumeSkill
- start-sessionSkill
- strategic-compactSkill
- tourSkill
- ux-heuristicsSkill
- verification-loopSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Run after setup.py finishes, or anytime the user asks "did install work" / "is the kit healthy" / "kit check".
- Very specific: line 68
Read .claude/settings.json, count entries in hooks object across all hook types (PreToolUse, PostToolUse, Stop, PreCompact, etc.).
- Distinctive: line 72
Use ✓ for pass, ✗ for fail, with green/red mental colors via emoji or text formatting.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Skill: kit-health
Trigger
Run after setup.py finishes, or anytime the user asks "did install work" / "is the kit healthy" / "kit check".
What this skill does
Inspects the Clankbrain install, confirms each piece is in place, and reports a green/red status for each. Builds confidence that install succeeded — the most important first impression.
Steps
- Find the kit root. Either:
- Current working directory if
.claude/exists (shared memory root for both apps) - Or ask: "Where did you install Clankbrain? (path to project root)"
- Current working directory if
Check each piece. Report green/red for each.
== Clankbrain Health Check == Memory directory [check .claude/memory/ exists] Skills loaded [count .claude/skills/*/SKILL.md files] Hooks active [parse .claude/settings.json, count hooks] Starter lessons [check .claude/memory/lessons.md is non-empty] Memory index [check .claude/memory/MEMORY.md exists] Settings file [check .claude/settings.json valid JSON] Tools directory [check tools/ exists with memory.py] Sync configured [check sync.py exists, optional check for git remote] Overall: [PASS / FAIL with X issues]- For each FAIL, give a specific fix:
- "Memory directory missing → Run:
python setup.py" - "No skills loaded → Re-run:
python setup.py" - "Settings.json invalid → Restore from
.claude/settings.json.bak" - "No starter lessons → That's okay, but you'll have nothing to demo. Run
tourto see the kit work with starter content."
- "Memory directory missing → Run:
- End with the next step:
✓ Install verified. Next: Type "tour" for a 5-minute walkthrough, or "Start Session" to begin working.
How to count skills (Bash)
ls .claude/skills/*/SKILL.md 2>/dev/null | wc -lHow to verify settings.json (Bash)
python -c "import json; json.load(open('.claude/settings.json'))" 2>&1Exit 0 = valid. Non-zero = invalid.
How to count hooks
Read .claude/settings.json, count entries in hooks object across all hook types (PreToolUse, PostToolUse, Stop, PreCompact, etc.).
Output format — make it visual
Use ✓ for pass, ✗ for fail, with green/red mental colors via emoji or text formatting.
== Clankbrain Health Check ==
✓ Memory directory .claude/memory/ (12 files)
✓ Skills loaded 32 of 32
✓ Hooks active 8 hooks across 5 events
✓ Starter lessons 3 entries
✓ Memory index MEMORY.md (118 lines)
✓ Settings file valid JSON
✓ Tools directory memory.py present
○ Sync configured skipped (optional — run `python sync.py setup` to enable)
Overall: PASS — 7/7 required checks green
Optional: 1 skipped (sync — only if you want GitHub backup)
Next: Type "tour" for a 5-minute walkthrough, or "Start Session" to begin.When something fails
Be specific. Don't just say "broken." Tell the user:
- What failed
- Why it matters
- The exact command to fix it
Example:
✗ Skills loaded: 0 of 32 expected
Why this matters: All the magic is in the skills. Without them, the kit is just a folder.
Fix: Run `python setup.py --force` to re-install skills.
If that fails, check that you cloned the full repo (not a sparse checkout).Why this skill exists
A new user's first 60 seconds with the kit determine whether they keep going. This matters even more now that people may open the same repo in Claude or Codex. Without this skill, install is silent — they don't know if it worked. With this skill, they get instant confirmation + a clear next step.
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.

