cqs-verify
Skill18 starsChanged 5 months agoMITView on GitHub
Verify all cqs features work. Run on session start and after compaction.
In this repository22 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- archeoSkill
- auditSkill
- before-editSkill
- boundary-probeSkill
- check-my-workSkill
- cqs-batchSkill
- cqs-bootstrapSkill
- cqs-planSkill
- cqsSkill
- docs-reviewSkill
- groom-notesSkill
- idleSkill
- investigateSkill
- landSkill
- migrateSkill
- prSkill
- recall-gateSkill
- reindexSkill
- releaseSkill
- troubleshootSkill
- update-tearsSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Run each command, check for errors.
- Distinctive: line 64
Don't skip commands — the point is to exercise the full tool
≈ “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
Verify cqs
Quick functional test of all cqs command categories. Exercises the full tool to build grounded understanding of what it does — not just what docs say.
When to run
- Session start (after reading tears)
- After context compaction
- After any release or binary update
Process
Run each command, check for errors. Report pass/fail summary.
# Redirect stderr to suppress tracing noise in JSON output
echo "=== cqs verify ===" && echo "Version: $(cqs --version 2>&1)"
# 1. Search (semantic)
echo "1. search:" && cqs "error handling" --json -n 3 2>/dev/null | python3 -c "import sys,json; r=json.load(sys.stdin); print(f' PASS ({len(r[\"results\"])} results)')" 2>&1 || echo " FAIL"
# 2. Name lookup
echo "2. name-only:" && cqs "Store" --name-only --json -n 3 2>/dev/null | python3 -c "import sys,json; r=json.load(sys.stdin); print(f' PASS ({len(r[\"results\"])} results)')" 2>&1 || echo " FAIL"
# 3. Read
echo "3. read:" && cqs read src/lib.rs 2>/dev/null | head -1 | grep -q . && echo " PASS" || echo " FAIL"
# 4. Callers
echo "4. callers:" && cqs callers search_filtered --json 2>/dev/null | python3 -c "import sys,json; r=json.load(sys.stdin); print(f' PASS ({r[\"count\"]} callers)')" 2>&1 || echo " FAIL"
# 5. Callees
echo "5. callees:" && cqs callees search_filtered --json 2>/dev/null | python3 -c "import sys,json; r=json.load(sys.stdin); print(f' PASS ({r[\"count\"]} callees)')" 2>&1 || echo " FAIL"
# 6. Explain
echo "6. explain:" && cqs explain search_filtered --json 2>/dev/null | python3 -c "import sys,json; r=json.load(sys.stdin); print(f' PASS (callers:{len(r.get(\"callers\",[]))}, callees:{len(r.get(\"callees\",[]))})')" 2>&1 || echo " FAIL"
# 7. Impact
echo "7. impact:" && cqs impact search_filtered --json 2>/dev/null | python3 -c "import sys,json; r=json.load(sys.stdin); print(f' PASS (callers:{len(r.get(\"callers\",[]))}, tests:{len(r.get(\"tests\",[]))})')" 2>&1 || echo " FAIL"
# 8. Stats
echo "8. stats:" && cqs stats --json 2>/dev/null | python3 -c "import sys,json; r=json.load(sys.stdin); print(f' PASS ({r[\"total_chunks\"]} chunks)')" 2>&1 || echo " FAIL"
# 9. Health
echo "9. health:" && cqs health --json 2>/dev/null | python3 -c "import sys,json; print(' PASS')" 2>&1 || echo " FAIL"
# 10. Doctor
echo "10. doctor:" && cqs doctor 2>/dev/null | grep -c "✓" | xargs -I{} echo " PASS ({} checks)"
# 11. Notes
echo "11. notes:" && cqs notes list --json 2>/dev/null | python3 -c "import sys,json; r=json.load(sys.stdin); print(f' PASS ({r[\"count\"]} notes)')" 2>&1 || echo " FAIL"
# 12. Dead code
echo "12. dead:" && cqs dead --json 2>/dev/null | python3 -c "import sys,json; print(' PASS')" 2>&1 || echo " FAIL"Rules
- Any FAIL = investigate before starting work
- Don't skip commands — the point is to exercise the full tool
- Report the summary to the user: "cqs verify: 12/12 pass, N chunks, N notes"
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.

