post-cold-start-verification
Skill3 starsChanged 4 months agoApache-2.0View on GitHub
Audit every ai/ file for gaps, stale placeholders, and inconsistencies after cold-start. Produces a prioritized findings report.
In this repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/add-feature.mdcCursor rule
- .cursor/rules/adversarial-audit.mdcCursor rule
- .cursor/rules/ai-knowledge-layer.mdcCursor rule
- .cursor/rules/check-drift.mdcCursor rule
- .cursor/rules/cold-start.mdcCursor rule
- .cursor/rules/create-feature-catalog.mdcCursor rule
- .cursor/rules/fix-bug.mdcCursor rule
- .cursor/rules/perform-feature-add-simulation.mdcCursor rule
- .cursor/rules/post-cold-start-verification.mdcCursor rule
- .cursor/rules/review-agent-config.mdcCursor rule
- .cursor/rules/review-change.mdcCursor rule
- .cursor/rules/verify-ai-readiness.mdcCursor rule
- add-featureSkill
- cold-startSkill
- deep-testSkill
- fix-bugSkill
- review-changeSkill
- add-featureSkill
- adversarial-auditSkill
- check-docsSkill
- check-driftSkill
- cold-startSkill
- create-feature-catalogSkill
- fix-bugSkill
- implement-specSkill
- perform-feature-add-simulationSkill
- review-agent-configSkill
- review-changeSkill
- verify-ai-readinessSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
If ai/analysis/audit-reports/VERIFICATION_MANIFEST.json exists, read its summary and the non-confirmed claims first: path-existence …
- Very specific: line 23
Internal consistency: every path mentioned in ai/guide/* exists on disk (covered by the manifest when present — see Step 0).
- Very specific: line 33
Write ai/analysis/audit-reports/<YYYY-MM-DD>-post-cold-start.md: findings grouped P1 (agent-blocking) / P2 (misleading) / P3 (cosmetic), …
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
<!-- Copyright (c) 2026 Kunal Suri (CEA LIST). All rights reserved. -->Audit the AI knowledge layer. Read-only with one exception: you may write ONE report.
Step 0 — use the mechanical verifier's output, don't redo its job
If ai/analysis/audit-reports/VERIFICATION_MANIFEST.json exists, read its summary
and the non-confirmed claims first: path-existence checking is already done
deterministically by the kit's verify command (run from the kit checkout:
node install.mjs verify <repo> — no LLM
involved, so its statuses are facts). Spend your pass on what a script cannot
judge (checks 1, 3, 4 below, and the semantic half of check 2). If the manifest
is absent or older than the docs it covers, recommend regenerating it in your
report instead of re-deriving path checks by hand.
Checks
- Placeholders: find every
<fill in>,?Stability, and{{...}}leftover acrossai/and the entry files (CLAUDE.md, AGENTS.md). - Internal consistency: every path mentioned in
ai/guide/*exists on disk (covered by the manifest when present — see Step 0); MODULE_MAP rows correspond to real directories; FEATURE_MAP entries point at real files; diagrams name real modules. - Profile consistency: build/test commands in CLAUDE.md/AGENTS.md match
ai/repo-profile.json; flag divergence (don't silently fix). - Provenance hygiene: no
[verified]tag lacking a date; nothing you can tell was agent-written carrying[verified].
Output
Write ai/analysis/audit-reports/<YYYY-MM-DD>-post-cold-start.md: findings grouped
P1 (agent-blocking) / P2 (misleading) / P3 (cosmetic), each with location and a
one-line suggested fix. Tag the report itself [inferred]. Do not modify the files
you are auditing.
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.

