instructions
Skill8 starsChanged 3 days agoMITView on GitHub
Audit AGENTS.md/CLAUDE.md for rot with verify-references/verify-commands, or capture a session's discovered commands and gotchas — append-only diffs, applied only with approval.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- yuri-xyz/skillstheir own version, first seen Nov 8, 2026
- Firzus/agent-skillstheir own version, first seen Nov 1, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- Firzus/agent-skills★ 4same name
- yuri-xyz/skills★ 2same name
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 repository34 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- batch-fixSkill
- brainstormingSkill
- code-review-and-qualitySkill
- code-simplificationSkill
- context-engineeringSkill
- fixSkill
- handoffSkill
- implementSkill
- incremental-implementationSkill
- lessonsSkill
- mtk-doctorSkill
- mtk-setupSkill
- mtkSkill
- planning-and-task-breakdownSkill
- pre-commit-reviewSkill
- prior-work-checkSkill
- promote-lessonSkill
- repo-healthSkill
- research-contextSkill
- security-and-hardeningSkill
- setup-auditSkill
- setup-bootstrapSkill
- setup-refreshSkill
- spec-drift-detectionSkill
- spec-driven-developmentSkill
- subagent-implementationSkill
- tech-stack-dotnetSkill
- tech-stack-pythonSkill
- tech-stack-typescriptSkill
- verification-before-completionSkill
- workflow-artifactsSkill
- writing-skillsSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
audit: every 4–8 weeks, after a large refactor, or when sessions hit broken commands or dead paths ("AGENTS.md feels off").
- Very specific: line 46
Shim integrity: When CLAUDE.md is a shim, confirm @AGENTS.md is present and bare (inside a code fence or backticks it is inert).
- Very specific: line 49
Apply: only the approved subset as one Edit per change.
- Very specific: line 58
Apply: only the approved subset with Edit, appended into the relevant section, never restructuring.
≈ “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
Instructions
Overview
Two modes over the project constitution, both append-only and approval-gated: audit re-grades what is there against the codebase and fixes rot; capture adds what this session learned that the constitution was missing.
When To Use
- audit: every 4–8 weeks, after a large refactor, or when sessions hit broken commands or dead paths ("AGENTS.md feels off").
- capture: at the end of a session that discovered a command, gotcha, env quirk or non-obvious pattern ("save what we learned", "remember this for next time").
When NOT To Use
- First-time setup →
/mtk-setup. Refreshingarchitecture-principles.md→/mtk-setup --audit. - An engineer correction →
lessons capture(a lesson, not a constitution fact). Session state to resume →handoff. - Audit right after a clean audit, or capture mid-task — both manufacture churn.
Workflow
Both modes
- Resolve the target first. The constitution is
AGENTS.mdwhen it exists, carries noAuto-generated by MTKmarker in its first 10 lines, andCLAUDE.mdis absent or a shim (a bare@AGENTS.mdline); otherwiseCLAUDE.md(legacy repo).bash scripts/resolve-constitution.shanswers the same question. No constitution → stop and point to/mtk-setup. Never migrate legacy → inverted as a side effect; that is/mtk-setup's regen-diff job. - Both files are protected (S1.5):
Editwith explicit old/new strings, neverWrite, even when the engineer asks for a rewrite.
Audit mode
- Mechanical currency checks — run, do not eyeball.
Extract the constitution's build/test/lint/format commands asCONST="$(bash scripts/resolve-constitution.sh)" bash scripts/verify-references.sh "$CONST" .claude/rules/*.md # exit 3 = STALE lines bash scripts/check-instruction-load.sh # exit 1 = a file a harness truncates, shadows or ignores; 2/missing = report "not checked"name<TAB>commandlines and run them throughbash scripts/verify-commands.sh --timeout 120. Never pass deploy, migrate, publish, push or anything that writes outside the tree — list those as unverified instead. Also runbash scripts/resolve-tech-stack.sh "$PWD": a constitution naming a different stack, or only the root's stack in a polyglot repo with per-subtree pins, is a currency finding. - Shim integrity. When
CLAUDE.mdis a shim, confirm@AGENTS.mdis present and bare (inside a code fence or backticks it is inert). A shim has no## Critical Rulesby design — not rot. Nested package files get a full pass only when they carry package-local content. - Judge what scripts cannot: architecture clarity, captured gotchas, conciseness, and vague rules ("write good tests") that need a concrete replacement. A line that is true but belongs elsewhere gets Move →
<named owner>(README, a rule file, a skill, the spec); the test: would a newcomer act differently because of this line here? No numeric grade — name the line and the reason. - Report, then stop. List every STALE path and failed command with its line, the judgement findings, and proposed changes. A clean file is reported as clean; never invent issues. Ask: "Approve these changes? (yes / partial / no)"
- Apply only the approved subset as one
Editper change. Removals need per-line approval; "approve all" does not cover deletions. Then re-run step 1 on the edited file and confirm the line count moved less than 10%.
Capture mode
- Reflect. Which commands, gotchas, env/config quirks or patterns, had they been in the constitution at the start, would have saved time? None → say "nothing to capture" and stop.
- Destination. Project fact → the resolved constitution (nearest package file in a monorepo when the fact is local to one package). Harness-only quirk → that shim's own short section, rarely. First-person preference or machine path →
CLAUDE.local.md(gitignored; check.gitignorebefore creating it). When in doubt it is a constitution fact, not a shim one. - Dedupe.
grep -in "<keyword>" AGENTS.md CLAUDE.md CLAUDE.local.md tasks/lessons.md. Already documented → update the line only if it is now wrong. - Draft one line per concept,
`<command or pattern>` — <why>, in the file's existing style. Budget:AGENTS.md60–80 lines, hard cap 120; aCLAUDE.mdshim 20. Over budget → move detail to.claude/rules/or drop the weakest candidate. The proposal must also passbash scripts/growth-gate.sh <target> <proposed>. - Propose, then stop. Each addition as a diff with its destination and a one-line why. Ask: "Apply these? (yes / partial / no)"
- Apply only the approved subset with
Edit, appended into the relevant section, never restructuring.
Verification
- Target resolved (or
/mtk-setupredirect); noWriteonAGENTS.md/CLAUDE.md - Audit:
verify-references.sh,verify-commands.shandcheck-instruction-load.shoutput cited, or "none found" stated - Every finding or addition names a line and a reason; no edits before approval; partial approval applied exactly
- Capture: duplicates grep-checked; growth gate passed;
AGENTS.md≤ 120 lines and the shim ≤ 20 after edits - Personal items went to
CLAUDE.local.md, not the committed file
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.

