memory-audit
Skill0 starsChanged 35 days agoMITView on GitHub
Audits a project's markdown memory (AGENTS.md, docs/, knowledge/, sources/, tasks/, memory/, SCRATCHPAD.md, HANDOFF.md) for size budgets, stale or contradictory entries, broken links, index drift, orphan files, missing frontmatter, unsafe content, and always-on token cost. Reports findings and proposes fixes. Use when asked to check, clean up, or review agent memory, or when AGENTS.md has grown large.
14 other projects use a version of this.
Adopted by
Most recently taken up by
- nightscout/AndroidAPStheir own version, first seen Nov 1, 2026
- shakhruz/mila-coretheir own version, first seen Nov 1, 2026
- AcKeskin/contexturetheir own version, first seen Nov 1, 2026
- qwwiwi/agentos-skills-publictheir own version, first seen Nov 1, 2026
- adamlinscott/claude-skillstheir own version, first seen Oct 30, 2026
- AdityaRon/claude-code-harnesstheir own version, first seen Oct 29, 2026
Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- FastLED/FastLED★ 7.5ksame name
- nightscout/AndroidAPS★ 1.2ksame name
- AdityaRon/claude-code-harness★ 14same name
- mfang0126/openclaw-skills★ 4same name
- qwwiwi/agentos-skills-public★ 4same name
- adamlinscott/claude-skills★ 3same name
- shakhruz/mila-core★ 3same name
- AcKeskin/contexture★ 2same name
- andreijirohdev-labs/gen-ai-labs★ 1same name
- brenbuilds1/skills★ 1same name
4 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 repository2 other files it gives its agents.
- initialize-agentic-memorySkill
- memory-reflectSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 16
Run node <this-skill-dir>/scripts/audit.mjs --json from the project root (or pass --root <dir>).
- Distinctive: line 19
After approved fixes, re-run the audit and report what changed.
- Distinctive: line 35
Check ids and fixes: references/checks.md
“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Memory audit
Requirements
Requires a local filesystem. If you cannot list and edit the project, stop and say so.
Procedure
- Run
node <this-skill-dir>/scripts/audit.mjs --jsonfrom the project root (or pass--root <dir>). If Node is unavailable, do the checks manually from references/checks.md. - Report findings grouped by severity: error, warn, info.
- Propose fixes as a table: file, check id, problem, proposed change. Apply nothing without confirmation. Never delete content. Archive by setting
status: archivedor moving todocs/archive/YYYY-MM-DD/. - After approved fixes, re-run the audit and report what changed.
Useful flags
| Flag | Meaning |
--check | CI mode: exit non-zero on errors or stale generated blocks; write nothing |
--write-index | Regenerate text between index markers only |
--write-toc | Regenerate TOC blocks |
--report-tokens | Print always-on cost estimate |
--include-archived | Include archived files in index generation |
Exit codes: 0 clean, 1 warnings only, 2 errors.
References
- Check ids and fixes: references/checks.md
- Layout and practices copies (when synced): references/layout.md, references/practices.md
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.