attic-stats
Skill5 starsChanged 2 months agoMITView on GitHub
Report what the attic costs and what it holds, measured from local session transcripts. Use when the user asks "is the attic worth it", "attic stats", "how many tokens is this saving", "how big is the attic", or questions the plugin's value.
In this repository12 other files it gives its agents.
- attic-doctorSkill
- attic-failSkill
- attic-gitSkill
- attic-helpSkill
- attic-indexSkill
- attic-pinSkill
- attic-pruneSkill
- attic-recallSkill
- attic-reviewSkill
- atticSkill
- attic-stashSkill
- attic-sweepSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 25
If it says NOT EARNING ITS KEEP, say so first and plainly: Do not soften it or bury it under what the attic contains.
- Very specific: line 38
If many items are past the injection budget, suggest /attic-pin for what must always be present and /attic-prune for what has gone stale.
≈ “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
Attic stats
node "${CLAUDE_SKILL_DIR}/../../scripts/attic-stats.js"Print what it reports. Then follow these rules when discussing it:
- Lead with the verdict, not the contents. The user is asking whether
this is worth keeping on. The
What this meansblock answers that; the item counts do not. - If it says NOT EARNING ITS KEEP, say so first and plainly. Do not
soften it or bury it under what the attic contains. Suggest
/attic off, or ask what they were expecting to recall that they never did. - Never invent a savings percentage. The script deliberately produces none, because token spend depends on the task. Quote what is measured: index cost, citations, repeat file reads.
- Two numbers carry the answer. Cited in replies is how often the model answered from the attic instead of re-reading. Repeat file reads is the share of reads that an earlier session had already done — the thing the plugin exists to reduce, so lower is better.
- Early sessions look bad and that is expected. The session that writes pays; later sessions collect. If there is one session and no citations, say it is too early rather than implying failure.
- If many items are past the injection budget, suggest
/attic-pinfor what must always be present and/attic-prunefor what has gone stale.
Nothing leaves the machine: the script makes no network calls and sends no telemetry. Say so if the user asks.
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.

