agentleFS
NishikantaRayNishikantaRay/Attic/skills/attic-stats/SKILL.md

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.

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
  1. Very specific:

    If it says NOT EARNING ITS KEEP, say so first and plainly: Do not soften it or bury it under what the attic contains.

    line 25
  2. Very specific:

    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.

    line 38

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Attic stats

node "${CLAUDE_SKILL_DIR}/../../scripts/attic-stats.js"

Print what it reports. Then follow these rules when discussing it:

  1. Lead with the verdict, not the contents. The user is asking whether this is worth keeping on. The What this means block answers that; the item counts do not.
  2. 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.
  3. 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.
  4. 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.
  5. 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.
  6. 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.

Nothing leaves the machine: the script makes no network calls and sends no telemetry. Say so if the user asks.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.