attic-sweep
Skill5 starsChanged 2 months agoMITView on GitHub
Save the state of the current session into the attic before context is lost: the current plan, open questions, in-progress work, and any finding not yet stashed. Use right before /compact or /clear, at the end of a session, or when the user says "save state", "wrap up", "before compact", "checkpoint", "context is getting long", "summarise what we've done so far", "where are we", or "recap the session". A request to recap session progress IS a sweep: give the recap and persist it in the same pass.
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-statsSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 27
Dedupe: Run the index and drop anything already covered.
≈ “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
Sweep the session into the attic
Goal: after this runs, a fresh session that reads only .attic/INDEX.md
could continue the work.
Pipeline:
- Collect. Review the conversation for anything not yet stashed: findings, decisions and why, the current plan and what is done, open questions, and in-progress state (files being edited, failing tests, commands to rerun).
- Dedupe. Run the index and drop anything already covered. Append to an existing item where there is genuinely new detail.
node "${CLAUDE_SKILL_DIR}/../attic/scripts/attic.js" index- Write. One stash per finding or decision, following
/attic-stash. Then one session item, usingtemplates/session.mdas the shape:
node "${CLAUDE_SKILL_DIR}/../attic/scripts/attic.js" stash \
--slug session-$(date +%F) --kind plan --title "Session $(date +%F)" \
--hook "<what this session is doing, one line>" --body-file <tmpfile>- Verify.
node "${CLAUDE_SKILL_DIR}/../attic/scripts/attic.js" validateFix anything it reports before finishing. 5. Report. List the handles written, one per line, then a single line: "Safe to /compact."
Copy commands, paths and errors verbatim. No secrets.
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.

