cleanup-flame-chase
Skill3 starsChanged 18 days agoApache-2.0View on GitHub
flame-chase plus a cleaner working between the two chasers. Every few turns it distills the workspace, writes a short NEXT.md, and squashes the epoch into one commit (old history kept in a tag). Run with /baton:cleanup-flame-chase "<task>".
In this repository17 other files it gives its agents.
- author-flowSkill
- cleanup-ralphSkill
- continue-loopSkill
- fixed-interruptSkill
- flame-chaseSkill
- flowsSkill
- gen-ideaSkill
- gen-planSkill
- goalSkill
- parallel-chase-prSkill
- parallel-chaseSkill
- protocolSkill
- ralph-loopSkill
- recursive-lean-proverSkill
- rlarSkill
- rlcrSkill
- stateful-ralphSkill
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 15
Add one line to the end of each chaser's turn prompt: If NEXT.md exists at the repository root, read it first: a cleaner wrote it after …
- Very specific: line 16
Every --cleanup-turns work turns, run the protocol's Cleaning steps.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
cleanup-flame-chase
Arguments: $ARGUMENTS
Load the run protocol first (Skill tool → baton:protocol; if that fails, Read ${CLAUDE_PLUGIN_ROOT}/skills/protocol/SKILL.md) and follow it, including its Cleaning section. Then Read ${CLAUDE_SKILL_DIR}/../flame-chase/SKILL.md and run exactly that flow (roles, turn prompt, stop rules), with these changes:
- The flow name in headers and commit messages is
cleanup-flame-chase. - Add one line to the end of each chaser's turn prompt:
If NEXT.md exists at the repository root, read it first: a cleaner wrote it after distilling the workspace. - Every
--cleanup-turnswork turns, run the protocol's Cleaning steps. The cleaner is not a chaser and doesn't change whose turn is next. - Also stop after 3 consecutive
emptywork turns.
Why
In a long chase, each chaser leaves traces of its own approach. The cleaner sits between them, keeps the tree to the work that matters, and leaves a short NEXT.md, so each fresh chaser spends its turn on the task instead of on archaeology. NEXT.md is part of the tree, so the "workspace is the only handoff" rule still holds.
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.

