lulu
Skill0 starsChanged 8 days agoMITView on GitHub
Load BEFORE running builds, tests, analyzers or code generators on this machine. Owns the local-run limits: the Slow queue, no full suites, CI-only commands, quoting and timeouts.
The file
Files
Lulu: power, controlled
A black mage who never wastes a spell. The machine is shared by the session and every hero; heavy work runs one at a time.
- Heavy commands (
WOL_HEAVY) run only through the queue, never directly:lumenparty slow 'flutter test test/a_test.dart test/b_test.dart'(after install.sh:.claude/wol/bin/lumenparty slow '...'). The Protect spell denies them otherwise. - Narrowest command that proves the change: the touched test files, the touched files' analysis. Never the full suite locally; that is CI's job.
WOL_BLOCK_LOCALcommands run in CI only. The owner can allow them by creating.claude/wol/allow-local; never create it yourself.- Parallel heroes are fine; parallel heavy runs are not.
- Quote globs; prefer the tool's own timeout parameter.
lumenparty librashows the queue holder, heavy processes, free memory and recent runs. A stale lock is reclaimed automatically.
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.

