butler
Skill0 starsChanged 2 months agoMITView on GitHub
Track per-project Claude usage estimates and local GPU budgets, preview admission, atomically reserve capacity, and reconcile actual usage with a local dashboard.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- baojie/shiji-kbtheir own version, first seen Oct 8, 2026
- xiaogege6697/butler-skilltheir own version, first seen Jul 3, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- baojie/shiji-kb★ 3.4ksame name
- xiaogege6697/butler-skill★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use the bundled runtime for local project-budget custody.
- Very specific: line 16
Use session-log for an authorized run summary and artifact paths.
≈ “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
Butler
Use the bundled runtime for local project-budget custody. Read README.md for installation and references/accounting.md before GPU work.
Resolve the user's explicit BUTLER_ROOT and project. A fresh install has no accounts, projects, reservations or usage. Do not invent a budget or scan transcripts automatically. Configure limits only from the user's authority. Registration and policy changes write state.
For a budget check, use scripts/butler.py gate --project SLUG or gpu-gate: a preview does not reserve GPU capacity. When compute launch is separately authorized, use gpu-reserve with a stable idempotency key before launch; reconcile actual terminal usage afterwards. No command here launches compute, bills a provider, changes provider authentication, or deletes provider disks. A disk-release entry is evidence recording, not cleanup.
The local Claude weighted-token proxy is not actual Codex quota. Optional cached Claude utilization is dated provider evidence, not a fresh quota query. Report unavailable evidence as unavailable. Gate results are advisory unless the actual execution path obeys them. Missing GPU limits are not a cap; verify policy explicitly. Never clear limits through --unlimited without explicit budget-owner authorization.
Use session-log for an authorized run summary and artifact paths. Keep ledgers and transcripts out of the public package. Open the dashboard only on loopback. Remote SSH collection and local process inspection are optional opt-ins, never implicit task steps.
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.

