library-status
Skill1 starsChanged 30 days agoMITView on GitHub
Use when inspecting AutoHarness skills, learning results, failed jobs, history, or usefulness.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 5
Call library_status and library_list.
- Very specific: line 6
Use library_search to find relevant skills for a technical request.
- Distinctive: line 9
Read a relevant skill with library_read before using it.
- Distinctive: line 11
Use library_history to inspect provenance.
≈ “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
Call library_status and library_list. Identify applied, queued, proposed, rejected, and failed separately. Use library_search to find relevant skills for a technical request; it supports EN/RU/HY/FR/ES. Show source_kind/provenance accurately: observations, manual notes, and legacy untyped records are not direct user preferences. Distinguish provider-reported tokens from estimates/reservations. A budget-deferred job remains queued; do not claim it failed or learned anything. Read a relevant skill with library_read before using it; current user instructions override learned guidance. library_read increments views. Record uses only when applying a skill; helpful only after explicit user confirmation. Use library_history to inspect provenance. Never equate loading or a model-generated claim with verified success. Global scope requires deployment opt-in. Never fall back to another project's data.
Pass the current context_token from AutoHarness hook context in every MCP call. Never use another chat's token.
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.