agentleFS
oktawianwybieralskioktawianwybieralski/coagent8/skills/coagent8-doctor/SKILL.md

coagent8-doctor

Skill2 starsChanged 11 days agoMITView on GitHub

Show which models, reasoning efforts and output prices each CoAgent8 backend accepts, or check backend health (installation, sign-in, quota) through the CoAgent8 doctor tool. Use when the user asks which model CoAgent8 can use, gives a price limit, asks why a backend fails, or wants CoAgent8 status.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is 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.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Do not edit CoAgent8 or client configuration files to change defaults or approval: the running server may read a different configuration …

    line 29

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

CoAgent8 doctor

  1. For models call doctor with scope: models (the default). It reads cached catalogs and lists, per backend, models, reasoning efforts, output prices, the day the price list added each model (not the vendor's release date), price freshness and each model's approval tag: ask: <rule>, deny or allow. Pass backend (codex, claude or agy) to narrow it and detail: full for the same report as JSON.
  2. For problems call doctor with scope: health. It checks installation, sign-in and quota and takes longer than the models view (backend readiness does not probe or verify workspace filesystem access permissions; on Windows, Codex reviews configure windows.sandbox="elevated").
  3. To apply a user's price limit or range (e.g. "X-Y" means output_price_below: Y), pass output_price_below to consult or review and leave model unset; the server, not the agent, picks the model (the qualifying default or the most recently released qualifying model). Do not pick a model from the list to work around it.
  4. A model tagged ask runs only after the user approves it in the form the server shows; tell the user its price and that the form will follow before you call it. You cannot approve it. A model tagged deny never runs: the user denied it, so do not call it. allow is the user's standing approval.

Do not edit CoAgent8 or client configuration files to change defaults or approval: the running server may read a different configuration file than the default path. For CLI installation, sign-in, registration or skill problems point the user to the VS Code commands CoAgent8: Manage Coding CLIs and CoAgent8: Manage Skills, or to npx -y coagent8@next status, repair and skills (coagent8 ... when installed globally).

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.