agentleFS
strikersamstrikersam/autonomous-ai-agency/.claude/skills/model-catalogue-update/SKILL.md

model-catalogue-update

Skill12 starsChanged 29 days agoMITView on GitHub

Add, change or retire a model id in the routing catalogue. Use whenever a task touches config/models.yaml, config/llm/models.yaml, packages/ai/brain_config.py PROVIDER_CANDIDATES or presets, or packages/ai/cost_tracker.py prices — including the daily "new models" automation.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never duplicate a key: Search the dict or YAML for the id before adding it.

    line 28
  2. Distinctive:

    Prove it: Run, and paste the summary line of:

    line 35

≈ “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

Model catalogue update

The catalogue decides what the agency routes to in production. A wrong id costs every call that lands on it, so the rules below are not style.

  1. Check the retired list first. RETIRED in tests/test_nvidia_default_model.py and the removed … / (404) / (410) comments in config/models.yaml name ids that failed live on this account. Do not re-add one. A vendor page saying the model exists is not evidence it answers here: #1695 (Nemotron 3.5 Lightning) and #1697 (Llama 3.3 Nemotron Super 49B) both re-added retired ids from vendor docs and went red.
  2. Never duplicate a key. Search the dict or YAML for the id before adding it; a duplicate silently overwrites the earlier entry (#1689).
  3. Unprobed means explicit-only. A new id gets priority: 99, stays out of PROVIDER_CANDIDATES and every preset, and its cost entry says it is an estimate until a probe (catalogue-probe.yml) has seen HTTP 200 with a real completion.
  4. Mirror both configs. config/models.yaml and brain_config.py must agree; test_yaml_presets_mirror_brain_config checks it.
  5. Prove it. Run, and paste the summary line of:

    pytest -q tests/test_one_model_catalogue.py tests/test_nvidia_default_model.py tests/test_model_router.py

The pre-PR gate (agent/pr_gate.py) runs these suites whenever model config changes, so an agent PR that breaks rule 1 or 2 does not open. This skill is the advisory half; the gate is the deterministic half.

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.