agentleFS
XakkiXakki/ai-agents-skills/skills/agent-model-find/SKILL.md

agent-model-find

Skill6 starsChanged 3 months agoMITView on GitHub

Resolve optional model-tier settings through the active agent runtime. Use when a task needs model selection or a delegation policy is configured. RU: выбор модели, уровни моделей.

The file

Files
SKILL.md

Model tiers

Use when a task explicitly needs model selection or the user has configured a delegation policy. The optional AI_MODEL_CHEAP, AI_MODEL_STANDARD and AI_MODEL_JUDGMENT values are runtime-specific selectors, not universal model names. Read them from the agent's supported environment or configuration interface, and verify that each selector and any model override is supported and authorized in the active runtime.

Keep the inherited model when no applicable override is requested or supported. An unset tier is unconfigured, not permission to invent a selector or substitute another provider's model. Profiles, role names and model selectors are distinct; preserve any required named profile and follow its actual capabilities.

For Claude-specific configuration and its shipped aliases, see the conditional reference. Other runtimes must use their own documented configuration and discovery interfaces. A session-start hook may report tier settings as hints; it does not override the user's model choice or require a model argument on every delegation.

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.