agentleFS
ThomasLangbroekThomasLangbroek/frugal/skills/models/SKILL.md

models

Skill37 starsChanged 4 months agoMITView on GitHub

Show or change which model each frugal agent runs on, per project. Use when the user wants to see the current tier-to-model mapping, move an agent to a different model (e.g. scout to sonnet), or reset overrides. Triggers on "frugal models", "change router models", "which model does scout use".

8 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use research.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Read each agent's default from the model: frontmatter line in <plugin-root>/agents/*.md (plugin root is two directories up from this …

    line 20
  2. Very specific:

    Read the "Model overrides" section of .claude/routing-overrides.md if it exists.

    line 23
  3. Very specific:

    Create or update the managed section in .claude/routing-overrides.md (create the file if missing, keep any unmanaged content above it …

    line 32
  4. Distinctive:

    Remove the managed section.

    line 54

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “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

Frugal model overrides

Manage the per-project model mapping for frugal's agents. Defaults live in each agent's frontmatter (agents/*.md under the plugin root); overrides live in the project's .claude/routing-overrides.md, which the routing policy reads first. Overrides work because the Agent tool accepts a model parameter per spawn - no plugin files are ever edited.

Valid agents: scout, extractor, mechanic, builder, sage. Valid models: haiku, sonnet, opus, fable.

No arguments: show the mapping

  1. Read each agent's default from the model: frontmatter line in <plugin-root>/agents/*.md (plugin root is two directories up from this skill's base directory).
  2. Read the "Model overrides" section of .claude/routing-overrides.md if it exists.
  3. Show one table: agent, default, override (or "-"), effective model. Nothing else.

Arguments like scout=sonnet builder=opus

  1. Validate every pair against the lists above. Invalid agent or model: reject with the valid options, change nothing.
  2. Create or update the managed section in .claude/routing-overrides.md (create the file if missing, keep any unmanaged content above it intact):

    ## Model overrides (managed by /frugal:models)
    
    | Agent | Model |
    |---|---|
    | scout | sonnet |
    
    When spawning a frugal agent listed above, pass its listed model as the
    Agent tool's `model` parameter.
  3. Merge with existing overrides: new pairs win, unmentioned pairs stay.
  4. Setting an agent to its default removes its row. Empty table: remove the whole section.
  5. Confirm with the resulting mapping table and apply it immediately to any spawns later in this session.

Argument reset

Remove the managed section. If the file is then empty, delete the file. Show the default mapping.

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.