agentleFS
Sign inStart free
malinskibeniaminmalinskibeniamin/skills/efficient-frontier/SKILL.md

efficient-frontier

Skill4 starsChanged 10 days agoMITView on GitHub

Apply eval-backed model routing and budget explicitly authorized agent waves without moving judgment away from the owner.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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
  1. Distinctive:

    Only for requested delegation, read Poteto.

    line 6
  2. Very specific:

    Keep chores inline on Opus.

    line 15
  3. Very specific:

    Before unrequested default changes run agent-evals/context-ablation/: vary one context group, fix tasks/scoring, prefer lower cost only …

    line 29

≈ “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.

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

Only for requested delegation, read Poteto.

Use tool choice.

config/model-routing.json owns routing; omit subjective prompt scores.

  1. Owner: Opus 5.5 xhigh for daily work, plans, code, UI.
  2. Sol xhigh reviews PRs via /codex; if unavailable, label a clean-context Opus xhigh pass and disclose missing different-family coverage.
  3. Opus owns UI, copy, API design (taste >= 8); if unavailable, report the UI lane blocked.
  4. Keep chores inline on Opus. Use Sol xhigh for user-selected Codex execution, computer use, or investigation.
  5. Route only Opus/Sol; never max. If neither is available, report the lane blocked. Owner preference overrides historical scores.
  6. The user explicitly authorizes a different-family pass; model preference is not spawning consent.
  7. ultra needs explicit delegation or /swarm. Pro mode, persisted reasoning, programmatic tools, explicit cache: API-only unless exposed.

Without delegation, keep lanes inline. Authorized briefs bound objective, inputs, exclusions, evidence, stop. One owner keeps architecture, priority, risk, synthesis and acceptance.

Capacity

Capacity: /stay-within-limits host meter, else unknown. Never infer from tokens/cost; remove routes, never lower quality.

Promotion

xhigh is owner-selected, not benchmark-promoted. Before unrequested default changes run agent-evals/context-ablation/: vary one context group, fix tasks/scoring, prefer lower cost only among quality-equivalent results. Record winner in routing config.

Packet and source: authorized delegation only.

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.

Check your setup, free