Maestro token efficiency
Skill mbanderas/maestro/.agents/skills/maestro-token-efficiency
Use when improving Maestro token efficiency, Codex fit, benchmark context hygiene, or agent orientation without weakening verification quality.From its SKILL.md
npx -y skills add mbanderas/maestro --skill maestro-token-efficiencyAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.1 KB, as published. Nobody here has run it
Maestro Token Efficiency
Use this skill for Maestro repo changes that affect agent context, instruction loading, benchmark search hygiene, or Codex behavior.
- Read
docs/agent-map.mdfirst for navigation. - Prefer benchmark summary files over raw streams unless doing
forensic scoring. Use
rg --no-ignorefor raw stream audits. - Preserve Maestro's quality bar: no weaker verification status, no hidden-oracle exposure, and no default behavior change without benchmark evidence.
- For Codex-specific behavior, check
docs/codex.mdand current official Codex docs before changing durable guidance. - Keep always-loaded instruction files stable. Put volatile run notes,
dated scratch state, machine-local paths, and benchmark deltas in
summaries or checkpoints, not
AGENTS.md/adapters.
Before completion after edits, run:
npm test
npm run lint
npm run bench-verify