domains / families / agent-tooling / context-audit

context-audit

separate

Audit an agent's context layout against the four places: system prompt, tools, history, tail. Use when the user asks to audit, review or fix their agent's context, prompt caching, token spend per turn, or CLAUDE.md / AGENTS.md layout. Read-only: reports findings and a fix list, changes nothing. Do NOT use for writing evals (evals-bootstrap) or for loop design (goal-test).

When to use

• audit agent context
• review prompt caching
• analyze token spend per turn
• review CLAUDE.md layout
• review AGENTS.md layout
• fix context layout

When not to use

• writing evals
• evals-bootstrap
• loop design
• goal-test

Skill page

Source