Agent Readiness

Assess, harden, scaffold, and diagnose a repository's agent-readiness for coding-agent harnesses (Claude Code, Cursor, Codex, Copilot, Windsurf, Aider). Harness-agnostic and portable-first (AGENTS.md, SKILL.md, MCP, OpenTelemetry). Grounding lives in skill.json; this file is runtime routing only. This is the repo-hardening arm of the agent-mirror family; agent-ops (the family front-door) routes here to harden a repo.

Boundaries

Do NOT use to design the SDK/tool surface an agent consumes (use agent-dx) or agent-native docs like llms.txt/AGENTS.md (use agent-docs), to promote recurring failures into rules from a feedback signal (use rules-from-coding-agent-failures), or to design or operate an AI product's eval loops (use agent-test / agent-ops).

Produces: an intent-specific report — assess-report.md, harden-recommendation.md, scaffold-bundle.md, or diagnose-runbook.md. Tracked assessments also emit harden-repo-for-coding-agents-findings-ledger-<date>-<slug>.md and harden-repo-for-coding-agents-workflow-state-<date>-<slug>.json.