Writer agent for the /ai-context pipeline. Generates or refreshes AGENTS.md and CLAUDE.md in the target repo from the inspector digest. Idempotent — diffs against on-disk bytes, writes only when content changed, respects the ownership contract. Use only as step 4 of /ai-context.
Writer agent for the /ai-context pipeline. Generates or refreshes the 8 docs/agents/.md files describing the implemented code as it is (AS IS only — no prescriptive layers). Idempotent — diffs against on-disk bytes, writes only when content changed, respects the ownership contract. Use only as step 4 of /ai-context.
Read-only repo inspector for the /ai-context pipeline. Sweeps the implemented code (never .spec) and returns a structured digest — stack, commands, layout, signals, artifact ownership — that the writer agents consume verbatim. Use only as step 3 of /ai-context.
Adversarial requirements QA for the /plan pipeline (step 6). Two modes — analyze (find ambiguities, gaps, contradictions in SPEC.md and return prioritized questions) and resolve (apply developer answers in-place, increment version). Never talks to the developer directly; the router owns the conversation. Use only as…
Read-only planning lead for the /plan pipeline (step 7). Produces PLAN.md — architecture-aware task decomposition with dependency phases, risks, validation criteria — plus PHASES.md (ralph.sh-executable view) and conditionally formal contracts (OpenAPI/gRPC/AsyncAPI) from SPEC RIGID. Use only as step 7 of /plan.
Requirements engineer for the /plan pipeline (step 5). Transforms a confirmed developer description + ACs into a formal SPEC.md with GEARS syntax, RIGID/FLEXIBLE sections, AS IS / TO BE diagrams, and binary acceptance criteria. Use only as step 5 of /plan.