
Periodic architectural sweep — reads existing ADRs, maps modules/dependencies/layering, and reports up to 10 prioritised findings…
Strip redundancy from prose — docs, READMEs, code comments, docstrings — keeping behaviour identical.
Shrink an agent harness (.agents/ skills + resources) to the minimum tokens that keep the exact same logic. Never touches…
Shrink the memory files sessions load — the root AGENTS.md plus every nested AGENTS.md / CLAUDE.md — to the minimum words that…
Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses…
Run the full agent-team pipeline end-to-end for one feature whose Tasks Plan is already approved by /squid-plan, handing the…
Diagnoses a red CI run, traces it to the responsible task, hands a concrete fix task to the SWE, and re-verifies green. Owns…
Reviews the pushed feature diff, tags every finding Blocker or Nit, and files ONE rollup task. Does NOT read CI, does NOT merge.
Grooms raw tasks into agent-ready specs (acceptance criteria + user stories) AND does final user-perspective acceptance review…
Implements a single groomed task assigned by the orchestrator. Writes code and tests locally. Does NOT commit until the Tester…
Verifies the SWE's uncommitted work for one task against every acceptance criterion with evidence and reports PASS or FAIL.
© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic