This repository also configures its own agents. See what pi-crew tells them →
Agent Claude Code
Analyze requirements, ambiguity, and hidden constraints When NOT to use: structuring the how (planner); post-implementation verification (verifier).
Agent Claude Code
Independently re-verify findings WITHOUT trusting prior analysis — an unbiased cold check to catch confirmation bias the chained reviewer/verifier path can introduce When NOT to use: routine correlation verification (verifier — faster and cheaper); first-pass review.
Agent Claude Code
Challenge plans and designs before execution When NOT to use: reviewing implemented code (reviewer); trivial one-phase plans with no risk surface.
Agent Claude Code
Implement planned code changes When NOT to use: design/UX decisions (designer), architecture calls (oracle), exploration-heavy discovery (explorer).
Agent Claude Code
Fast codebase discovery and file/symbol mapping When NOT to use: write-actions of any kind; external docs lookup (librarian); deep adversarial analysis (council).
Agent Claude Code
Create an execution plan with clear sequencing and risk notes When NOT to use: requirements clarification (analyst); executing phases (executor).
Agent Claude Code
Review code changes for correctness, maintainability, and regressions When NOT to use: pre-execution plan critique (critic); security threat-modeling (security-reviewer).
Agent Claude Code
Review changes for security vulnerabilities and trust-boundary issues When NOT to use: general correctness/style review (reviewer); running audits yourself — no shell access, route audit commands to executor.
Agent Claude Code
Design and implement test strategy for a change When NOT to use: implementing the feature under test (executor); one-off verification runs (verifier).
Agent Claude Code
Verify that implementation satisfies the requested goal When NOT to use: adversarial cold re-checks of high-stakes verdicts (cold-verifier); authoring new tests (test-engineer).
Agent Claude Code
Write concise documentation, migration notes, and summaries When NOT to use: code changes (executor); verifying claims — mark sections DRAFT instead.
Agent Claude Code
Critic seat on a decision council. Receives ONLY the question (no conversation history) and stress-tests the reasoning itself — fallacies, hidden assumptions, real vs assumed constraints. Spawned by the council skill. When NOT to use: outside a council round — invoke via the council skill, not this seat directly.
Agent Claude Code
Pragmatist seat on a decision council. Receives ONLY the question (no conversation history) and weighs practical tradeoffs — cost, maintenance, time-to-value, alternatives. Spawned by the council skill. When NOT to use: outside a council round — invoke via the council skill, not this seat directly.
Agent Claude Code
Skeptic seat on a decision council. Receives ONLY the question (no conversation history) and finds every flaw, risk, and failure mode. Spawned by the council skill. When NOT to use: outside a council round — invoke via the council skill, not this seat directly.
Agent Claude Code
UI/UX specialist for designing, reviewing, and implementing interfaces — web frontends and terminal UIs. Use for styling, layout, interaction, and design handoff. When NOT to use: backend/data logic (reviewer); design changes beyond the assigned scope — surface in NOTES instead.
Agent Claude Code
Documentation and dependency-source research. Use for library internals, version behavior, README/CHANGELOG archaeology, and nodemodules source analysis. When NOT to use: repo-local code mapping (explorer); web fetching — no web tools, flag UNCERTAIN instead.
Agent Claude Code
Strategic technical advisor for architecture decisions, complex debugging guidance, and simplification (YAGNI). Escalation-tier, read-only. When NOT to use: routine decisions the team can make; requirement ambiguity (analyst); plan hole-finding (critic).
Agent Claude Code
Delegated orchestration specialist: routes work across lanes, dispatches, monitors, reconciles, and verifies multi-agent runs. Use when a worker itself must coordinate sub-work end-to-end. When NOT to use: when the main session can orchestrate directly (cheaper), or for single-task execution (executor).
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: