consult-grok
25Command Claude Code
Get a second opinion from Grok (via xAI's API, direct) on a hard problem — advisory, cross-examined, never executed blindly.
not rated 2 19d ago A 35 tokens
original MIT
crew
26Command Claude Code
Cross-vendor build — a coordinator routes work to the cheapest capable model from any vendor; Claude subagents write, external engines propose gated patches.
not rated 2
changed 1mo ago A 30 tokens
original MIT
feedback
27Command Claude Code
Rate an office agent or command from inside the IDE (fuels the improvement loop).
not rated 2 19d ago A 19 tokens
original MIT
goal
28Command Claude Code
Drive a GitHub issue to a draft PR — build, then an independent judge verifies each criterion (max 3 rounds).
not rated 2 19d ago A 27 tokens
original MIT
office-setup
29Command Claude Code
Interview the user and tailor the global office — wiring, context, and custom agents.
not rated 2 19d ago A 21 tokens
original MIT
plan
30Command Claude Code
Break work into small verifiable tasks with acceptance criteria and dependency ordering.
not rated 2 19d ago A 15 tokens
original MIT
Command Claude Code
Interview the team about this repo — fill project context and scaffold tailored specialists.
not rated 2 19d ago A 19 tokens
original MIT
ratchet
32Command Claude Code
Metric-gated autonomous optimization loop — propose, evaluate, keep the gain or revert, in a throwaway worktree; you review the staircase and merge.
not rated 2
changed 1mo ago A 33 tokens
original MIT
scout
33Command Claude Code
Multi-vendor adversarial review — fan disjoint areas to Claude tiers, ChatGPT, and Grok, cross-examine over two rounds, synthesize with convergence.
not rated 2 19d ago A 36 tokens
original MIT
ship
34Command Claude Code
Run the pre-launch checklist via parallel fan-out to specialist personas, then synthesize a go/no-go decision.
not rated 2 19d ago A 23 tokens
original MIT
snapshot
35Command Claude Code
Capture a session snapshot for this repo's Cohort context, filled from this conversation.
not rated 2 19d ago A 19 tokens
original MIT
spec
36Command Claude Code
Start spec-driven development — write a structured specification before writing code.
not rated 2 19d ago A 14 tokens
original MIT
test
37Command Claude Code
Run TDD workflow — write failing tests, implement, verify. For bugs, use the Prove-It pattern.
not rated 2 19d ago A 25 tokens
original MIT
update
38Command Claude Code
Update Cohort to the latest upstream version and recompile your IDEs.
not rated 2 19d ago A 17 tokens
original MIT
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: