crew

A multi-model build workflow in which a coordinator splits development work and assigns each task to a suitable AI model from any vendor. External models suggest changes in isolated temporary workspaces, while approved workers and a human review the results.

In plain words
What is it for?
Planning and implementing features, testing changes, reviewing diffs, and coordinating coding tasks across several AI models.
Why use it?
It distributes work according to task difficulty and cost while preventing outside models from editing the main project directly.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/askwigconsulting/cohort/crew
Clone the repo
git clone --depth 1 https://github.com/askwigconsulting/cohort
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,903 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.02903
Opus 5 $0.00015 $0.01452
Sonnet 5 $0.00006 $0.00581
Haiku 4.5 $0.00003 $0.00290

Measured 2d ago against content hash 06187129e222, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

crew scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

canonical/commands/crew.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The standard development protocol, widened across vendors: the coordinating session researches, plans, and signs off; tiered subagents implement. /crew wraps the existing loops — it uses /plan's decomposition discipline for phase 2 and /build's implement–test–verify–commit discipline inside each worker — and adds the model-routing and signoff layer on top, routing each task to the cheapest capable model from any vendor (the same token-optimization reason /scout reviews across vendors; /crew is the build sibling of /scout). It is human-invoked; the human gates (commit review, PR review) are unchanged.

The line: external engines never touch the main tree

This is the invariant, not a preference:

  • Claude subagents write directly. A Claude worker is inside the trust boundary; it edits files in a disjoint footprint (or its own worktree) and the coordinator verifies the diff. Route by tier: fable architecture-critical, opus complex, sonnet well-scoped, haiku mechanical.
  • External engines (Grok, ChatGPT) never touch the main working tree. They reach the code only inside an isolated, throwaway worktree, two ways:
    • OS-sandboxed CLI doer (preferred when the CLI is installed) — the engine's own agentic CLI edits a fresh worktree directly, with real file access, every write OS/kernel-confined there: cohort engine work gpt runs Codex under its own workspace-write sandbox; cohort engine work grok runs grok-cli under a Cohort-imposed bubblewrap jail (grok-cli has no sandbox of its own). An engine with no available sandbox is refused — never run unconfined.
    • Gated patch proposal (API fallback)cohort engine propose <engine> [--agentic] has the engine return (or explore-then-return) a candidate diff that Cohort — never the engine — parses and applies in a worktree behind the egress/secret/footprint gates. This is the API-direct path used when the local CLI isn't present; with grok-cli + bwrap installed, engine propose/review/consult grok prefer the sandboxed CLI automatically (local file access), and fall back to this API path with a printed note otherwise. Either way the coordinator verifies the diff and integrates, and it still passes the unchanged human PR review.

That is the difference between "let an external model do the work" being useful and being an RCE: it writes only where a bad run is thrown away — never your working tree, which changes only when Claude integrates a reviewed diff.

Read the full file on GitHub · 208 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 208 lines · 30 tokens per session scan A 06187129e222

Subscribe to this mod's changes

crew is a command published in the GitHub repository askwigconsulting/cohort (2 stars, last pushed 25d ago), licensed MIT. It adds 30 tokens to every session and 2,903 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.