crew

A meta-role for managing the crew role catalogue and activating or installing the crew. It delegates a supplied task to the crew subagent within that role’s defined scope.

In plain words
What is it for?
Use it to govern the available roles or install and activate the crew for a specific task.
Why use it?
It gives one entry point for role-catalogue governance and crew setup while keeping the requested task within explicit boundaries.

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/jircdev/crew-plugin/crew
Clone the repo
git clone --depth 1 https://github.com/jircdev/crew-plugin
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 134 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 $0.00015 $0.00134
Opus 5 $0.00008 $0.00067
Sonnet 5 $0.00003 $0.00027
Haiku 4.5 $0.00002 $0.00013

Measured yesterday against content hash f3d0ad08d5dc, 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 yesterday.

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.

commands/crew.md · 9 lines

What it actually says

Spawn the crew subagent for the following task. Operate strictly within that role's Authority and Scope as defined in the role document. Default to a conversational reply scoped exactly to what was asked. Produce the role's canonical Deliverable only when the user explicitly asks for a brief, spec, or document, or when the conversation has converged on a decision and writing it up is the next step. Do not drift into other roles — if the task requires a different role, say so and stop.

Task: $ARGUMENTS

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. yesterday First seen · 9 lines · 15 tokens per session scan A f3d0ad08d5dc

Subscribe to this mod's changes

crew is a command published in the GitHub repository jircdev/crew-plugin (2 stars, last pushed 12d ago), licensed MIT. It adds 15 tokens to every session and 134 once invoked, about $0.0001 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.