A command for coordinating multiple coding agents on one project. It routes requests such as setup, task execution, status checks, indexing, configuration, history, rollback, and agent management.

Use it to initialize a project, send coding tasks, inspect the team or code index, change settings, review past tasks, undo the latest task, or manage custom agents.

It gives one entry point for common multi-agent work instead of requiring separate commands for each operation.

crew — Command by d3x293

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/d3x293/code-crew/crew

Clone the repo

git clone --depth 1 https://github.com/d3x293/code-crew

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 517 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.

Model	Per session	Once invoked
Fable 5	$0.00023	$0.00517
Opus 5	$0.00012	$0.00259
Sonnet 5	$0.00005	$0.00103
Haiku 4.5	$0.00002	$0.00052

Measured 2d ago against content hash 3f312f3421e2, 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.

commands/crew.md · 39 lines

What it actually says

/crew

You are the CodeCrew orchestration system. Parse the user's subcommand and route accordingly:

Subcommand Routing

If the user typed /crew init → Use the codecrew:crew-init skill to analyze the project and set up the agent team
If the user typed /crew task "..." → Route through crew-task command (handles --lite flag detection, then invokes task-router or lite-router)
If the user typed /crew lite "..." → Route through crew-lite command (directly invokes lite-router — lite mode, no Opus)
If the user typed /crew status → Use the codecrew:team-status skill to show current state
If the user typed /crew reindex → Use the codecrew:codebase-index skill to rebuild the 3-layer index
If the user typed /crew config ... → Use the codecrew:crew-config skill to view/update configuration
If the user typed /crew history ... → Use the codecrew:task-history skill to view past tasks
If the user typed /crew rollback → Use the codecrew:task-rollback skill to undo the last task
If the user typed /crew agent ... → Use the codecrew:agent-manager skill to create/list/remove custom agents
If no subcommand or unrecognized → Show this help:

CodeCrew — Your Virtual Dev Crew

  /crew init                  Setup project index + agent team
  /crew task "desc"           Delegate task (full mode with Opus CEO)
  /crew lite "desc"           Delegate task (no Opus, saves 40-60%)
  /crew status                Team, index health, performance
  /crew reindex               Rebuild codebase index
  /crew config show|set|reset Configuration
  /crew history               Past tasks (--type, --agent, --limit)
  /crew rollback              Undo last task via git
  /crew agent create|list|remove  Custom agents

Start: /crew init | Save costs: /crew lite "desc"

Always invoke the appropriate skill using the Skill tool. Do not attempt to handle the subcommand logic yourself.

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.

2d ago First seen · 39 lines · 23 tokens per session scan A 3f312f3421e2

Subscribe to this mod's changes

crew is a command published in the GitHub repository d3x293/code-crew (13 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 517 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 2026-08-30.

Code review Data and AI Planning ai-agents ai-coding-assistant-tools anthropic-claude claude-code claude-code-plugin claude-code-skills

crew

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

/crew

Subcommand Routing

What this file has done since we first saw it

Other commands, from other repositories

README

update-docs

plugin-audit

seo-auditor

clean

review