crew-task

A command that sends a coding task to a team of specialized CodeCrew agents. It can choose agents, models, and whether tasks run in parallel or in sequence.

In plain words
What is it for?
Use it to delegate feature work, bug fixes, or other coding tasks to the CodeCrew team with either full or lite routing.
Why use it?
It removes the need to decide which agent should handle a task or coordinate the team manually. A lite option uses fewer model tiers and skips the Opus-based coordinator.

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/d3x293/code-crew/crew-task
Clone the repo
git clone --depth 1 https://github.com/d3x293/code-crew
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 241 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 $0.00038 $0.00241
Opus 5 $0.00019 $0.00120
Sonnet 5 $0.00008 $0.00048
Haiku 4.5 $0.00004 $0.00024

Measured 2d ago against content hash 8f36593a5dbd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

crew-task 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-task.md · 24 lines

What it actually says

Parse the user's message after /crew task for flags and task description.

Mode Detection

  • If the message contains --liteLite Mode: Invoke the codecrew:lite-router skill (bypasses Opus CEO, uses only Sonnet + Haiku agents)
  • Otherwise → Full Mode: Invoke the codecrew:task-router skill (uses CEO on Opus for triage + full agent team)

Strip the --lite flag from the description before passing it to the skill.

What the router will do:

  1. Read the project profile and team config
  2. Classify the task (type + complexity)
  3. Select the right agents and model tiers
  4. Choose parallel vs sequential execution
  5. Auto-inject relevant skills from the catalog
  6. Execute via the agent team
  7. Auto-update the codebase index for modified files

Pass the cleaned task description to the selected skill.

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 · 24 lines · 38 tokens per session scan A 8f36593a5dbd

Subscribe to this mod's changes

crew-task is a command published in the GitHub repository d3x293/code-crew (13 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 241 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 2026-08-30.