delegate

A command for assigning an independent task to another coding agent while the current agent continues working.

In plain words
What is it for?
Use it for self-contained coding, research, documentation, or data-analysis tasks that do not need constant back-and-forth with the current agent.
Why use it?
It reduces waiting and divides work that can be completed separately, such as writing tests, researching options, or analyzing data.

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/b33eep/claude-code-setup/delegate
Clone the repo
git clone --depth 1 https://github.com/b33eep/claude-code-setup
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,997 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 $0.00000 $0.01997
Opus 5 $0.00000 $0.00999
Sonnet 5 $0.00000 $0.00399
Haiku 4.5 $0.00000 $0.00200

Measured 2d ago against content hash 06276c53b50e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

delegate 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/delegate.md · 256 lines

How it starts

The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delegate: Independent Teammate for Parallel Work

Spawn a teammate to work on a separate task independently. You continue your own work and get notified when the teammate finishes.

Works for any independent task: coding, research, data analysis, information gathering, documentation, etc.

Usage

/delegate "write unit tests for the auth module"
/delegate "research how other CLIs handle plugin systems, summarize findings"
/delegate "analyze the last 10 Milan matches and summarize their performance"
/delegate "summarize key findings from the 5 most cited papers on topic X"
/delegate "compare pricing models of top 5 SaaS competitors"

Tasks

1. Validate arguments

The command requires a task description.

No arguments:

Usage: /delegate "task description"

Example: /delegate "write unit tests for the auth module"

Stop here. Do not proceed.

2. Assess task fitness

Delegation works best for independent tasks. If the task requires constant back-and-forth with the user or tight integration with ongoing work, suggest /with-advisor instead:

This task needs your continuous input. Use /with-advisor instead — it keeps you in the loop with expert feedback.

Stop here. Do not proceed. Otherwise, continue.

3. Classify task type

Determine whether the delegate needs to modify repo files or only read/research. This applies to all tasks: development work, research, analysis, documentation, etc.

Task type Where delegate works Examples
Write (code, docs, config) git worktree on separate branch "write tests", "refactor module", "add feature", "add documentation to repo"
Read-only (research, analysis, information gathering) Scratchpad in /tmp "research how X works", "analyze Milan's last games", "compare competitor pricing", "summarize key findings from papers"

4. Create team and spawn delegate

Use Agent Teams (TeamCreate + Task tool) to spawn the delegate.

Read the full file on GitHub · 256 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 · 256 lines · 0 tokens per session scan A 06276c53b50e

Subscribe to this mod's changes

delegate is a command published in the GitHub repository b33eep/claude-code-setup (56 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,997 tokens. 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.