delegate

A guide for splitting a large coding, research, or checking task into focused pieces that separate helper agents can handle.

In plain words
What is it for?
Use it when independent parts of a multi-step task can run in parallel, such as exploring separate files, making bounded edits, or running focused tests.
Why use it?
It helps divide work safely while keeping the main decisions, integration, final review, and verification together.

Skill for Claude CodeCodex

▶ DeepSeek TUI | CodeWhale: Free Claude Code Alternative Built in Rust (Full Install & Demo) AI BrainBox · about Hmbown/CodeWhale · on YouTube →
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 skills/hmbown/codewhale/delegate
Any agent
npx skills add Hmbown/CodeWhale --skill delegate
Clone the repo
git clone --depth 1 https://github.com/Hmbown/CodeWhale

Made for: Claude Code, Codex.

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 663 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 $0.00036 $0.00663
Opus 5 $0.00018 $0.00331
Sonnet 5 $0.00007 $0.00133
Haiku 4.5 $0.00004 $0.00066

Measured 2d ago against content hash c9cd48fbc33d, 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.

crates/tui/assets/skills/delegate/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delegate

Use sub-agents when they can do focused work in parallel while the parent keeps architectural judgment, integration, and final verification.

Keep vs Delegate

Keep in the parent:

  • Understanding the user's actual request and constraints
  • Architecture, security, product, and release-risk decisions
  • Cross-module integration
  • Final review, test interpretation, and user-facing summary

Delegate to sub-agents:

  • Read-only exploration over a bounded file set
  • Mechanical edits with a clear file ownership boundary
  • Focused test or lint runs
  • Boilerplate generation from an explicit spec
  • Independent checks that can run while parent work continues

Do not delegate tiny one-step tasks, ambiguous product decisions, destructive operations without a clear acceptance criterion, or final verification.

Launch Focused Work

Use agent for a focused child run. Launch independent children together so they can run in parallel.

Prefer provider-neutral model_strength over hardcoded model ids. Children inherit the active model by default (model_strength: "same"), including type: "scout", so pass model_strength: "faster" explicitly to get the cheaper same-family sibling for read-only exploration:

{
  "name": "config_audit",
  "prompt": "Inspect crates/tui/src/config.rs and crates/tui/src/settings.rs for duplicate model-default logic. Return file/line findings only; do not edit files.",
  "type": "scout",
  "model_strength": "faster",
  "cwd": "."
}

For code changes, give the child a precise write boundary and tell it not to revert unrelated edits. Keep implementation children capable with model_strength: "same":

{
  "name": "docs_patch",
  "prompt": "Update only docs/configuration.md to document the new [statusline] keys. Match the surrounding style. Do not edit other files.",
  "type": "builder",
  "model_strength": "same",
  "cwd": "."
}

Use fork_context: true only when the child genuinely needs the current conversation prefix. Leave it omitted for fresh, narrower context.

Read the full file on GitHub · 91 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 · 91 lines · 36 tokens per session scan A c9cd48fbc33d

Subscribe to this mod's changes

delegate is a skill published in the GitHub repository Hmbown/CodeWhale (40,889 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 663 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.