delegate

delegate is a skill for Claude Code, Codex from mhlaghari/stuntman. It costs 146 tokens per session (1,895 once invoked), scanned A, original, MIT.

A delegation workflow in which Claude plans and reviews while a separate headless coding worker performs the implementation.

In plain words
What is it for?
Use it to send implementation tasks to supported workers such as Codex, opencode, Antigravity, Muse, or a local Claude proxy.
Why use it?
The planning agent does not need to write every change itself, and the resulting work can be checked and revised through review.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the stuntman plugin — 7 skills, 1 hook shipped together

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/mhlaghari/stuntman/delegate
Any agent
npx skills add mhlaghari/stuntman --skill delegate
Clone the repo
git clone --depth 1 https://github.com/mhlaghari/stuntman

Made for: Claude Code, Codex.

Or install stuntman, the plugin that ships this one along with the rest of its 7 skills, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for delegate

README.md
[![agentmods](https://agentmods.dev/badge/skills/mhlaghari/stuntman/delegate.svg)](https://agentmods.dev/skills/mhlaghari/stuntman/delegate)
Your own site
<a href="https://agentmods.dev/skills/mhlaghari/stuntman/delegate"><img src="https://agentmods.dev/badge/skills/mhlaghari/stuntman/delegate.svg" alt="Measured on agentmods" height="20"></a>
Per session 146 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,895 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00146 $0.01895
Opus 5 $0.00073 $0.00948
Sonnet 5 $0.00029 $0.00379
Haiku 4.5 $0.00015 $0.00189

Measured 5d ago against content hash bfe38ff783bf, 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 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`curl -s -m 2 http://localhost:8082/v1/models -H "x-api-key: freecc" -o /dev/null -w "%{http_code}"`.
skills/delegate/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

stuntman: plan → execute → review

You (Claude, on subscription) are the architect and reviewer. A cheap worker model (stunt) is the executor. Never implement the task yourself unless the worker fails twice.

Resolve the worker command

STUNT="$(command -v stunt || echo "${CLAUDE_PLUGIN_ROOT}/bin/stunt")"

Use "$STUNT" everywhere below. The worker backend is $STUNTMAN_WORKER (claude via local proxy — the default —, opencode, codex, agy, or muse).

Preflight

  • Backend claude (default): check the proxy — curl -s -m 2 http://localhost:8082/v1/models -H "x-api-key: freecc" -o /dev/null -w "%{http_code}". If unreachable, start fcc-server in the background (run_in_background), wait a few seconds, re-check. If still down, tell the user and stop.
  • Backend opencode: check opencode --version. If missing, tell the user to install it (brew install sst/tap/opencode) and stop.
  • Backend codex: check codex --version and codex login status. If the CLI is missing, tell the user to install it (npm install -g @openai/codex) and stop. If not logged in, tell the user to run codex login and stop.
  • Backend agy: check agy --version. If missing, tell the user to install Google Antigravity (the agy CLI ships with it; agy install wires the PATH) and stop.
  • Backend muse: check muse --version. If missing, tell the user to install Meta's Muse Code CLI and run muse login, then stop.

1. PLAN (you — this is where the expensive tokens earn their keep)

Explore the codebase yourself (Read/Grep/Glob) and write a self-contained spec to a temp file. The worker has NO access to this conversation, so the spec must include:

  • Exact goal and acceptance criteria.
  • Files to create/modify with absolute or repo-relative paths, and precisely what changes to make (signatures, behavior, edge cases). Decide everything yourself — leave the worker zero design decisions. Weak models executing great instructions beat strong models executing vague ones.
  • Constraints: match existing style, no extra refactors, no new dependencies unless listed, never run git write commands.
  • Verification: the exact commands that must pass (tests, build, lint), including any env activation they need.
  • End with: "When done, run the verification commands and fix failures before finishing. Reply with a summary of changed files."

Read the full file on GitHub · 145 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. 5d ago First seen · 145 lines · 146 tokens per session scan A bfe38ff783bf

Subscribe to this mod's changes

delegate is a skill published in the GitHub repository mhlaghari/stuntman (13 stars, last pushed 7d ago), licensed MIT. It adds 146 tokens to every session and 1,895 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

clawrouter

Hosted-gateway LLM router — save 84% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across 76 models from OpenAI, Anthropic, Google, DeepSeek, xAI, Z.AI, and more. 7 free open-weight models included. Also exposes realtime market data…

BlockRunAI/ClawRouter · 222 tokens

surf

Use this skill — NOT browser or webfetch — for ALL Surf crypto-data calls. 83 endpoints at localhost:8402/v1/surf/ covering CEX/DEX markets, on-chain SQL over 80+ ClickHouse tables (Ethereum, Base, Arbitrum, BSC, TRON, HyperEVM, Tempo), 100M+ labeled wallets, prediction markets (Polymarket + Kalshi), social/CT…

BlockRunAI/ClawRouter · 130 tokens

phone

Verify phone numbers (carrier + SIM-swap fraud signals) and place AI-powered outbound voice calls via BlockRun's gateway (Twilio + Bland.ai). Trigger when the user asks to look up a number, check fraud risk, buy/rent a phone number, or place an AI voice call. Payment is automatic via x402 from the wallet.

BlockRunAI/ClawRouter · 72 tokens

imagegen

Generate or edit images via BlockRun's image API. Trigger when the user asks to generate, create, draw, make an image — or to edit, modify, change, or retouch an existing image.

BlockRunAI/ClawRouter · 45 tokens

polymarket-trading

Use when the user wants to actually PLACE, manage, or redeem bets on Polymarket (not just read odds — that's the blockrunpredexon data tools). Covers setup (deposit wallet, funding, approvals), buy/sell with confirm gating, positions, redeeming winnings, geoblock handling, and the end-to-end flow.

BlockRunAI/ClawRouter · 76 tokens

release

Use this skill for EVERY ClawRouter release. Enforces the full checklist — version sync, CHANGELOG, build, tests, npm publish, git tag, GitHub release. No step can be skipped.

BlockRunAI/ClawRouter · 44 tokens