claude-delegator: Instructions file for Claude Code

CLAUDE.md

claude-delegator CLAUDE.md is an instructions file for Claude Code from jarrodwatts/claude-delegator. It costs 1,042 tokens per session, scanned A, original, MIT.

Repository instructions for a Claude Code plugin that asks GPT and Gemini command-line tools to act as specialist reviewers or implementers.

In plain words
What is it for?
Developing, testing, installing, or removing the plugin, and routing architecture, planning, scope, code-review, or security tasks to specialist agents.
Why use it?
It gives coding agents the project context, commands, testing steps, and delegation rules needed to work consistently in the repository.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is jarrodwatts/claude-delegator's own configuration. It tells Claude Code how to work on claude-delegator itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-delegator configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jarrodwatts/claude-delegator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jarrodwatts/claude-delegator/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jarrodwatts/claude-delegator

Made for: Claude Code.

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 claude-delegator CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jarrodwatts/claude-delegator/claude-md/github.svg)](https://agentmods.dev/instructions/jarrodwatts/claude-delegator/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jarrodwatts/claude-delegator/claude-md"><img src="https://agentmods.dev/badge/instructions/jarrodwatts/claude-delegator/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for claude-delegator CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jarrodwatts/claude-delegator/claude-md"><img src="https://agentmods.dev/badge/instructions/jarrodwatts/claude-delegator/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,042 This file is loaded in full into every session.
When invoked 1,042 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01042 $0.01042
Opus 5 $0.00521 $0.00521
Sonnet 5 $0.00208 $0.00208
Haiku 4.5 $0.00104 $0.00104

Measured 10d ago against content hash 0b9830052557, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

claude-delegator CLAUDE.md 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 10d 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.

CLAUDE.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What This Is

A Claude Code plugin that provides GPT (via Codex CLI) and Gemini (via Gemini CLI) as specialized expert subagents. Five domain experts that can advise OR implement: Architect, Plan Reviewer, Scope Analyst, Code Reviewer, and Security Analyst.

Development Commands

# Test plugin locally (loads from working directory)
claude --plugin-dir /path/to/claude-delegator

# Run setup to test installation flow
/claude-delegator:setup

# Run uninstall to test removal flow
/claude-delegator:uninstall

No build step, no dependencies. Uses native MCP servers from Codex and Gemini CLIs.

Architecture

Orchestration Flow

Claude acts as orchestrator—delegates to specialized experts based on task type. Supports both single-shot (independent calls) and multi-turn (context preserved via threadId).

User Request → Claude Code → [Match trigger → Select expert & provider]
                                    ↓
              ┌─────────────────────┼─────────────────────┐
              ↓                     ↓                     ↓
         Architect            Code Reviewer        Security Analyst
              ↓                     ↓                     ↓
    [Advisory (read-only) OR Implementation (workspace-write)]
              ↓                     ↓                     ↓
    Claude synthesizes response ←──┴──────────────────────┘

How Delegation Works

  1. Match trigger - Check rules/triggers.md for semantic patterns
  2. Read expert prompt - Load from prompts/[expert].md
  3. Build 7-section prompt - Use format from rules/delegation-format.md
  4. Call provider tool - mcp__codex__codex or mcp__gemini__gemini
  5. Synthesize response - Never show raw output; interpret and verify

The 7-Section Delegation Format

Every delegation prompt must include: TASK, EXPECTED OUTCOME, CONTEXT, CONSTRAINTS, MUST DO, MUST NOT DO, OUTPUT FORMAT. See rules/delegation-format.md for templates.

Read the full file on GitHub · 98 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. 10d ago First seen · 98 lines · 1,042 tokens per session scan A 0b9830052557

Subscribe to this mod's changes

claude-delegator CLAUDE.md is an instructions file published in the GitHub repository jarrodwatts/claude-delegator (996 stars, last pushed 6mo ago), licensed MIT. It adds 1,042 tokens to every session, about $0.0052 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens