nested-subagent CLAUDE.md

nested-subagent CLAUDE.md is an instructions file for coding agents from gruckion/nested-subagent. It costs 895 tokens per session, scanned A, original, MIT.

Repository instructions for a Claude Code plugin that lets newly created coding agents create further agents. It explains the plugin’s architecture and lists Bun commands for building, checking, developing, and testing its MCP server.

In plain words
What is it for?
Use them when developing or testing the nested-agent plugin, running its TypeScript checks, building its server, or installing it for a Claude Code session.
Why use it?
They clarify how the plugin works around the normal limit on agent nesting and provide the project’s expected development commands.

Instructions file

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 instructions/gruckion/nested-subagent/claude-md
Clone the repo
git clone --depth 1 https://github.com/gruckion/nested-subagent

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 nested-subagent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gruckion/nested-subagent/claude-md.svg)](https://agentmods.dev/instructions/gruckion/nested-subagent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/gruckion/nested-subagent/claude-md"><img src="https://agentmods.dev/badge/instructions/gruckion/nested-subagent/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 895 This file is loaded in full into every session.
When invoked 895 The same file — it is already loaded in full.
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 $0.00895 $0.00895
Opus 5 $0.00447 $0.00447
Sonnet 5 $0.00179 $0.00179
Haiku 4.5 $0.00089 $0.00089

Measured 4d ago against content hash 4e3442a865e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nested-subagent 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 4d 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 · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 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.

Project Overview

This is a Claude Code plugin that enables unlimited nested subagents. The native Task tool blocks subagents from spawning other subagents (via tool filtering in AgentTool). This plugin bypasses that limitation by spawning fresh claude -p processes, which are full main agents with complete tool access.

Commands

Build & Development

cd mcp-server && bun run build      # Build MCP server (uses tsdown)
cd mcp-server && bun run dev        # Run MCP server in development mode (tsx)
cd mcp-server && bun run typecheck  # TypeScript type checking

Testing

cd mcp-server && bun run test           # Run unit tests
cd mcp-server && bun run test:watch # Watch mode
cd mcp-server && bun run test:integration  # Integration tests (*.integration.test.ts files)

Plugin Installation

claude --plugin-dir ./       # Per-session usage

Architecture

Key Insight

The native Task tool's recursion blocker (.filter(_ => _.name !== AgentTool.name)) is process-local. By spawning a fresh claude -p process via MCP, we create a new main agent that has full tool access including the Task tool.

Native:  Main → Subagent → BLOCKED (Task tool filtered out)
Plugin:  Main → MCP Tool → spawn "claude -p" → Fresh Main Agent → CAN use Task → Unlimited nesting

Directory Structure

fallback-agent/
├── .claude-plugin/
│   └── marketplace.json     # Plugin manifest for marketplace distribution
├── .mcp.json               # MCP server configuration
├── mcp-server/
│   ├── src/index.ts        # MCP server implementation (core logic)
│   ├── dist/               # Built output (bundled with tsdown)
│   └── test/               # Unit and integration tests
└── src/                    # Reference Claude Code source (for understanding internals)

MCP Server (mcp-server/src/index.ts)

Read the full file on GitHub · 89 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. 4d ago First seen · 89 lines · 895 tokens per session scan A 4e3442a865e4

Subscribe to this mod's changes

nested-subagent CLAUDE.md is an instructions file published in the GitHub repository gruckion/nested-subagent (24 stars, last pushed 8mo ago), licensed MIT. It adds 895 tokens to every session, about $0.0045 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

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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 · 5,182 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 · 4,345 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

next.js 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