claude-agents-forge CLAUDE.md

claude-agents-forge CLAUDE.md is an instructions file for Claude Code from Mationetap/claude-agents-forge. It costs 1,156 tokens per session, scanned A, a copy of claude-agents-forge CLAUDE.md, MIT.

A set of instructions for Claude Code projects that explains the repository, agent specification format, folder structure, and architecture rules. Claude Code is a coding assistant that follows project guidance stored in files such as CLAUDE.md.

In plain words
What is it for?
Use it when working on the Claude Agents Forge repository, especially when creating or reviewing agent specifications and related documentation.
Why use it?
It gives coding agents a shared description of how the repository is organised and what rules its agent files must follow, reducing inconsistent changes.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: mentions CLAUDE.md; mentions subagents; names the NotebookEdit tool.

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/mationetap/claude-agents-forge/claude-md
Clone the repo
git clone --depth 1 https://github.com/Mationetap/claude-agents-forge

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-agents-forge CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mationetap/claude-agents-forge/claude-md.svg)](https://agentmods.dev/instructions/mationetap/claude-agents-forge/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mationetap/claude-agents-forge/claude-md"><img src="https://agentmods.dev/badge/instructions/mationetap/claude-agents-forge/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,156 This file is loaded in full into every session.
When invoked 1,156 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.01156 $0.01156
Opus 5 $0.00578 $0.00578
Sonnet 5 $0.00231 $0.00231
Haiku 4.5 $0.00116 $0.00116

Measured 5d ago against content hash b790cf559557, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

claude-agents-forge 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 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.

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.

Origin

This is a copy

100% identical to claude-agents-forge CLAUDE.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

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.

Project Overview

Claude Agents Forge is a collection of production-hardened agent specs (.md files with YAML frontmatter) for Claude Code. It is NOT a code project — there is no build system, no tests, no dependencies. The deliverables are agent specification files.

Repository Structure

agents/
  orchestration/conductor.md    # Central orchestrator (opus, 200 turns)
  quality/                      # Read-only quality gate agents (sonnet)
  development/                  # Dev agents that write code (sonnet)
docs/
  agent-spec.md                 # Full YAML frontmatter reference
  comparison.md                 # Comparison with other agent repos
  getting-started.md            # Installation & usage guide

Agent Spec Format

Every agent is a Markdown file with YAML frontmatter. All these fields are required:

---
name: agent-name                    # lowercase, hyphens
description: >                      # role + capabilities + limitations
tools: [Read, Glob, Grep, Bash]     # explicit allowlist
disallowedTools: [Write, Edit, ...]  # hard denylist
model: sonnet                       # sonnet | opus | haiku | inherit
permissionMode: bypassPermissions   # default | bypassPermissions | plan
maxTurns: 60                        # hard turn limit
memory: local                       # user | project | local
mcpServers: [eslint, semgrep]       # optional MCP integrations
---

Architecture Rules

  • Conductor uses opus, never writes code, orchestrates via Task() references
  • Quality agents (agents/quality/) are read-only — Write/Edit/NotebookEdit must be in disallowedTools
  • Dev agents (agents/development/) must declare a "File Scope" section
  • Dual-mode agents (test-engineer, doc-writer, monitoring-engineer) have explicit review/write modes
  • Every agent must have: turn budget table, bash timeout table, memory strategy section, 75% turn limit safety trigger

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. 5d ago First seen · 98 lines · 1,156 tokens per session scan A b790cf559557

Subscribe to this mod's changes

claude-agents-forge CLAUDE.md is an instructions file published in the GitHub repository Mationetap/claude-agents-forge (1 stars, last pushed 6mo ago), licensed MIT. It adds 1,156 tokens to every session, about $0.0058 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to claude-agents-forge CLAUDE.md, differing in 0 lines, and is treated as a copy.