claude-forge: Instructions file for Codex

AGENTS.md

claude-forge AGENTS.md is an instructions file for Codex, OpenCode from ForgeyClap/claude-forge. It costs 2,754 tokens per session, scanned A, original, MIT.

A project instruction file describing Forge’s built-in coding agents, how they divide work, and how quality checks send unfinished work back for fixes.

In plain words
What is it for?
It helps plan builds, assign work to specialist agents, run tests and reviews, and manage the fix loop.
Why use it?
It gives Claude Code a shared operating model for coordinating multiple agents instead of handling every task as one unstructured conversation.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is ForgeyClap/claude-forge's own configuration. It tells Codex and OpenCode how to work on claude-forge 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-forge configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ForgeyClap/claude-forge. 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/ForgeyClap/claude-forge/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/ForgeyClap/claude-forge

Made for: Codex, OpenCode.

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-forge AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/forgeyclap/claude-forge/agents-md.svg)](https://agentmods.dev/instructions/forgeyclap/claude-forge/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/forgeyclap/claude-forge/agents-md"><img src="https://agentmods.dev/badge/instructions/forgeyclap/claude-forge/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,754 This file is loaded in full into every session.
When invoked 2,754 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 $0.02754 $0.02754
Opus 5 $0.01377 $0.01377
Sonnet 5 $0.00551 $0.00551
Haiku 4.5 $0.00275 $0.00275

Measured 4d ago against content hash ad32fce26a11, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

claude-forge AGENTS.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.

AGENTS.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents

Forge ships 18 built-in agents12 permanent Bosses plus 6 on-demand specialists — and turns Claude Code into a coordinated team that builds, tests, reviews and ships. Every one is a real Claude Code Agent-tool subagent defined in .claude/agents/*.md, not a simulated persona or a fabricated name on a dashboard.

[!NOTE] Honest count. Forge ships exactly 18 agents and 23 skills. Forge can also route to your wider agent ecosystem (ECC / Claude-Code agent types) when a task calls for something outside the built-ins — but those are not part of this repo. When you see large numbers elsewhere, that is the routable ecosystem, not what claude-forge ships. See Routing to your wider ecosystem.


How Forge uses agents

Forge is a hierarchy, not a free-for-all. Work flows top-down and quality flows bottom-up:

You (orchestrator) ── /forge <task>
        │
        ▼
   Boss (Lead)  ──►  Head Chef  ──►  domain Bosses + specialists
   owns mission     splits into        do the actual work
                    work packages
        ▲                                     │
        └──────── QA fix-loop ◄───── Test Boss / Review Boss
  • Lead → Bosses → specialists. The Boss owns the mission; Head Chef breaks it into exact work packages; the right domain Bosses and specialists execute; Test Boss and Review Boss gate the result.
  • Real subagents. Each agent is dispatched via the Claude Code Agent tool with its own model, tools and effort budget (from its frontmatter). Nothing is theatre.
  • Dynamic, right-sized teams. Forge picks the smallest relevant team per task (see the fan-out levels in CLAUDE.md): a one-line fix gets one or two agents; a full-stack build gets a phased swarm. Forge does not over-spawn to look impressive, and does not lock to a fixed count.
  • Honest ledger. Every run records which agents actually worked in FORGE_AGENT_LEDGER.md, with evidence and one of the fixed statuses — REAL INVOKED · REAL TOOL/SKILL USED · INTERNAL ROLE ONLY · NOT USED · FAILED. No fake "done", no invented tests, no imaginary agents.

Read the full file on GitHub · 120 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 · 120 lines · 2,754 tokens per session scan A ad32fce26a11

Subscribe to this mod's changes

claude-forge AGENTS.md is an instructions file published in the GitHub repository ForgeyClap/claude-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,754 tokens to every session, about $0.0138 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 2026-09-03.

Related

Other instructions, from other repositories

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

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

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

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

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