What is arcforge AGENTS.md?

A contributor guide for the arcforge repository. It points coding agents to the files that contain the project's rules, commands, architecture, and contribution process.

Use it when contributing to arcforge to locate repository conventions, test commands, product documents, and contribution instructions.

It gives agents one starting point for finding the rules they must follow before changing the repository.

How GregoryHo/arcforge configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to GregoryHo/arcforge. 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/GregoryHo/arcforge/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/GregoryHo/arcforge

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/gregoryho/arcforge/agents-md/github.svg)](https://agentmods.dev/instructions/gregoryho/arcforge/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/gregoryho/arcforge/agents-md"><img src="https://agentmods.dev/badge/instructions/gregoryho/arcforge/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/gregoryho/arcforge/agents-md"><img src="https://agentmods.dev/badge/instructions/gregoryho/arcforge/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 560 This file is loaded in full into every session.

When invoked 560 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.

Model	Per session	Once invoked
Fable 5.1	$0.00560	$0.00560
Opus 5.5	$0.00224	$0.00224
Sonnet 5.5	$0.00112	$0.00112
Haiku 4.5	$0.00056	$0.00056

Measured 2d ago against content hash e4ae75d50c2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

arcforge 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 2d 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 · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Contributor Guide

This file is the harness-neutral entry point for AI agents working on the arcforge repo itself (Codex, Claude Code, or anything else). It deliberately contains no rules of its own — it tells you where the binding ones live, so there is exactly one copy of each.

The product ships on two hosts from one tree — Claude Code in full, Codex CLI as skills only — and the contributor surface is harness-neutral. What each host loads is .claude/rules/plugin.md (the manifest pair) and .claude/rules/architecture.md (Packaging Targets); nothing here changes it.

Read these before changing anything

.claude/rules/*.md — the standing conventions. They bind all agents, not only Claude Code (Claude Code merely auto-loads them; if your harness does not, read them yourself). Start with architecture.md — it carries the boundaries every contribution must respect, including "Docs Are the Contract".
CLAUDE.md — the command reference (test runners, static checks, dev session).
CONTRIBUTING.md — workflows: dev setup, skill authoring process (the Iron Law), PR expectations.
product/ — the product's living specs, roadmap, backlog, and decision log, maintained per product/AGENTS.md. Product-level "what and why" lives there (change the product → change its spec in the same PR); everything above is the engineering "how".

Non-negotiables (pointers, not restatements)

Skills are self-contained black boxes; engine access is the bare arcforge CLI only — .claude/rules/architecture.md (D1/D9).
Engine and hooks never reference skills/ — same file (D8).
Behavioral skill edits need eval evidence, not a self-report — .claude/rules/skills.md and .claude/rules/eval.md.
User-facing surfaces are written for users, never for contributors — .claude/rules/dev-context.md.

Verify before you hand work back

npm test                      # 5 runners, all must pass
npm run check:versions && npm run check:docs && npm run check:cli-consumers \
  && npm run check:hooks && npm run check:eval-targets && npm run check:product \
  && npm run check:file-size
npm run lint

Read the full file on GitHub · 50 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.

2d ago First seen · 50 lines · 560 tokens per session scan A e4ae75d50c2e

Subscribe to this mod's changes

arcforge AGENTS.md is an instructions file published in the GitHub repository GregoryHo/arcforge (8 stars, last pushed 14d ago), licensed MIT. It adds 560 tokens to every session, about $0.0022 per session on Opus 5.5. 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 2026-11-07.

Project management

arcforge AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
arcforge AGENTS.mdGregoryHo/arcforge	Instructions file	8	14d ago	MIT	A	560	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

arcforge: Instructions file for Codex