What is forge CLAUDE.md?

Project instructions for Forge, an open-source system that assembles teams of AI agents for scientific work. They describe the expected file formats, technology choices, team sizes, roles, handoffs, and evidence requirements.

Use them when creating or reviewing Forge skills, agent definitions, team blueprints, packaging scripts, and library metadata.

They give contributors shared rules for structuring agent definitions and team plans. This makes the project easier to maintain and discourages unsupported research claims.

How jdforsythe/forge configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jdforsythe/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/jdforsythe/forge/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/jdforsythe/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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/jdforsythe/forge/claude-md/github.svg)](https://agentmods.dev/instructions/jdforsythe/forge/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/jdforsythe/forge/claude-md"><img src="https://agentmods.dev/badge/instructions/jdforsythe/forge/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.

Your own site · 80×15

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

Per session 214 This file is loaded in full into every session.

When invoked 214 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	$0.00214	$0.00214
Opus 5.5	$0.00086	$0.00086
Sonnet 5.5	$0.00043	$0.00043
Haiku 4.5	$0.00021	$0.00021

Measured 2mo ago against content hash d4f9fdb47e1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 2mo 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 · 24 lines

What it actually says

Forge

An open-source system for science-backed AI team assembly.

Tech Stack

Pure markdown skills and agent definitions (no framework dependency)
Python scripts for packaging (package_skill.py)
JSON for library index and usage tracking

Conventions

All skill/agent files use YAML frontmatter
Agent definitions follow the 7-component structure (see schemas/agent-definition.md)
Team blueprints follow the blueprint format (see schemas/team-blueprint.md)
SKILL.md files must be <500 lines; overflow goes in references/
Reference files must be <300 lines with TOC if >150 lines
File/folder names: kebab-case
All research claims must cite sources

Key Principles

Start simple, add complexity only when demonstrated need requires it
Vocabulary routing is the primary generative-quality lever
Real-world roles define scope, register, and decision boundaries
3-4 agents recommended, 5 maximum per team
Structured artifacts for handoffs, not free-form dialogue

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.

2mo ago First seen · 24 lines · 214 tokens per session scan A d4f9fdb47e1b

Subscribe to this mod's changes

forge CLAUDE.md is an instructions file published in the GitHub repository jdforsythe/forge (151 stars, last pushed 4mo ago), licensed MIT. It adds 214 tokens to every session, about $0.0009 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 2026-08-30.

Building agents

forge CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
forge CLAUDE.mdjdforsythe/forge	Instructions file	151	4mo ago	MIT	A	214	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

forge: Instructions file for Claude Code