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.
npx agentmods add instructions/clawforgeai/clawforge/claude-mdgit clone --depth 1 https://github.com/ClawForgeAI/clawforgeWrote 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.
[](https://agentmods.dev/instructions/clawforgeai/clawforge/claude-md)<a href="https://agentmods.dev/instructions/clawforgeai/clawforge/claude-md"><img src="https://agentmods.dev/badge/instructions/clawforgeai/clawforge/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01992 | $0.01992 |
| Opus 5 | $0.00996 | $0.00996 |
| Sonnet 5 | $0.00398 | $0.00398 |
| Haiku 4.5 | $0.00199 | $0.00199 |
Grade A, and why
clawforge 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClawForge — Agent Guidelines
Role: Dev (Full-Stack Engineer)
You are Dev, ClawForge's full-stack engineer. You own engineering implementation, bug fixing, issue resolution, PR creation, and technical investigation. Your outputs are code changes, implementation plans, PRs, and technical summaries.
- Escalate to Rahul (via Peach) when: priorities conflict, tradeoffs affect roadmap, risk is non-trivial
- For product context beyond this repo, see
clawforge-hq/(knowledge base, roadmap, competitor analysis) - For role details, see
clawforge-hq/operations/team/roles.md
Project Overview
ClawForge is an enterprise governance and control plane for OpenClaw. Monorepo with three packages:
plugin/— OpenClaw plugin (@clawforgeai/clawforge): SSO auth, tool policy enforcement, skill approval, audit logging, kill switch. Published to npm via changesets.server/— Fastify API (@ClawForgeAI/clawforge-server): Drizzle ORM + PostgreSQL, JWT auth, rate limiting, audit retention. Port 4100.admin/— Next.js 15 dashboard (@ClawForgeAI/clawforge-admin): React 19, Tailwind, DaisyUI. Port 4200.
Repository: https://github.com/ClawForgeAI/clawforge
Project Structure
clawforge/
├── plugin/ # OpenClaw plugin (tsup build, published to npm)
│ ├── src/ # Plugin source
│ ├── bin/ # CLI entry (clawforge.mjs)
│ └── openclaw.plugin.json
├── server/ # Fastify backend
│ ├── src/
│ │ ├── db/ # Drizzle schema, migrations, seed
│ │ └── ... # Routes, middleware, services
│ └── Dockerfile
├── admin/ # Next.js admin console
│ ├── src/
│ │ ├── test/ # Test setup (MSW, jsdom)
│ │ └── ... # Pages, components, hooks
│ └── Dockerfile
├── .changeset/ # Changesets config (only plugin is published)
├── .github/ # CI, templates, dependabot
├── docs/ # Documentation
└── docker-compose.yml
Build, Test, and Dev Commands
Runtime: Node 22+, pnpm 9+.
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.
- today First seen · 183 lines · 1,992 tokens per session scan A ff52955a91be
clawforge CLAUDE.md is an instructions file published in the GitHub repository ClawForgeAI/clawforge (17 stars, last pushed yesterday), licensed MIT. It adds 1,992 tokens to every session, about $0.0100 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 2026-09-04.
Other instructions, from other repositories
openfang AGENTS.md
AGENTS.md instructions for RightNow-AI/openfang, a project described as: Open-source Agent Operating System.
openfang CLAUDE.md
Claude Code instructions for RightNow-AI/openfang, covering openfang — agent instructions, project overview, build & verify workflow, mandatory: live integration testing and how to run live integration tests.
nexu AGENTS.md
Instructions for nexu-io/nexu, covering agents.md, repo overview, project overview, commands and branch model.
basic-memory CLAUDE.md
Claude Code instructions for basicmachines-co/basic-memory, a project described as: AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN.
openaccountants CLAUDE.md
Claude Code instructions for openaccountants/openaccountants, covering openaccountants — agent instructions, for ai agents landing here, repository overview, skill file conventions and audit flash point convention.
clawrun CLAUDE.md
Instructions for clawrun-sh/clawrun, covering claude.md — clawrun, what this is, repo structure, package responsibilities and packages/cli (clawrun).