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/razaib-khan/forgeweave/agents-mdgit clone --depth 1 https://github.com/Razaib-khan/ForgeWeaveWrote 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/razaib-khan/forgeweave/agents-md)<a href="https://agentmods.dev/instructions/razaib-khan/forgeweave/agents-md"><img src="https://agentmods.dev/badge/instructions/razaib-khan/forgeweave/agents-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 | $0.04224 | $0.04224 |
| Opus 5 | $0.02112 | $0.02112 |
| Sonnet 5 | $0.00845 | $0.00845 |
| Haiku 4.5 | $0.00422 | $0.00422 |
Grade A, and why
ForgeWeave 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.
How it starts
The opening of the file, as written. The whole thing — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Version: 2.0 Last updated: 2026-06-20 Status: Active
This file is loaded by every agent at initialization time. It defines the project's agent registry AND provides global behavioral rules that all coding agents must follow.
IMPORTANT: Agents must not modify this file directly. Configuration changes must go through the
forgeCLI or a maintainer-approved PR.
Table of Contents
- Global Rules for All Agents
- Working with ForgeWeave
- Usage of Skills
- Usage of Subagents
- Usage of MCP Servers
- Agent Registry
- Validation Rules
Global Rules for All Agents
These rules apply to EVERY agent operating in this project, regardless of role:
- Read AGENTS.md first — Before any task, read this file to understand project conventions and available agents/skills.
- Use skills — Always check available skills before writing code from scratch. Load the matching skill and follow its instructions.
- Use subagents — Delegate complex, independent work to subagents. Do not do everything yourself.
- Use MCP servers — Prefer Playwright MCP tools (
browser_*) over raw bash/subprocess for browser automation. Use Headroom MCP (headroom_compress) to reduce token costs on large tool outputs before sending to the LLM. - No hallucination — Every claim about external APIs, libraries, or tools must come from a loaded skill, MCP tool output, Context7 documentation, or official documentation.
- Skill-builder is mandatory — When you learn a repeatable pattern, create a skill for it using the skill-builder skill. Skills are the project's collective knowledge.
Working with ForgeWeave
ForgeWeave provides a complete agent orchestration framework. Every coding agent operates within this system:
The Playwright MCP Server
Playwright MCP (npx @playwright/mcp@latest) provides browser automation tools. All web interaction tasks use Playwright MCP tools:
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.
- 4d ago First seen · 400 lines · 4,224 tokens per session scan A c1c725b171a5
ForgeWeave AGENTS.md is an instructions file published in the GitHub repository Razaib-khan/ForgeWeave (1 stars, last pushed 2mo ago), licensed MIT. It adds 4,224 tokens to every session, about $0.0211 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 2026-08-31.
Other instructions, from other repositories
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
nanobot CLAUDE.md
Claude Code instructions for HKUDS/nanobot, a project described as: Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps.
agentic-harness AGENTS.md
AGENTS.md instructions for frangelbarrera/agentic-harness, covering project context, architecture in 30 seconds, non-negotiable rules (from manifesto.md), coding standards and commit conventions.
initrunner CLAUDE.md
Instructions for vladkesler/initrunner, covering initrunner and project map.
tri-party-framework AGENTS.md
Instructions for r-design-j/tri-party-framework, covering global codex working agreements, output review standard, daily work standard extraction, tri-party framework definition and tri-party trigger contract.
openlegion AGENTS.md
AGENTS.md instructions for openlegion-ai/openlegion, a project described as: Secure autonomous AI agent framework and platform. Build AI teams by describing what you want. Orchestrate agents that can do everything a human can do.