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/bgreenwell/claude-forge/agents-mdgit clone --depth 1 https://github.com/bgreenwell/claude-forgeWrote 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/bgreenwell/claude-forge/agents-md)<a href="https://agentmods.dev/instructions/bgreenwell/claude-forge/agents-md"><img src="https://agentmods.dev/badge/instructions/bgreenwell/claude-forge/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 | $0.00570 | $0.00570 |
| Opus 5 | $0.00285 | $0.00285 |
| Sonnet 5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
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 3d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This document provides context and guidelines for AI agents working on the claude-forge codebase.
Project Overview
claude-forge (binary name: cforge) is a Rust CLI tool for scaffolding and managing "Claude Code" marketplaces and plugins. It helps users create valid directory structures and configuration files for the Claude ecosystem.
Architecture & Code Structure
The project is organized as a standard Rust binary:
src/main.rs: Entry point. Defines theclapCLI structure (Clistruct andCommandsenum).src/commands/: Contains the implementation logic for each subcommand.init.rs: Scaffolds a new marketplace.add.rs: Adds components (skills, commands) to plugins.register.rs: Registers plugins inmarketplace.json.validate.rs: Validates plugin structure.
src/templates/: Contains string templates or logic for generating boilerplate files.src/utils/: Shared utility functions (file I/O, string manipulation).
Tech Stack
- Language: Rust (2021 edition)
- CLI Framework:
clap(derive feature) - Error Handling:
anyhow - Serialization:
serde,serde_json
Development Workflow
Dependency Management
Dependencies are managed in Cargo.toml. No manual setup is required beyond having a working Rust toolchain.
Build & Run
Always verify changes by building and running the binary.
- Build:
cargo build - Run:
cargo run -- <command> <args>- Example:
cargo run -- init --name my-marketplace
- Example:
Testing Strategy
Important: This project currently lacks a formal test suite (cargo test will likely do nothing).
- Validation: You must manually verify changes by running the CLI commands against a temporary directory or file.
- Sanity Check: Ensure
cargo checkpasses to catch type errors.
Code Style
- Formatting: Run
cargo fmton all modified files. - Linting: Run
cargo clippyand fix warnings.
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.
- 3d ago First seen · 57 lines · 570 tokens per session scan A 083880ea0bf4
claude-forge AGENTS.md is an instructions file published in the GitHub repository bgreenwell/claude-forge (2 stars, last pushed 8mo ago), licensed MIT. It adds 570 tokens to every session, about $0.0029 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
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.