agentmods.dev

agentforge CLAUDE.md

Project instructions for AgentForge, a tool for building AI-assisted software projects. They describe its commands, code structure, security rules, and testing expectations.

In plain words
What is it for?
Use them when building, testing, or extending the TypeScript and JavaScript codebase with npm.
Why use it?
They give coding agents consistent guidance so changes fit the existing design and avoid unsafe or unnecessarily complex code.

Instructions file

2 15d ago A scan 305 tokens original MIT
View the source file mrzroot/agentforge
Install

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.

agentmods
npx agentmods add instructions/mrzroot/agentforge/claude-md
Clone the repo
git clone --depth 1 https://github.com/mrzroot/agentforge
Per session 305 This file is loaded in full into every session.
When invoked 305 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00305 $0.00305
Opus 5 $0.00152 $0.00152
Sonnet 5 $0.00061 $0.00061
Haiku 4.5 $0.00030 $0.00030

Measured yesterday against content hash 0d91935d8aae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentforge 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 yesterday.

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 · 34 lines

What it actually says

CLAUDE.md - Project Directives for Claude Code

Generated by AgentForge (https://github.com/mrzroot/agentforge)

Project Overview: agentforge

AI-assisted modern codebase powered by AgentForge

Commands & Environment

  • Build / Compile: npm run build (or equivalent)
  • Run Tests: node test/test.js
  • Package Manager: npm
  • Runtime / Languages: TypeScript, JavaScript

Code Architecture & Philosophy

  • Write minimal, concise, and robust code. Avoid over-engineering (YAGNI).
  • Follow language idioms and leverage the standard library before third-party abstractions.
  • Never compromise on security, input validation, error handling, or accessibility.
  • Maintain existing style, patterns, and architectural conventions across edits.

Architectural Conventions

  • Keep modules focused, decoupled, and single-responsibility.
  • Colocate tests, types, and documentation with the corresponding modules.

Security Standards

  • Never hardcode API keys, secrets, credentials, or private tokens in source code or rules.
  • Sanitize and validate all external inputs, request payloads, and query parameters.

Testing Requirements

  • Ensure all new features, edge cases, and bug fixes have automated test coverage.
  • Keep tests deterministic, isolated, and fast.

Git Commit Standards

  • Follow Conventional Commits format (feat, fix, refactor, docs, chore).
  • Keep pull requests and commits small, atomic, and focused.
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.

  1. yesterday First seen · 34 lines · 305 tokens per session scan A 0d91935d8aae

Subscribe to this mod's changes

agentforge CLAUDE.md is an instructions file published in the GitHub repository mrzroot/agentforge (2 stars, last pushed 15d ago), licensed MIT. It adds 305 tokens to every session, about $0.0015 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.

Data and AISecurityTestingai-agentsaiderantigravityclaude-codecopilotcursor
Related

Other instructions, from other repositories

gortex CLAUDE.md

Instructions for zzet/gortex, covering gortex, build & test, codebase overview, discovery (read once, then keep using) and llm provider (powers ask and searchsymbols assist: modes).

zzet/gortex · 5,172 tokens

imagine-mcp CLAUDE.md

Instructions for n24q02m/imagine-mcp, covering imagine-mcp, architecture, tool signatures, model selection and transport modes.

n24q02m/imagine-mcp · 2,964 tokens

imagine-mcp AGENTS.md

Instructions for n24q02m/imagine-mcp, covering imagine-mcp, architecture, tool signatures, model selection and transport modes.

n24q02m/imagine-mcp · 1,454 tokens

Conductor-for-all AGENTS.md

Instructions for hlhr202/Conductor-for-all, covering conductor context and universal file resolution protocol.

hlhr202/Conductor-for-all · 533 tokens

token-ninja CLAUDE.md

Instructions for oanhduong/token-ninja, covering claude.md, what this project is, source layout, commands and invariants the code relies on.

oanhduong/token-ninja · 1,736 tokens

Conductor-for-all CLAUDE.md

Instructions for hlhr202/Conductor-for-all, covering conductor context and universal file resolution protocol.

hlhr202/Conductor-for-all · 533 tokens