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/he-yufeng/ruleforge/agents-mdgit clone --depth 1 https://github.com/he-yufeng/RuleForgeWrote 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/he-yufeng/ruleforge/agents-md)<a href="https://agentmods.dev/instructions/he-yufeng/ruleforge/agents-md"><img src="https://agentmods.dev/badge/instructions/he-yufeng/ruleforge/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 | $0.00251 | $0.00251 |
| Opus 5 | $0.00125 | $0.00125 |
| Sonnet 5 | $0.00050 | $0.00050 |
| Haiku 4.5 | $0.00025 | $0.00025 |
Grade A, and why
RuleForge 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.
What it actually says
AGENTS.md
RuleForge is a small Python CLI that scans a repository and generates assistant rule files such as CLAUDE.md, .cursorrules, and .github/copilot-instructions.md.
Commands
- Install locally with
pip install -e ".[dev]" - Run tests with
python -m pytest -q - Run lint with
python -m ruff check . - Build packages with
python -m build - Smoke-test the CLI with
python -m ruleforge.cli scan .andpython -m ruleforge.cli audit .
Boundaries
- Keep generated rule text concise and project-specific. Generic agent advice is not useful here.
- Do not commit
dist/, cache directories, virtualenvs, or local test databases. - Do not add secrets, tokens,
.envvalues, or machine-specific paths to docs or tests. - Keep CLI behavior scriptable. New commands should have a plain output path or JSON mode when practical.
Style
- Prefer small, readable helpers over large templates with hidden behavior.
- Add tests for detection, generation, and CLI output when changing user-facing behavior.
- Keep README examples aligned with the actual CLI.
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 · 25 lines · 251 tokens per session scan A c8fef26e4ef4
RuleForge AGENTS.md is an instructions file published in the GitHub repository he-yufeng/RuleForge (8 stars, last pushed 10d ago), licensed MIT. It adds 251 tokens to every session, about $0.0013 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
mcp-server-tree-sitter AGENTS.md
Instructions for wrale/mcp-server-tree-sitter, covering agents.md, project overview, setup, before committing and key architecture.
ScalaSemantic AGENTS.md
Instructions for MercurieVV/ScalaSemantic, covering agents.md instructions and quick start.
codeTree CLAUDE.md
Instructions for ThinkyMiner/codeTree, covering claude.md, what this is, structural analysis tools (13), graph & onboarding tools (10) and supported languages.
TechDebtMCP copilot-instructions.md
Instructions for PierreJanineh/TechDebtMCP, covering ai agent instructions for tech debt mcp, project overview, architecture, copilot pr review workflow and before creating a pr.
discoclaw CLAUDE.md
Instructions for DiscoClaw/discoclaw, covering discoclaw, safety, context loading (strict), identity and workspace file ownership.
nextjs-skills CLAUDE.md
Instructions for mohamed-hossam1/nextjs-skills: All contribution rules — style, naming, file layout, verification — live in AGENTS.md. Read that first.