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.
git clone --depth 1 https://github.com/mrzroot/agentforgeWrote 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/rules/mrzroot/agentforge/project-rules)<a href="https://agentmods.dev/rules/mrzroot/agentforge/project-rules"><img src="https://agentmods.dev/badge/rules/mrzroot/agentforge/project-rules/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/mrzroot/agentforge/project-rules"><img src="https://agentmods.dev/badge/rules/mrzroot/agentforge/project-rules.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00215 | $0.00215 |
| Opus 5.5 | $0.00086 | $0.00086 |
| Sonnet 5.5 | $0.00043 | $0.00043 |
| Haiku 4.5 | $0.00021 | $0.00021 |
Grade A, and why
project-rules 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 1mo 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
agentforge Development Guidelines
1. Core Principles
- 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.
2. Architecture & Patterns
- Keep modules focused, decoupled, and single-responsibility.
- Colocate tests, types, and documentation with the corresponding modules.
3. Security Requirements
- 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.
4. Testing Protocols
- Ensure all new features, edge cases, and bug fixes have automated test coverage.
- Keep tests deterministic, isolated, and fast.
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.
- 1mo ago First seen · 26 lines · 215 tokens per session scan A acebc1709edd
project-rules is a cursor rule published in the GitHub repository mrzroot/agentforge (3 stars, last pushed 7d ago), licensed MIT. It adds 215 tokens to every session, about $0.0009 per session on Opus 5.5. 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 cursor rules, from other repositories
bootstrap-alwayson
Minimal always-required LLM fixes.
read-xlsx
Reading, writing, diffing, and repairing spreadsheets (.xlsx) for AI agents via the xfa MCP server.
ui-components
USE WHEN: Building UI components, structuring layouts, and applying styles using Tailwind CSS.
fastapi
FastAPI best practices with Pydantic v2, async patterns, and dependency injection.
head-of-product
Head of Product persona — planning, user stories, UX decisions, scope guardian. Use when discussing product strategy, PRDs, user research, feature proposals, or backlog prioritization.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.