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/ProductionMasterAI/production-master-mcpWrote 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/productionmasterai/production-master-mcp/000-project)<a href="https://agentmods.dev/rules/productionmasterai/production-master-mcp/000-project"><img src="https://agentmods.dev/badge/rules/productionmasterai/production-master-mcp/000-project/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/productionmasterai/production-master-mcp/000-project"><img src="https://agentmods.dev/badge/rules/productionmasterai/production-master-mcp/000-project.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 | $0.00284 | $0.00284 |
| Opus 5.5 | $0.00114 | $0.00114 |
| Sonnet 5.5 | $0.00057 | $0.00057 |
| Haiku 4.5 | $0.00028 | $0.00028 |
Grade A, and why
000-project 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
production-master-mcp — canonical agent policy
The single source of truth for how agents work in this repo is AGENTS.md at the
repo root. Read it before making any change.
Key points it enforces (see AGENTS.md for the full, authoritative text):
- This repo is the standalone MCP server for the Production Master hosted service —
it terminates the Model Context Protocol (Streamable HTTP
POST /mcpand stdio) and forwards tool calls upstream. All investigation logic is server-side and never lives here. - Auth is opaque bearer pass-through — never log, store, or persist a forwarded token.
- No LLM/provider SDK imports and no server-side investigation logic — CI grep-enforces both (the ip-guard job).
- Tool schemas come from the shared
@production-master/mcp-tool-contractpackage; never redefine them here. - CI runs on GitHub-hosted
ubuntu-latestonly; no secrets in code/config. - Conventional Commits,
feat/|fix/branches, squash-merge, green CI before merge.
Do not fork policy into this file — edit AGENTS.md instead.
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 · 284 tokens per session scan A 2e9f82ede390
000-project is a cursor rule published in the GitHub repository ProductionMasterAI/production-master-mcp (0 stars, last pushed today), licensed MIT. It adds 284 tokens to every session, about $0.0011 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
python
Python best practices and patterns for modern software development with Flask and SQLite.
nativescript
NativeScript best practices and patterns for mobile applications.
cursor
You are working on the checkout service. Preserve transaction integrity and auditability.
error-handling-and-validation
A code-quality guide for handling errors, invalid inputs, edge cases, preconditions, logging, and user-friendly error messages.
server-state
USE WHEN: Fetching and caching server data with TanStack Query 5: queryOptions, hooks, mutations, invalidation.
archcore-files
Enforce MCP-only operations when working with .archcore/ files.