Borrowing it
Nothing to install: this file belongs to ProductionMasterAI/production-master. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ProductionMasterAI/production-master/main/AGENTS.mdgit clone --depth 1 https://github.com/ProductionMasterAI/production-masterWrote 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/productionmasterai/production-master/agents-md)<a href="https://agentmods.dev/instructions/productionmasterai/production-master/agents-md"><img src="https://agentmods.dev/badge/instructions/productionmasterai/production-master/agents-md/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/instructions/productionmasterai/production-master/agents-md"><img src="https://agentmods.dev/badge/instructions/productionmasterai/production-master/agents-md.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 | $0.00505 | $0.00505 |
| Opus 5.5 | $0.00202 | $0.00202 |
| Sonnet 5.5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
production-master 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 4d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions — production-master
This repo has no CLAUDE.md; agent-capable tools that look for one (Claude
Code 2.1.277+ among them) read this file instead. The full, authoritative
rules live in .claude/rules/constraints.md
— read that before making any change. This file is the short version every
session should see up front.
The essentials
- No secrets, ever. Config comes from the environment at runtime; never
commit credentials, tokens, or
.envfiles. - No force-push to
main. All changes land through a pull request. - No unreviewed
.github/workflows/edits. Workflow changes need an explicit review on the PR. - PUBLIC-REPO SCOPE BOUNDARY (most important). This repo is the thin
client only — it talks to the hosted Production Master service over its
public HTTP interface. It must never contain pipeline/agent logic or
import an LLM/model-provider SDK of any kind. CI enforces this with an
ip-guardcheck and a no-LLM-SDK-import check; either failing fails the build. If a feature needs a provider SDK or local model logic, it belongs in the hosted service, not here. - GitHub-hosted runners only. Never add a
self-hostedrunner label to any workflow — this is public, fork-PR territory. - Host-neutral core; IDE behavior lives in adapters. Core packages make
no assumptions about a specific editor. Per-IDE behavior lives in
packages/adapter-*.
Verifying a change
Run the same gates CI does before opening a PR — the
run-production-master
skill scripts this end to end: install, build all workspaces, test, lint,
then validate install manifests. Claude Code 2.1.286+ also runs the
lighter verify skill (build, test,
lint) automatically right before every commit that isn't docs-only or
tests-only — still run run-production-master yourself before opening
the PR for the full gate.
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.
- 4d ago Changed · +4 lines · +69 tokens per session 4f3787614ebc
- 1mo ago First seen · 35 lines · 436 tokens per session scan A 2fc2d13b88c1
production-master AGENTS.md is an instructions file published in the GitHub repository ProductionMasterAI/production-master (1 stars, last pushed today), licensed MIT. It adds 505 tokens to every session, about $0.0020 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 2026-09-22.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.