Borrowing it
Nothing to install: this file belongs to openzot/machinery. 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/openzot/machinery/main/AGENTS.mdgit clone --depth 1 https://github.com/openzot/machineryWrote 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/openzot/machinery/agents-md)<a href="https://agentmods.dev/instructions/openzot/machinery/agents-md"><img src="https://agentmods.dev/badge/instructions/openzot/machinery/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/openzot/machinery/agents-md"><img src="https://agentmods.dev/badge/instructions/openzot/machinery/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 | $0.03115 | $0.03115 |
| Opus 5.5 | $0.01246 | $0.01246 |
| Sonnet 5.5 | $0.00623 | $0.00623 |
| Haiku 4.5 | $0.00312 | $0.00312 |
Grade A, and why
machinery 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 2mo 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The machinery
This repository is a demonstration: a software factory that ships one working
machine every shift, unattended. You are the factory. Each run of
orders/new-machine.yaml is one shift; the workflow commits whatever you leave
in the working tree and publishes site/ to GitHub Pages.
A machine is a control panel for something that does not exist - a lunar regolith refinery, a 1960s telephone exchange, a kelp harvester on the sea floor - with a live simulation behind it, faults you can trigger and recover from, and the manual that teaches you to run it. The panel is the product. It is judged by looking at it, and you will look at it before you are done.
Layout
site/
index.html the catalogue page (reads machines.json; do not edit)
machines.json the catalogue - one entry per machine, append only
machines/<slug>/
index.html the panel: structure only - links machine.css, loads machine.js
machine.css every rule the panel and the manual need
machine.js every line of behaviour; exposes window.machine
manual.html the operating manual, in the machine's own design
scripts/check.sh validates the catalogue (static); must exit 0 before a shift ends
scripts/probe.sh commissions the newest machine in a browser (dynamic); must exit 0 too
scripts/probe.js what probe.sh runs; also takes the screenshots you look at
orders/new-machine.yaml the standing order you are running
What is on the machine
No need to go looking: the shift installs the toolbox before you start.
nodev22 andpython3. There is nopackage.jsonhere and there must not be one - machines are vanilla and dependency-free.- Playwright with headless Chromium.
require('playwright')resolves from any directory.scripts/probe.jsuses it; so can you, for anything the probe does not cover (drive a lever, read a gauge, screenshot a state). - The
viewtool. You can look at images. The probe writes PNGs to/tmp/machinery/; view them. This is not optional - a panel is a visual object and the order requires you to look at it and change it in response. prettier --check index.html machine.css machine.js manual.html,htmlhint index.html manual.html,quick-lint-js machine.js,node --check machine.js. Point the linter straight at the file.
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.
- 2mo ago First seen · 234 lines · 3,115 tokens per session scan A 7e6f4b5daa34
machinery AGENTS.md is an instructions file published in the GitHub repository openzot/machinery (5 stars, last pushed 26d ago), licensed MIT. It adds 3,115 tokens to every session, about $0.0125 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.
machinery AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| machinery AGENTS.mdopenzot/machinery | Instructions file | 5 | 26d ago | MIT | A | 3,115 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |