machinery AGENTS.md

machinery AGENTS.md is an instructions file for Codex, OpenCode from openzot/machinery. It costs 3,115 tokens per session, scanned A, original, MIT.

Repository instructions for Machinery, a demonstration software factory that builds interactive control panels for simulated machines and publishes them as web pages.

In plain words
What is it for?
Use them when creating or editing a machine’s panel, simulation, faults, manual, styles, behaviour, catalogue entry, or publication files.
Why use it?
They explain the project’s structure and the checks needed before changing a machine, including reviewing the available shelf and design brief.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/openzot/machinery/agents-md
Clone the repo
git clone --depth 1 https://github.com/openzot/machinery

Made for: Codex, OpenCode.

Per session 3,115 This file is loaded in full into every session.
When invoked 3,115 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.03115 $0.03115
Opus 5 $0.01558 $0.01558
Sonnet 5 $0.00623 $0.00623
Haiku 4.5 $0.00312 $0.00312

Measured 3d ago against content hash 7e6f4b5daa34, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

AGENTS.md · 234 lines

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.

  • node v22 and python3. There is no package.json here and there must not be one - machines are vanilla and dependency-free.
  • Playwright with headless Chromium. require('playwright') resolves from any directory. scripts/probe.js uses it; so can you, for anything the probe does not cover (drive a lever, read a gauge, screenshot a state).
  • The view tool. 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.

Read the full file on GitHub · 234 lines

Changes

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.

  1. 3d ago First seen · 234 lines · 3,115 tokens per session scan A 7e6f4b5daa34

Subscribe to this mod's changes

machinery AGENTS.md is an instructions file published in the GitHub repository openzot/machinery (5 stars, last pushed 3d ago), licensed MIT. It adds 3,115 tokens to every session, about $0.0156 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.