What is rules-as-programs AGENTS.md?

A setup guide for Rules as Programs, which turns written instructions for a coding agent into separate Python checks. The checks watch the agent's reasoning and actions for rule violations and report them without blocking work.

Use it when adding rule monitoring to a project, translating natural-language agent rules into checks, or reviewing reported violations.

It makes it easier to install, initialize, convert existing project rules, and verify that the checks are working.

How programasweights/rules-as-programs configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to programasweights/rules-as-programs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/programasweights/rules-as-programs/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/programasweights/rules-as-programs

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/programasweights/rules-as-programs/agents-md/github.svg)](https://agentmods.dev/instructions/programasweights/rules-as-programs/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/programasweights/rules-as-programs/agents-md"><img src="https://agentmods.dev/badge/instructions/programasweights/rules-as-programs/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/programasweights/rules-as-programs/agents-md"><img src="https://agentmods.dev/badge/instructions/programasweights/rules-as-programs/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,831 This file is loaded in full into every session.

When invoked 2,831 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02831	$0.02831
Opus 5.5	$0.01132	$0.01132
Sonnet 5.5	$0.00566	$0.00566
Haiku 4.5	$0.00283	$0.00283

Measured 2mo ago against content hash 65af7434822d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rules-as-programs 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.

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.

Rules as Programs — setup guide for coding agents

You are helping a user add Rules as Programs to their existing Codex project. Rules as Programs turns each agent rule into an independent Python function (PAW-backed for fuzzy judgment) that audits the agent's reasoning and actions and reports violations. v1 is non-blocking (observability only). macOS has the full native menu-bar inbox and Rule Editor; Linux and Windows use a reduced tray menu. Follow these steps.

1. Install the package

Run in the project root:

python -m pip install "git+https://github.com/programasweights/rules-as-programs.git" \
  --extra-index-url https://pypi.programasweights.com/simple/

This installs Rules as Programs directly from GitHub. It also installs ProgramAsWeights (programasweights), which compiles each rule's natural-language spec into a small local neural program. The ProgramAsWeights package index supplies prebuilt llama-cpp-python wheels for local inference; it does not host Rules as Programs. For an isolated CLI installation, the equivalent pipx form is:

pipx install "git+https://github.com/programasweights/rules-as-programs.git" \
  --pip-args="--extra-index-url https://pypi.programasweights.com/simple/"

Python 3.10 or newer is required. Use an environment that will remain available because the hook and login-autostart entry retain its interpreter path.

2. Initialize

rap init --scan

This installs the Codex hook (.codex/hooks.json + .codex/hooks/rap-hook.sh), scaffolds the built-in rule programs (.py) into .codex/rules-as-programs/rules/, drafts rule programs from any existing prose rules it finds (--scan), and launches the daemon + menu-bar item.

Prefer rap init --scan for a project-local setup (recommended).
Use rap init --global --scan only if the user wants the rules to apply to all their projects (writes to $CODEX_HOME, normally ~/.codex/).
Restart Codex, open /hooks, and review and trust the RAP hook definitions. Codex skips new or changed non-managed hooks until their exact hash is trusted.

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.

2mo ago First seen · 234 lines · 2,831 tokens per session scan A 65af7434822d

Subscribe to this mod's changes

rules-as-programs AGENTS.md is an instructions file published in the GitHub repository programasweights/rules-as-programs (9 stars, last pushed 13d ago), licensed MIT. It adds 2,831 tokens to every session, about $0.0113 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.

Building agents

rules-as-programs AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
rules-as-programs AGENTS.mdprogramasweights/rules-as-programs	Instructions file	9	13d ago	MIT	A	2,831	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
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

rules-as-programs: Instructions file for Codex