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.
npx agentmods add instructions/programasweights/rules-as-programs/agents-mdgit clone --depth 1 https://github.com/programasweights/rules-as-programsWhat 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 | $0.02831 | $0.02831 |
| Opus 5 | $0.01416 | $0.01416 |
| Sonnet 5 | $0.00566 | $0.00566 |
| Haiku 4.5 | $0.00283 | $0.00283 |
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 yesterday.
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.
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 --scanfor a project-local setup (recommended). - Use
rap init --global --scanonly 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.
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.
- yesterday First seen · 234 lines · 2,831 tokens per session scan A 65af7434822d
rules-as-programs AGENTS.md is an instructions file published in the GitHub repository programasweights/rules-as-programs (4 stars, last pushed 2d ago), licensed MIT. It adds 2,831 tokens to every session, about $0.0142 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.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain 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.