ruleProb AGENTS.md

ruleProb AGENTS.md is an instructions file for Codex, OpenCode from canblmz1/ruleProb. It costs 871 tokens per session, scanned A, original, MIT.

A set of instructions for RuleProbe, a command-line tool that checks whether AI assistants follow instruction files such as AGENTS.md and CLAUDE.md. It creates test situations, runs them through AI providers, and scores the results.

In plain words
What is it for?
Use it when developing, testing, comparing, or diagnosing RuleProbe, including its rule extraction and scoring features.
Why use it?
It prevents contributors from treating RuleProbe like a general AI playground or code linter. It also records the required commands and checks for reliable changes.

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/canblmz1/ruleprob/agents-md
Clone the repo
git clone --depth 1 https://github.com/canblmz1/ruleProb

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.

agentmods badge for ruleProb AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/canblmz1/ruleprob/agents-md.svg)](https://agentmods.dev/instructions/canblmz1/ruleprob/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/canblmz1/ruleprob/agents-md"><img src="https://agentmods.dev/badge/instructions/canblmz1/ruleprob/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 871 This file is loaded in full into every session.
When invoked 871 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 $0.00871 $0.00871
Opus 5 $0.00436 $0.00436
Sonnet 5 $0.00174 $0.00174
Haiku 4.5 $0.00087 $0.00087

Measured 3d ago against content hash ac63dd1e1b72, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ruleProb 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 · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — RuleProbe

Project

RuleProbe is a CLI that extracts rules from AI instruction files (CLAUDE.md, AGENTS.md, .cursor/rules, etc.), generates sandbox scenarios, runs AI providers against them, and scores compliance. It is not a generic LLM playground, linter, or greenfield project.

Maturity: stable core; AI-assisted and hybrid extraction are brittle.

Commands

pnpm install          # always pnpm, never npm/yarn
pnpm build            # tsup — ESM + DTS, two entry points
pnpm typecheck        # tsc --noEmit
pnpm test             # vitest run (15s timeout, globals enabled)

pnpm dev <cmd>        # tsx src/cli/index.ts <cmd>
pnpm dev benchmark --fixtures-only
pnpm dev run examples/basic --provider mock
pnpm dev list-rules examples/basic
pnpm dev doctor       # local diagnostics
pnpm dev compare . --provider mock   # deterministic vs hybrid diff

CI order: install -> build -> typecheck -> test -> benchmark -> smoke tests.

Architecture

Layer Path
CLI entry src/cli/index.ts
Config loading src/config/load.ts
Deterministic extraction src/rules/extract.ts
AI/hybrid extraction src/extractors/aiAssisted.ts
Scenario generation src/scenarios/generate.ts
Providers src/providers/*
Evaluation src/evaluator/score.ts
Reporting src/reporters/* (json, md, html)
Types src/types/index.ts

Two tsup entry points: src/cli/index.ts -> dist/cli/index.js (CLI bin), src/index.ts -> dist/index.js (library export).

Providers

Provider Extraction Runtime Needs key?
mock no simulated no
dry-run no none no
gemini yes sandbox bridge yes (GEMINI_API_KEY)
openrouter yes sandbox bridge yes (OPENROUTER_API_KEY)
opencode-go yes experimental bridge yes (OPENCODE_GO_API_KEY)
claude-code no real local CLI yes (local install)

API keys: copy .env.example to .env and fill in. Mock and dry-run work without keys.

Read the full file on GitHub · 90 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 · 90 lines · 871 tokens per session scan A ac63dd1e1b72

Subscribe to this mod's changes

ruleProb AGENTS.md is an instructions file published in the GitHub repository canblmz1/ruleProb (7 stars, last pushed 3mo ago), licensed MIT. It adds 871 tokens to every session, about $0.0044 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.