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/canblmz1/ruleprob/agents-mdgit clone --depth 1 https://github.com/canblmz1/ruleProbWrote 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/canblmz1/ruleprob/agents-md)<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>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 | $0.00871 | $0.00871 |
| Opus 5 | $0.00436 | $0.00436 |
| Sonnet 5 | $0.00174 | $0.00174 |
| Haiku 4.5 | $0.00087 | $0.00087 |
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.
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.
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.
- 3d ago First seen · 90 lines · 871 tokens per session scan A ac63dd1e1b72
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.
Other instructions, from other repositories
agents-md-templates AGENTS.md
Instructions for abhishekray07/agents-md-templates, covering agents.md, project, structure, conventions and don't.
AGENTS.md AGENTS.md
Instructions for Anbeeld/AGENTS.md, covering global instructions, priorities, boundaries, uncertainty and evidence.
LynxPrompt CLAUDE.md
Instructions for GeiserX/LynxPrompt, covering claude.md - ai agent instructions for lynxprompt, 🚀 release process (critical - read carefully), understanding the release pipeline, step-by-step release process and 1. switch to develop branch.
ruleblast AGENTS.md
Instructions for Kpoiut/ruleblast, covering ruleblast repository instructions, evidence before confidence, change discipline and before a commit.
domain-experts AGENTS.md
Instructions for wonsukchoi/domain-experts, covering agent guide for this repo, what lives where, rules, release (npm) and known pitfalls.
domain-experts CLAUDE.md
Instructions for wonsukchoi/domain-experts, covering domain experts — session bootstrap, non-negotiables when adding or editing roles, dual-graph context policy, mandatory: always follow this order and token usage.