whichrules AGENTS.md

Project-specific instructions for contributing to WhichRules, a project that shows which instructions an AI coding agent receives and where they conflict.

In plain words
What is it for?
Use them when changing WhichRules, especially when adding instruction formats or rule detectors.
Why use it?
They define the required runtime, checks, testing, offline behaviour, and evidence for detected conflicts.

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/z35068037/whichrules/agents-md
Clone the repo
git clone --depth 1 https://github.com/z35068037/whichrules

Made for: Codex, OpenCode.

Per session 76 This file is loaded in full into every session.
When invoked 76 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 $0.00076 $0.00076
Opus 5 $0.00038 $0.00038
Sonnet 5 $0.00015 $0.00015
Haiku 4.5 $0.00008 $0.00008

Measured 2d ago against content hash 195963bcf30b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

whichrules 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 2d 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 · 8 lines

What it actually says

WhichRules contributor instructions

  • Use Node.js 20 or newer and npm for local scripts.
  • Run npm run check before submitting changes.
  • Keep the CLI zero-runtime-dependency and offline by default.
  • Add a fixture and a test for every new instruction format or rule detector.
  • Do not weaken conflict evidence: every finding must include a file and line.
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. 2d ago First seen · 8 lines · 76 tokens per session scan A 195963bcf30b

Subscribe to this mod's changes

whichrules AGENTS.md is an instructions file published in the GitHub repository z35068037/whichrules (4 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session, about $0.0004 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.