00-agents-md

A set of repository rules that tells coding agents to read the root AGENTS.md file first and use other rule files only as path-specific additions.

In plain words
What is it for?
Use it to establish which project rules take priority, report contradictions, and keep editor-specific rule files aligned with canonical sources.
Why use it?
It prevents agents from following conflicting instructions or treating copied editor rules as the main authority.

Cursor rule for Cursor

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 rules/commerce-atoms/agents/00-agents-md
Clone the repo
git clone --depth 1 https://github.com/commerce-atoms/agents

Made for: Cursor.

Per session 211 This file is loaded in full into every session.
When invoked 211 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 $0.00211 $0.00211
Opus 5 $0.00105 $0.00105
Sonnet 5 $0.00042 $0.00042
Haiku 4.5 $0.00021 $0.00021

Measured 2d ago against content hash 5cccab828323, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

00-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.

kit/.cursor/rules/00-agents-md.mdc · 11 lines

What it actually says

ALWAYS read AGENTS.md at the repo root for the canonical rules. This .cursor/rules/ directory contains path-scoped overlays that complement AGENTS.md — they do not replace it.

If a rule appears here and not in AGENTS.md, treat it as a path-specific extension. If a rule contradicts AGENTS.md, treat AGENTS.md as authoritative and surface the contradiction so it can be resolved at the canonical source.

Per-tool overlay files (.cursor/rules/*.mdc, copilot-instructions.md, CLAUDE.md) are hand-maintained mirrors of the canonical sources in rules/core/*.md. Edit the canonical source first; the overlays are kept in sync by the maintainer. Generation from canonical sources is a planned future step (ADR 001).

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 · 11 lines · 211 tokens per session scan A 5cccab828323

Subscribe to this mod's changes

00-agents-md is a cursor rule published in the GitHub repository commerce-atoms/agents (1 stars, last pushed 4mo ago), licensed MIT. It adds 211 tokens to every session, about $0.0011 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.