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/coffeecheese/easy-prd-testing/agents-mdgit clone --depth 1 https://github.com/CoffeeCheese/easy-prd-testingWrote 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/coffeecheese/easy-prd-testing/agents-md)<a href="https://agentmods.dev/instructions/coffeecheese/easy-prd-testing/agents-md"><img src="https://agentmods.dev/badge/instructions/coffeecheese/easy-prd-testing/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 | $0.00620 | $0.00620 |
| Opus 5 | $0.00310 | $0.00310 |
| Sonnet 5 | $0.00124 | $0.00124 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
easy-prd-testing 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
This repository is a Codex plugin for PRD/prototype-driven automation testing.
.codex-plugin/plugin.jsondefines plugin metadata and points Codex to./skills/.skills/contains the runnable skill modules. Keep eachSKILL.mdfocused on one workflow stage.skills/*/templates/contains stage-specific Markdown templates used by the helper scripts and agents.scripts/contains local validation and scaffolding helpers.docs/contains public contributor-facing workflow, artifact, and agent protocol docs for this project only.docs/superpowers/anddocs/external-plugins/are intentionally ignored and must not be committed.
Build, Test, and Development Commands
Run these from the repository root:
scripts/validate-plugin.sh
Validates plugin metadata, skill files, templates, and public docs.
bash -n scripts/validate-plugin.sh scripts/scaffold-testing-docs.sh
Checks shell syntax.
scripts/scaffold-testing-docs.sh "/tmp/easy-prd-output" "订单管理"
Generates a sample testing artifact tree under <output-root>/easy-prd-testing/testing/<module-name>/.
Coding Style & Naming Conventions
Use Markdown for skills, templates, and docs. Keep headings descriptive and action-oriented. Shell scripts should use #!/usr/bin/env bash and set -euo pipefail when they perform filesystem operations. Prefer explicit paths and stable filenames such as 01-模块拆解.md, 05-执行记录.md, and 06-缺陷记录.md.
Testing Guidelines
There is no separate unit test framework. Treat scripts/validate-plugin.sh as the baseline test. For scaffold changes, verify missing-argument handling, directory creation, and no-overwrite behavior. Do not use browser, MCP, or Playwright during repository validation unless a future task explicitly requires it.
Commit & Pull Request Guidelines
Follow Conventional Commits, as in the existing history:
feat: add testing artifact scaffold scriptfix: align plugin default prompts with manifest schemadocs: align artifact templates with workflow contractchore: ignore superpowers planning docs
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 · 58 lines · 620 tokens per session scan A c6bca1006606
easy-prd-testing AGENTS.md is an instructions file published in the GitHub repository CoffeeCheese/easy-prd-testing (2 stars, last pushed 22d ago), licensed MIT. It adds 620 tokens to every session, about $0.0031 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
spec-kit AGENTS.md
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.
playwriter AGENTS.md
Instructions for remorses/playwriter, covering backward compatibility, architecture, development, running mcp locally and running cli locally.
playwright-rust CLAUDE.md
Instructions for padamson/playwright-rust, covering claude.md, project, repository layout, skills (procedural reference) and documentation hierarchy.
sveltest AGENTS.md
AGENTS.md instructions for spences10/sveltest, covering agents.md, unbreakable rules, essential commands, development and testing.
react-redux-boilerplate AGENTS.md
AGENTS.md instructions for marcoturi/react-redux-boilerplate, covering agents.md, project overview, setup commands, testing and linting, formatting, and type checking.
clearcote-browser AGENTS.md
Instructions for clearcotelabs/clearcote-browser, covering agents.md — guide for contributors (human and automated), what this project is, repository layout, conventions and common commands.