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 skills/hculap/better-code/prd-readme-standardnpx skills add hculap/better-code --skill prd-readme-standardgit clone --depth 1 https://github.com/hculap/better-codeWrote 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/skills/hculap/better-code/prd-readme-standard)<a href="https://agentmods.dev/skills/hculap/better-code/prd-readme-standard"><img src="https://agentmods.dev/badge/skills/hculap/better-code/prd-readme-standard.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 | $0.00084 | $0.01559 |
| Opus 5 | $0.00042 | $0.00779 |
| Sonnet 5 | $0.00017 | $0.00312 |
| Haiku 4.5 | $0.00008 | $0.00156 |
Grade A, and why
PRD-README v1 Standard 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD-README v1 Standard
Product-Ready Documentation README standard for creating documentation that reliably produces correct adoption decisions, fast first success, low support burden, sustained trust, and low drift.
Core Definition
A README is "perfect" when it achieves:
- Correct adoption decision - Reader quickly knows if project fits their needs
- Fast first success - Copy/paste path to working result in under 5 minutes
- Low support burden - Answers top questions upfront
- Sustained trust - Clear status and quality signals
- Low drift - Stays accurate via process/automation
The 9-Step Build Process
Follow these steps in order when creating or improving a README.
Step 0: Specify Target Reader and Job-to-be-Done
Before writing any README content, define these three lines:
Primary user: [e.g., "Python developer who wants an HTTP client library"]
Primary job: [e.g., "install → call API → handle auth"]
Success in 5 minutes: [e.g., "send one request and see JSON response"]
Failure to define these results in either a manifesto or an API dump.
Step 1: Engineer the Top Section (Above the Fold)
Goal: 15-30 seconds to decide whether to continue reading.
Include in this exact order:
# ProjectName- One-sentence value proposition: what it does + for whom + differentiator
- Status line (mandatory):
Status: active | beta | stable | deprecated | unmaintained - Primary links: docs, releases/changelog, issues/discussions/support
- Badges (optional, limited): only build, version, license
- One visual if product is visual (screenshot/GIF)
Rules:
- If first screen is 70% badges → conversion problem
- If status is unclear → trust problem
Step 2: Provide Executable Quickstart
Goal: First working result in under 5 minutes (TTFS - Time To First Success).
Quickstart must contain:
- Prerequisites (explicit versions)
- Install (one-liner if possible)
- Run/Use (minimal example)
- Expected output or "what success looks like"
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 219 lines · 84 tokens per session scan A 4158eef1d359
PRD-README v1 Standard is a skill published in the GitHub repository hculap/better-code (2 stars, last pushed 7mo ago), licensed MIT. It adds 84 tokens to every session and 1,559 once invoked, 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.
Other skills, from other repositories
golden-jupyter-dir
Use when testing the goldenjupyterdir golden build.
golden-man-kw
Use when testing the man golden build.
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
golden-chat-topics
Use when testing the goldenchattopics golden build.
golden-chat-single
Use when testing the goldenchatsingle golden build.
golden-rss-empty
Use when testing the empty rss golden build.