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 skills add sachin0034-tech/mini-pm --skill prdgit clone --depth 1 https://github.com/sachin0034-tech/mini-pmWrote 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/sachin0034-tech/mini-pm/prd)<a href="https://agentmods.dev/skills/sachin0034-tech/mini-pm/prd"><img src="https://agentmods.dev/badge/skills/sachin0034-tech/mini-pm/prd/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sachin0034-tech/mini-pm/prd"><img src="https://agentmods.dev/badge/skills/sachin0034-tech/mini-pm/prd.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00088 | $0.03032 |
| Opus 5.5 | $0.00035 | $0.01213 |
| Sonnet 5.5 | $0.00018 | $0.00606 |
| Haiku 4.5 | $0.00009 | $0.00303 |
Grade A, and why
prd 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 1mo 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.
This is a copy
92% identical to prd-writer — 7 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Writer
Trigger
Activate on "write a PRD", "create a PRD", "draft a PRD", "PRD for [feature]", "spec out [feature]", or "one pager for [feature]".
Context
The PRD isn't dead. The bad PRD is dead. AI killed the 10-page PRD — no one read those. The modern PRD is lighter, sharper, and example-heavy.
Core philosophy:
- Think crisp, not complete. Teammates hate AI-generated bloat and crave human-written clarity. 2-3 pages max.
- PRDs are for alignment, not dictation. They drive discussion and decisions. They're what you discuss, debate, refer to, and sync on.
- A PRD engineers actually want to read nails the "why" and the "what," not the "how."
- You don't write a PRD once. You write it over time. The PRD is a living document reflecting the team's current thinking at each stage.
Behavior
Step 1: Clarify Before Writing
Before generating anything, ask 3-5 clarifying questions. Tailor to what's missing. Common gaps:
- Who specifically has this problem? (Not "users" — which users? Job title, company size, situation)
- What data do we have that this is worth solving? (Usage data, support tickets, revenue impact, customer quotes)
- What's the scope? (MVP vs full vision — and what stage is this PRD at?)
- Are there technical constraints the engineering team has flagged?
- What's the timeline and why?
Do NOT proceed until the user answers. A PRD without clear answers to these is vague and useless.
If the user is early-stage or exploring, generate a "speclet" (Stage 1) — just enough for the team to explore further. Never force a full PRD on an idea that needs discovery first.
Step 2: Determine the PRD Stage
The PRD evolves through stages. Ask or infer which stage the user is at:
| Stage | What It Is | What the PRD Looks Like |
|---|---|---|
| 1. Team Kickoff | Exploring the problem with design + eng | A "speclet" — title, problem hypothesis, 2-3 open questions. Maybe just a paragraph. |
| 2. Planning Review | Presenting to leadership for prioritization | A 1-pager: problem, strategic fit, initial data, potential approach. Audience: VP, CEO. |
| 3. XFN Kickoff | Bringing in sales, support, marketing, legal, QA | Expanded doc with cross-functional input needed. Compelling problem + initial solution direction. |
| 4. Solution Review | Staking a position on the solution | Full PRD with solution details, flows, edge cases. May be presented to senior leadership. |
| 5. Launch Readiness | Engineering handoff | Concrete specs: edge cases, metrics, user flows. Engineers comment heavily on this version. |
| 6. Impact Review | Post-launch learning | Add results link at top. What worked, what didn't, rollback notes. Closes the build-test-learn loop. |
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.
- 1mo ago First seen · 268 lines · 0 tokens per session scan A 50a0df459f09
prd is a skill published in the GitHub repository sachin0034-tech/mini-pm (4 stars, last pushed 6mo ago), licensed MIT. It adds 88 tokens to every session and 3,032 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 92% identical to prd-writer, differing in 7 lines, and is treated as a copy.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…