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/thedesignproject/agent-skills/create-prdnpx skills add thedesignproject/agent-skills --skill create-prdgit clone --depth 1 https://github.com/thedesignproject/agent-skillsWrote 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/thedesignproject/agent-skills/create-prd)<a href="https://agentmods.dev/skills/thedesignproject/agent-skills/create-prd"><img src="https://agentmods.dev/badge/skills/thedesignproject/agent-skills/create-prd.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 5.1 | $0.00015 | $0.01780 |
| Opus 5 | $0.00008 | $0.00890 |
| Sonnet 5 | $0.00003 | $0.00356 |
| Haiku 4.5 | $0.00002 | $0.00178 |
Grade A, and why
create-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 5d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Generator
You are a senior product manager generating a structured PRD from a feature request transcript or description. Follow these steps precisely.
Step 1: Read the Input
The user's input is in $ARGUMENTS. It can be:
- A file path — Read the file to get the transcript/description content
- Inline text — Use the text directly as the feature description
If $ARGUMENTS is empty or missing, ask the user to provide a transcript file path or feature description.
Step 2: Extract Key Elements
From the input, identify and extract:
- Problem: What problem is being discussed? Who is affected?
- Proposed solution: What solution ideas were mentioned?
- Users: Who are the target users? Any personas discussed?
- Goals/metrics: Any success metrics, KPIs, or targets mentioned?
- Risks: Any risks, concerns, or open questions flagged?
- Technical constraints: Any technical requirements, limitations, or dependencies mentioned?
- Timeline: Any deadlines or phasing discussed?
- Stakeholders: Any names, roles, or teams mentioned?
- Non-goals: Anything explicitly called out as out of scope?
Keep track of what was explicitly stated vs. what you'll need to infer or mark as [TODO].
Step 3: Research the Codebase
Search the codebase for code relevant to the feature area. This makes the Technical Scope section accurate rather than speculative.
- Use
Globto find relevant files (components, routers, modules, schema) - Use
Grepto search for related function names, model names, or feature references - Use
Readto examine key files that the feature would touch or extend
Document what you find — real file paths, module names, existing patterns that the feature should follow.
Step 4: Load Reference Materials
Read these files from the skill directory:
- Template: Read
.claude/skills/create-prd/template.md— this is the PRD structure to follow - Company context: Read
.claude/skills/create-prd/company-context.md— product and architecture reference
What ships with it
3 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.
- 5d ago First seen · 154 lines · 15 tokens per session scan A 4d56e992dd48
create-prd is a skill published in the GitHub repository thedesignproject/agent-skills (85 stars, last pushed 10d ago), licensed MIT. It adds 15 tokens to every session and 1,780 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…