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 kensaurus/cursor-kenji --skill design-prdgit clone --depth 1 https://github.com/kensaurus/cursor-kenjiWrote 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/kensaurus/cursor-kenji/design-prd)<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/design-prd"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/design-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/kensaurus/cursor-kenji/design-prd"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/design-prd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.02975 |
| Opus 5 | $0.00019 | $0.01488 |
| Sonnet 5 | $0.00008 | $0.00595 |
| Haiku 4.5 | $0.00004 | $0.00298 |
Grade A, and why
design-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 — 450 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate PRD Skill
Degree of freedom: MIXED. Clarifying questions, scope, and requirements
[HIGH freedom]; stack/feature/schema detection [LOW freedom — run exactly].
Create detailed, actionable Product Requirements Documents through structured conversation, informed by codebase analysis and competitive research.
How to reason
- Discover — stack, features, schema, existing PRDs
- Clarify — 3–5 numbered questions with lettered options
- Scope — P0/P1/P2 plus explicit non-goals
- Specify — testable requirements, not implementation
Worked example
Discover: Next.js + Supabase;
notificationstable missing; noprd-*.md. Clarify: in-app vs email vs push? (user: 1A in-app only). MVP vs polish? (2A MVP). Scope: P0 in-app bell + read state; non-goal: email/push (design-email/mobile-capacitor-platform). Specify: FR-1 "unread count on the header within 2s of insert" — not "feel realtime".
Self-critique before reporting
- Context recorded — stack, features, schema, and existing PRDs were listed first
- Questions capped — 3–5, lettered; coding did not start first
- Testable FRs — no "should be fast" without a number
- Right owner — ready to implement →
workflow-build-feature; UI from scratch →design-frontend; RLS matrix →plan-rls-audit
Step 0: Auto-Detect Project Context [LOW freedom — run exactly]
Before writing any PRD, understand the project from its source code.
0a. Detect Tech Stack
Read package.json (or equivalent) to extract:
- Framework: Next.js, Remix, SvelteKit, Nuxt, Django, Rails, etc.
- UI library: React, Vue, Svelte, Angular
- Database: Supabase, Prisma, Drizzle, raw SQL
- Auth: Supabase Auth, NextAuth, Clerk, Auth0
- State management: TanStack Query, Zustand, Redux, Pinia
- CSS: Tailwind, CSS Modules, Styled Components
0b. Discover Existing Features
Glob: **/app/**/page.tsx → Next.js routes (features)
Glob: **/features/*/ → Feature directories
Glob: **/src/routes/**/*.tsx → Route-based features
Grep: pattern "export default" glob "**/page.tsx" output_mode "files_with_matches"
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 · 450 lines · 39 tokens per session scan A 0b5376d6ccd5
design-prd is a skill published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 10d ago), licensed MIT. It adds 39 tokens to every session and 2,975 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
comprehensive-enrichment
Enrich any person or company from any identifier — email, name, LinkedIn URL, domain, company name, Twitter/X handle. Use when asked to enrich, look up, or research a lead, contact, person, or company.
paid-channel-prioritizer
For founders who don't know where to start with paid ads. Analyzes ICP, competitor ad presence, budget constraints, and product type to recommend which 1-2 paid channels to start with and provides a 90-day ramp plan. Prevents the common mistake of spreading a small budget across too many platforms.
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
email-finder-hunter
Email finder and verifier - find emails, verify deliverability, discover companies.
lead-discovery
Orchestrator that runs first for lead generation requests. Gathers business context via website analysis or questions, identifies competitors, builds ICP, and routes to signal skills with pre-filled inputs.
render-mosaic-grid-reveal
Render a 'mosaic-grid-reveal' video from a config — a real-DOM FULL-BLEED N×N mosaic of real product tiles that pops in one tile at a time (scatter order, ease-out-back overshoot), the grid clears, then the brand wordmark builds line-by-line followed by a sub-label, tagline, and CTA; frame-stepped via Playwright and…