agentmods.dev

write-prd

A workflow for creating a product requirements document, or PRD—a written plan describing a feature and how it should work—in ChatPRD.

In plain words
What is it for?
Use it to inspect a codebase, choose a ChatPRD project and template, draft feature requirements, and save a local copy.
Why use it?
It turns codebase context and a feature idea into organized requirements, user stories, technical details, edge cases, and open questions.

Skill for Claude CodeCodex

5 6mo ago A scan 37 tokens original MIT
View the source file ChatPRD/cursor-plugin
Install

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.

agentmods
npx agentmods add skills/chatprd/cursor-plugin/write-prd
Any agent
npx skills add ChatPRD/cursor-plugin --skill write-prd
Clone the repo
git clone --depth 1 https://github.com/ChatPRD/cursor-plugin

Made for: Claude Code, Codex.

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 494 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00037 $0.00494
Opus 5 $0.00018 $0.00247
Sonnet 5 $0.00007 $0.00099
Haiku 4.5 $0.00004 $0.00049

Measured yesterday against content hash 2bd32899cb2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write-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 yesterday.

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.

skills/write-prd/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write a PRD

Trigger

User wants to create a product requirements document for a feature, with context from the current codebase.

Workflow

  1. Ask the user what feature or change they want to spec out.
  2. Explore the codebase to understand relevant context:
    • Existing data models and schema
    • Related components, routes, and API endpoints
    • Current patterns and conventions
  3. List the user's ChatPRD projects using list_projects and ask which project this PRD belongs to (or skip if none).
  4. Pick the right template:
    • List available templates using list_templates.
    • Use the user's default template if they have one set.
    • Otherwise use the default PRD template.
    • If multiple templates could fit (e.g., a "Technical Spec" vs "Feature PRD"), ask the user which to use.
  5. Draft an outline with sections tailored to the feature:
    • Problem statement and goals
    • User stories and acceptance criteria
    • Technical context (from codebase analysis)
    • Edge cases and error states
    • Open questions
  6. Create the document in ChatPRD using create_document with the outline and selected template.
  7. Save a local copy of the PRD as a markdown file in the prd/ directory at the project root (create the directory if it doesn't exist). Name the file using the document title in kebab-case (e.g., prd/user-authentication.md). This gives the team local access to specs for reference during development.
  8. Share the ChatPRD document link and local file path with the user.

Guardrails

  • Ground the PRD in actual codebase context, not generic boilerplate.
  • Include specific file paths and existing patterns when describing technical context.
  • Keep scope focused — one feature per PRD.
  • Flag unknowns as open questions rather than making assumptions.
  • The prd/ directory should be committed to the repo so the whole team has specs alongside the code.

Output

  • PRD created in ChatPRD with document link
  • Local copy saved to prd/ directory
  • Summary of what was included

Read the full file on GitHub · 48 lines

Changes

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.

  1. yesterday First seen · 48 lines · 37 tokens per session scan A 2bd32899cb2b

Subscribe to this mod's changes

write-prd is a skill published in the GitHub repository ChatPRD/cursor-plugin (5 stars, last pushed 6mo ago), licensed MIT. It adds 37 tokens to every session and 494 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 2026-08-31.

DocumentsPlanningWriting and docs
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens