write-prd

write-prd is a skill for Claude Code, Codex from shaan-ad/pm-os. It costs 42 tokens per session (1,073 once invoked), scanned A, original, MIT.

A guided process for creating a product requirements document, or PRD: a written plan explaining what a product feature should do and how its launch will be measured. It gathers context, user stories, testable Given/When/Then criteria, metrics, and a launch plan.

In plain words
What is it for?
Use it to develop a feature idea into a complete PRD, using project context, strategy, objectives, and a standard document template.
Why use it?
It turns an initial feature idea into a specification that product and engineering teams can act on. The guided questions help expose missing information about users, goals, constraints, and success.

Skill for Claude CodeCodex

Part of the pm-os plugin — 27 skills, 1 hook shipped together

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/shaan-ad/pm-os/write-prd
Any agent
npx skills add shaan-ad/pm-os --skill write-prd
Clone the repo
git clone --depth 1 https://github.com/shaan-ad/pm-os

Made for: Claude Code, Codex.

Or install pm-os, the plugin that ships this one along with the rest of its 27 skills, 1 hook.

Wrote 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.

agentmods badge for write-prd

README.md
[![agentmods](https://agentmods.dev/badge/skills/shaan-ad/pm-os/write-prd.svg)](https://agentmods.dev/skills/shaan-ad/pm-os/write-prd)
Your own site
<a href="https://agentmods.dev/skills/shaan-ad/pm-os/write-prd"><img src="https://agentmods.dev/badge/skills/shaan-ad/pm-os/write-prd.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,073 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 $0.00042 $0.01073
Opus 5 $0.00021 $0.00536
Sonnet 5 $0.00008 $0.00215
Haiku 4.5 $0.00004 $0.00107

Measured 4d ago against content hash 52852d1eb1bf, 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 4d 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.

skills/write-prd/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write PRD

You are a senior product manager generating a Product Requirements Document. You combine user insight, strategic context, and (when available) technical awareness to produce specs that engineers can build from immediately.

Inputs

  • Argument: If the user passed an argument, treat it as the feature name or description.
  • knowledge/pm-context.md: Central product context. Always read first.
  • knowledge/strategy.md: Product strategy and vision. Read for alignment.
  • knowledge/okrs.md: Current OKRs. Read for goal alignment.
  • references/prd-template.md: PRD structure template. Read for output format.

Workflow

Step 1: Understand the Feature

If the user provided an argument, acknowledge it and move to clarifying questions. Otherwise ask:

What feature are you thinking about? Give me a sentence or two.

Step 2: Clarifying Questions

Ask 5-7 targeted questions. Present them all at once so the user can answer in a single pass:

  1. Target user: Who specifically will use this? (persona, segment, role)
  2. Problem: What problem does this solve for them? What pain are they experiencing?
  3. Current workaround: How do they solve this today? What's broken about that?
  4. Success definition: What does success look like? How would we measure it?
  5. Constraints: Any hard constraints? (timeline, tech debt, compliance, dependencies)
  6. Scope boundary: What is explicitly NOT in scope for v1?
  7. Prior art: Any competitor implementations or internal references worth looking at?

Wait for the user's answers before proceeding.

Step 3: Gather Context

Read context files from the user's knowledge directory:

Read knowledge/pm-context.md
Read knowledge/strategy.md (if it exists)
Read knowledge/okrs.md (if it exists)

Note which OKRs this feature supports. Flag if the feature does not clearly align with any stated goal.

Step 4: Codebase Analysis (if applicable)

Check if the current working directory contains a codebase (look for package.json, Cargo.toml, go.mod, pyproject.toml, or src/ directories).

Read the full file on GitHub · 116 lines

Files

What ships with it

1 file 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.

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. 4d ago First seen · 116 lines · 42 tokens per session scan A 52852d1eb1bf

Subscribe to this mod's changes

write-prd is a skill published in the GitHub repository shaan-ad/pm-os (31 stars, last pushed 5mo ago), licensed MIT. It adds 42 tokens to every session and 1,073 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 2026-08-30.

Related

Other skills, from other repositories

kimchi

Turn a raw product idea into build-ready docs — one doc per EPIC with locked decisions, exact API contracts, a story-by-story priority plan, and an execute.md handoff Claude can build from across sessions. Gets the clarity by interrogating the user through a roster of expert personas that grill, counter, and refuse to…

chitransh-cj/kimchi · 122 tokens

alive:demo

Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.

alivecontext/alive · 52 tokens

alive:session-history

Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…

alivecontext/alive · 76 tokens

alive:world

The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.

alivecontext/alive · 63 tokens

alive-people

Weekly -- cross-reference people mentions, nudge stale contacts.

alivecontext/alive · 15 tokens

alive-search

Search across all walnuts -- decisions, people, files, references, insights, log history.

alivecontext/alive · 20 tokens