make-prd

A requirements-writing tool that turns a product idea into a structured model of features, relationships, and facts. It saves the result as a Product Requirements Document, or PRD, for later implementation planning.

In plain words
What is it for?
Use it to model requirements and produce a versioned PRD in the project's design directory.
Why use it?
It creates a traceable link between what a product should do and the plan for building it.

Skill for Claude CodeCodex

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/context4ai/workflow/make-prd
Any agent
npx skills add context4ai/workflow --skill make-prd
Clone the repo
git clone --depth 1 https://github.com/context4ai/workflow

Made for: Claude Code, Codex.

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,025 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00039 $0.05025
Opus 5 $0.00019 $0.02513
Sonnet 5 $0.00008 $0.01005
Haiku 4.5 $0.00004 $0.00502

Measured yesterday against content hash da008429dc7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

make-prd scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- ❌ "curl API returns correct JSON" -- API call is not an interface behavior; describe what the user sees in the interface instead
skills/make-prd/SKILL.md · 402 lines

How it starts

The opening of the file, as written. The whole thing — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/make-prd - Product Requirements Modeling (Product-Layer Graph)

Model requirement descriptions as a Product-layer Node / Edge / Fact knowledge graph.

Design Workspace (design-dir)

The default workspace for design documents is design/. When the Agent starts, check:

  1. design/ directory exists -> use design/ as <design-dir>
  2. design/ does not exist -> pause and ask the user for the design workspace path, explaining the accepted directory structure:
    <design-dir>/<version>/(prd|plan).md
    Examples: design/v1.0.1/prd.md, design/v0.5.0/plan.md
    

design/archive/: Archived or inactive design documents. Treat as low-priority reference when exploring existing graph structures -- prioritize reading active version directories, and only fall back to archive when relevant context cannot be found in active versions.

All subsequent paths using <design-dir> refer to this directory.


TL;DR -- Hard Rules (Above the Fold)

  • Input: Requirement description + version number (required); architecture documents (optional)
  • Output: Product Node tree + Edges + Facts, written to <design-dir>/<version>/prd.md
  • Prohibited: Do not produce Package/Symbol (that belongs to Plan); do not write implementation code
  • Product kind: domain / application / story (not feature -- Feature is an iteration delivery unit and does not enter the graph)
  • story = long-lived knowledge asset: Describes who can do what and gain what value. Specs attach only to stories, not to domain/application
  • spec must be end-to-end verifiable: Each spec must be verifiable through the product interface (Web UI preferred), not solely through API calls or running tests. CLI is an acceptable fallback when no UI exists. If interface-level verification is impossible -> it is a technical spec, leave it for Plan
  • Technical element triage: When input contains technical proposals, extract only product-layer elements; leave technical constraints for /make-plan
  • Minimum output: Each story Node >= 1 [description] + >= 1 [spec]
  • Fact numbering: All specs use [S1] [S2] ... stable numbering, for Plan implements references
  • content <= 256 characters, detail is optionally inlined (> block); if over 100 lines, link externally to details/
  • Non-goals = [decision] Facts, attached to the relevant Node, with version constraints
  • Do not write corresponds edges without code context -- better to omit than to guess
  • Fact changes: Modifying an existing Fact requires [-kind] + [+kind] + supersedes association
  • PRD can be simple or even absent: When the input is primarily a technical proposal, the PRD may contain only a few stories; if no stories or product specs can be extracted at all, classify it as a pure technical upgrade -- do not produce a PRD, proceed directly to /make-plan

Read the full file on GitHub · 402 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 · 402 lines · 39 tokens per session scan A da008429dc7a

Subscribe to this mod's changes

make-prd is a skill published in the GitHub repository context4ai/workflow (4 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 5,025 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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