to-prd

to-prd is a skill for Claude Code, Codex from a1f/agent-templates. It costs 36 tokens per session (1,029 once invoked), scanned A, original, MIT.

A workflow for turning a conversation and light codebase review into a short product requirements document, or PRD, and publishing it as a GitHub issue. A PRD describes what should be built and the decisions behind it.

In plain words
What is it for?
Use it to draft, approve, create, or update GitHub issues containing implementation plans, with optional titles and labels.
Why use it?
It turns scattered discussion into a concise plan that people can review and track. It also asks for clarification when a missing fact could change the design.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: names the AskUserQuestion tool.

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/a1f/agent-templates/to-prd
Any agent
npx skills add a1f/agent-templates --skill to-prd
Clone the repo
git clone --depth 1 https://github.com/a1f/agent-templates

Made for: Claude Code, Codex.

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 to-prd

README.md
[![agentmods](https://agentmods.dev/badge/skills/a1f/agent-templates/to-prd.svg)](https://agentmods.dev/skills/a1f/agent-templates/to-prd)
Your own site
<a href="https://agentmods.dev/skills/a1f/agent-templates/to-prd"><img src="https://agentmods.dev/badge/skills/a1f/agent-templates/to-prd.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,029 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 5.1 $0.00036 $0.01029
Opus 5 $0.00018 $0.00515
Sonnet 5 $0.00007 $0.00206
Haiku 4.5 $0.00004 $0.00103

Measured 5d ago against content hash 5c19094bd787, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

to-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.

skills/to-prd/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

To PRD

Turn the conversation and codebase into a short PRD a human actually reads, then publish it as a GitHub issue.

/to-prd [--title="..."] [--label=Plan] [--issue=N]

  1. Gather context (conversation + light repo read)
  2. Clarify gaps via AskUserQuestion   (gate, only if thin)
  3. Draft the PRD
  4. Show it, wait for approval          (gate)
  5. Publish the issue; print URL + number

Arguments

Arg Default Notes
--title="..." Derived from context Issue title
--label=... Plan Dropped if the repo has no such label; pass --label= for none
--issue=N Create new Re-publish: replace the PRD, keep any appended slices/PRs

Phase 1 — Gather context

Read the conversation; explore the repo only if you haven't. Use the codebase's own vocabulary and respect existing ADRs.

Phase 2 — Clarify (gate)

If a fact that changes the design is missing, ask with AskUserQuestion (≤4 at a time, concrete options) — otherwise skip when context is rich.

Phase 3 — Draft

Write it tight:

  • One screen. Cut anything that doesn't change a decision.
  • The english rule governs every line — it loads each session, so you already have it. Cut all hedging.
  • Tables and bullets over paragraphs. A PRD is scanned, not read: this is the one document where a list beats prose.
  • Only what was discussed or confirmed — invent nothing.
  • No file paths or code; they rot. Rare exception: a tiny snippet that nails a decision — a type, a schema.

Use these sections:

## The problem
<What's wrong today, in the reader's words. One short paragraph.>

## What we're building
<A few sharp sentences. The core idea.>

## How it works
<The key mechanics as bullets.>

## Decisions already made
<Table: Area | Choice.>

## In scope / Out of scope
<Two short lists.>

## Open questions
<What still needs the user's call. Omit if none.>

Phase 4 — Approve (gate)

Show the draft in chat. Wait for an OK or edits. Don't publish until approved.

Read the full file on GitHub · 106 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. 5d ago First seen · 106 lines · 36 tokens per session scan A 5c19094bd787

Subscribe to this mod's changes

to-prd is a skill published in the GitHub repository a1f/agent-templates (2 stars, last pushed 6d ago), licensed MIT. It adds 36 tokens to every session and 1,029 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.

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

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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-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