speckit-prd

speckit-prd is a skill for Claude Code, Codex from racecraft-lab/racecraft-plugins-public. It costs 164 tokens per session (1,051 once invoked), scanned A, original, MIT.

A guided writing workflow that turns a raw product or technical idea into a product requirements document, a technical roadmap, and a map of the planned specifications.

In plain words
What is it for?
Use it to interview someone about an idea, define what the product should do, order the technical work, and prepare notes for later specification and automation.
Why use it?
It gives an idea a clear written shape before development starts, so product goals and technical work stay connected.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions subagents; mentions Codex; $skill-name invocation.

Part of the speckit-pro plugin — 12 skills, 13 agents, 4 hooks, 1 MCP server shipped together

Good fit Use it to interview someone about an idea, define what the product should do, order the technical work, and prepare notes for later specification and automation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/racecraft-lab/racecraft-plugins-public/speckit-prd
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.

Any agent
npx skills add racecraft-lab/racecraft-plugins-public --skill speckit-prd
Clone the repo
git clone --depth 1 https://github.com/racecraft-lab/racecraft-plugins-public

Made for: Claude Code, Codex.

Or install speckit-pro, the plugin that ships this one along with the rest of its 12 skills, 13 agents, 4 hooks, 1 MCP server.

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 speckit-prd

README.md
[![agentmods](https://agentmods.dev/badge/skills/racecraft-lab/racecraft-plugins-public/speckit-prd/github.svg)](https://agentmods.dev/skills/racecraft-lab/racecraft-plugins-public/speckit-prd)
Your own site
<a href="https://agentmods.dev/skills/racecraft-lab/racecraft-plugins-public/speckit-prd"><img src="https://agentmods.dev/badge/skills/racecraft-lab/racecraft-plugins-public/speckit-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.

agentmods 80×15 button for speckit-prd

Your own site · 80×15
<a href="https://agentmods.dev/skills/racecraft-lab/racecraft-plugins-public/speckit-prd"><img src="https://agentmods.dev/badge/skills/racecraft-lab/racecraft-plugins-public/speckit-prd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 164 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,051 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00164 $0.01051
Opus 5 $0.00082 $0.00526
Sonnet 5 $0.00033 $0.00210
Haiku 4.5 $0.00016 $0.00105

Measured today against content hash c7de90865c3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

speckit-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 today.

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.

speckit-pro/codex-skills/speckit-prd/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SpecKit PRD

Create or update three consistent Markdown artifacts: a lean PRD for WHAT and WHY, a technical roadmap whose SPEC catalog maps 1:1 to PRD Features, and a roadmap-MOC that makes the spec tree navigable.

Ground recommendations

Inspect the tools and skills actually available. Follow the shared capability-discovery and grounding contracts. Read applicable project instructions, .specify/memory/constitution.md, prior roadmaps and decisions, and targeted code. Disclose uncertainty; do not guess.

Codex interaction adapter

In an active user chat, prefer request_user_input whenever it is present. Send one question at a time with 2-3 mutually exclusive choices: put the grounded recommendation first, suffix its label (Recommended), and state each tradeoff briefly. Wait for the user's reply before the next question.

If the picker is absent or its call is unavailable, use a free-text fallback only in the already active user chat. Ask exactly one question, list the recommended choice first plus 1-2 mutually exclusive alternatives, and wait for the user's direct reply.

In codex exec, background automation, CI, autopilot, or subagent execution, never use the fallback and never fabricate intent. A caller that explicitly requested a draft may receive only a best-effort PRD from supplied material, with every unvalidated decision in Open Questions and a clear "interactive pass required" status. Do not claim it is roadmap-ready and do not create or update its roadmap or roadmap-MOC.

Workflow

Read and follow the shared PRD authoring protocol before authoring. Determine whether the user is creating from an idea or updating an existing PRD; before overwriting, confirm the exact output path and preserve stable feature and SPEC identifiers for unchanged work. Use the shared PRD template, technical-roadmap template, slicing heuristics, and, for a new roadmap, roadmap-MOC template. If docs/ai/specs/ubiquitous-language.md exists, read it first and use its terms verbatim in the PRD. Apply the protocol's interview, update, slicing/estimation, MOC, index, and verification rules. Report created or updated paths and recommend $speckit-scaffold-spec <SPEC-ID> for the first ready entry.

Read the full file on GitHub · 70 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. today Changed · -217 lines · -95 tokens per session c7de90865c3f
  2. 6d ago First seen · 287 lines · 259 tokens per session scan A 5756bbbea158

Subscribe to this mod's changes

speckit-prd is a skill published in the GitHub repository racecraft-lab/racecraft-plugins-public (5 stars, last pushed today), licensed MIT. It adds 164 tokens to every session and 1,051 once invoked, about $0.0008 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 2026-09-04.