compose-brownfield-prd

compose-brownfield-prd is a skill for Claude Code from SebastienDegodez/skraft-plugin. It costs 95 tokens per session (1,318 once invoked), scanned C, original, GPL-3.0.

A document-writing tool for turning existing project findings into an HVE-format product requirements document. A product requirements document explains what a product should do and the constraints it must meet.

In plain words
What is it for?
Use it to write or update PRDs in docs/prds/ after an existing codebase has been characterized. It covers current features, limits, integrations, test coverage, and technical debt.
Why use it?
It organizes information about an existing system into a structured plan with requirements and links back to the evidence behind them. The input must come from a brownfield characterization, meaning analysis of an already-built project.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the skraft plugin — 36 skills, 15 agents, 5 hooks shipped together

Good fit Use it to write or update PRDs in docs/prds/ after an existing codebase has been characterized. It covers current features, limits, integrations, test coverage, and technical debt.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sebastiendegodez/skraft-plugin/compose-brownfield-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 SebastienDegodez/skraft-plugin --skill compose-brownfield-prd
Clone the repo
git clone --depth 1 https://github.com/SebastienDegodez/skraft-plugin

Made for: Claude Code.

Or install skraft, the plugin that ships this one along with the rest of its 36 skills, 15 agents, 5 hooks.

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 compose-brownfield-prd

README.md
[![agentmods](https://agentmods.dev/badge/skills/sebastiendegodez/skraft-plugin/compose-brownfield-prd/github.svg)](https://agentmods.dev/skills/sebastiendegodez/skraft-plugin/compose-brownfield-prd)
Your own site
<a href="https://agentmods.dev/skills/sebastiendegodez/skraft-plugin/compose-brownfield-prd"><img src="https://agentmods.dev/badge/skills/sebastiendegodez/skraft-plugin/compose-brownfield-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 compose-brownfield-prd

Your own site · 80×15
<a href="https://agentmods.dev/skills/sebastiendegodez/skraft-plugin/compose-brownfield-prd"><img src="https://agentmods.dev/badge/skills/sebastiendegodez/skraft-plugin/compose-brownfield-prd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,318 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 $0.00095 $0.01318
Opus 5 $0.00048 $0.00659
Sonnet 5 $0.00019 $0.00264
Haiku 4.5 $0.00010 $0.00132

Measured 10d ago against content hash e955a996224d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

compose-brownfield-prd scanned grade C 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 10d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

- File starts with `<!-- markdownlint-disable-file -->` then `<!-- markdown-table-prettify-ignore-start -->`.
plugins/skraft-framework/skills/compose-brownfield-prd/SKILL.md · 81 lines

The source is not reproduced here

Licensed GPL-3.0

The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 10d ago First seen · 81 lines · 95 tokens per session scan C e955a996224d

Subscribe to this mod's changes

compose-brownfield-prd is a skill published in the GitHub repository SebastienDegodez/skraft-plugin (8 stars, last pushed 2d ago), licensed GPL-3.0. It adds 95 tokens to every session and 1,318 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.