implement-prd

implement-prd is a skill for Claude Code from rtazima/claude-proj-blueprint. It costs 29 tokens per session (666 once invoked), scanned A, original, MIT.

A workflow for building a feature from a product requirements document, or PRD—a document describing what the product should do. It checks related architecture and design documents, implements the feature, tests it, and updates documentation when needed.

In plain words
What is it for?
Use it when implementing, building, or constructing a feature from a PRD, including checking architecture decisions, specifications, UI requirements, tests, compliance, and documentation.
Why use it?
It gives feature work a defined path from requirements to verified code. It also chooses between following a Figma design and creating the interface from the project’s design system when no design link exists.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md.

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/rtazima/claude-proj-blueprint/implement-prd
Any agent
npx skills add rtazima/claude-proj-blueprint --skill implement-prd
Clone the repo
git clone --depth 1 https://github.com/rtazima/claude-proj-blueprint

Made for: Claude Code.

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 implement-prd

README.md
[![agentmods](https://agentmods.dev/badge/skills/rtazima/claude-proj-blueprint/implement-prd.svg)](https://agentmods.dev/skills/rtazima/claude-proj-blueprint/implement-prd)
Your own site
<a href="https://agentmods.dev/skills/rtazima/claude-proj-blueprint/implement-prd"><img src="https://agentmods.dev/badge/skills/rtazima/claude-proj-blueprint/implement-prd.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 666 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 $0.00029 $0.00666
Opus 5 $0.00015 $0.00333
Sonnet 5 $0.00006 $0.00133
Haiku 4.5 $0.00003 $0.00067

Measured 5d ago against content hash d2c7095efebd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

implement-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.

.claude/skills/implement-prd/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement from PRD

Workflow

  1. Read the PRD completely in docs/product/
  2. Check related ADRs in docs/architecture/
  3. Check applicable specs in docs/specs/ (design, compliance, etc.)
  4. Detect design flow — determine how UI will be built:
    • Figma flow: PRD contains a Figma link → use Figma MCP server to extract design context (components, spacing, colors, layout) → implement matching the design
    • Agent flow: PRD has no Figma link → activate .claude/skills/frontend-agent/SKILL.md → load design tokens from docs/specs/design-system/README.md → scan existing components → generate UI from tokens + component library + PRD requirements
  5. Plan Mode — create implementation plan before coding
  6. Implement following CLAUDE.md conventions
  7. Tests — create tests following .claude/skills/testing/SKILL.md
  8. Spec checks — verify compliance with active modules
  9. Document — update docs if needed

Design flow detection

Check the PRD for these patterns to determine the flow:

  • Contains figma.com URL or ## Design section with link → Figma flow
  • Contains ## Design with "see design-system tokens" or no link → Agent flow
  • No design section at all → Agent flow (use tokens + existing patterns)

Rules

  • Never implement without reading the full PRD first
  • If the PRD is ambiguous, ask before assuming
  • Always check if an ADR already exists for the technical decision
  • Atomic commits per feature/sub-feature
  • Never hardcode UI values — always use design tokens or Figma specs

Racionalizações comuns

Racionalização Realidade
"O código tá simples, não precisa de testes" Código simples hoje vira complexo amanhã. Testes documentam intenção.
"Já sei o que o PRD quer, não preciso ler tudo" PRDs têm restrições e edge cases nas entrelinhas. Leia completo.
"Esse ADR não se aplica aqui" Se o ADR existe, alguém já enfrentou esse problema. Verifique antes de ignorar.
"Vou commitar tudo junto, é mais rápido" Commits atômicos permitem revert cirúrgico. Commit grande = revert impossível.
"Design tokens são exagero pra esse componente" Hardcode hoje, inconsistência amanhã. Sempre use tokens.

Read the full file on GitHub · 52 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 · 52 lines · 29 tokens per session scan A d2c7095efebd

Subscribe to this mod's changes

implement-prd is a skill published in the GitHub repository rtazima/claude-proj-blueprint (20 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 666 once invoked, about $0.0001 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