prd-build

prd-build is a skill for Claude Code, Codex from sjarmak/agent-workflows. It costs 18 tokens per session (2,407 once invoked), scanned A, original, MIT.

An orchestrator that turns a product requirements document (PRD) into implementation tasks, assigns them to separate coding agents, reviews their work, and merges the tasks that pass.

In plain words
What is it for?
Use it to build a PRD through parallel work units, isolated workspaces, independent code reviews, acceptance checks, retries, and multi-pass recovery.
Why use it?
It coordinates dependent work and recovery across multiple agents, reducing the need to manually divide, track, review, and merge a large feature.

Skill for Claude CodeCodex

Part of the agent-workflows plugin — 28 skills, 4 agents, 4 hooks shipped together

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/sjarmak/agent-workflows/prd-build
Any agent
npx skills add sjarmak/agent-workflows --skill prd-build
Clone the repo
git clone --depth 1 https://github.com/sjarmak/agent-workflows

Made for: Claude Code, Codex.

Or install agent-workflows, the plugin that ships this one along with the rest of its 28 skills, 4 agents, 4 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 prd-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/sjarmak/agent-workflows/prd-build.svg)](https://agentmods.dev/skills/sjarmak/agent-workflows/prd-build)
Your own site
<a href="https://agentmods.dev/skills/sjarmak/agent-workflows/prd-build"><img src="https://agentmods.dev/badge/skills/sjarmak/agent-workflows/prd-build.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,407 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 $0.00018 $0.02407
Opus 5 $0.00009 $0.01203
Sonnet 5 $0.00004 $0.00481
Haiku 4.5 $0.00002 $0.00241

Measured 5d ago against content hash d71ea1eb01d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prd-build 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/prd-build/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Automated PRD-to-implementation orchestrator. Takes a PRD, decomposes it into a dependency-ordered set of work units, dispatches parallel agents in isolated worktrees to implement each unit, runs independent review agents to verify acceptance criteria, and merges passing work onto an integration branch. Handles retries, evictions, and multi-pass recovery.

You are the orchestrator. Your ONLY job is to decompose, dispatch, and land. You do NOT:

  • Ask the user design questions
  • Make implementation decisions
  • Pause for confirmation (unless --dry-run)
  • Do any implementation work yourself

You DO:

  • Decompose the PRD into work units with verifiable acceptance criteria
  • Use the Agent tool with isolation: "worktree" to dispatch each unit to a separate agent
  • Use the Agent tool with subagent_type: "code-reviewer" for independent reviews
  • Merge completed work onto the integration branch
  • Track state in .claude/prd-build-artifacts/

CRITICAL: Every work unit MUST be executed by an Agent tool call with isolation: "worktree". You NEVER implement code yourself.

Arguments

$ARGUMENTS — format: <path/to/prd.md> [--max-passes N] [--max-parallel N] [--dry-run]

Parse:

  • prd_path: path to the PRD file (required)
  • max_passes: maximum retry passes for evicted units (default: 3)
  • max_parallel: maximum parallel agents per layer (default: 5)
  • dry_run: if set, decompose and print the work plan but do not execute

Read the PRD file. If it does not exist, report an error and stop.

Phase 1: DECOMPOSE

Break the PRD into work units.

Decomposition Rules

  1. Minimize file overlap between units (prevents merge conflicts)
  2. Tests belong WITH implementation, not in separate units
  3. Dependencies = real code dependencies only (imports, not conceptual)
  4. Prefer 5-10 cohesive units over many tiny ones
  5. Extract acceptance criteria directly from the PRD — each requirement should have verifiable criteria. Map these to units.
  6. If the PRD lacks verifiable acceptance criteria for a requirement, generate them: each criterion must be a concrete, testable condition (a command to run, an output to check, a behavior to observe). "Works correctly" is NOT acceptable. "Running npm test passes with 0 failures" IS acceptable.

Read the full file on GitHub · 237 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 · 237 lines · 18 tokens per session scan A d71ea1eb01d3

Subscribe to this mod's changes

prd-build is a skill published in the GitHub repository sjarmak/agent-workflows (9 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 2,407 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 2026-08-31.

Related

Other skills, from other repositories

speckit.clarify

Skill "speckit.clarify" from caipe-io/ai-platform-engineering, covering user input and outline.

caipe-io/ai-platform-engineering · 0 tokens

speckit.specify

Skill "speckit.specify" from caipe-io/ai-platform-engineering, covering user input, outline, quick guidelines, section requirements and for ai generation.

caipe-io/ai-platform-engineering · 0 tokens

release-docs

Generate a combined release blog post for ai-platform-engineering. Produces a single docs/releases/YYYY-MM-DD-release-X-Y-Z.md file containing release notes and the upgrade guide (migration guide) inline. Use when cutting a release, when a user asks "what changed in 0.4.x", or when upgrading their values.yaml to a new…

caipe-io/ai-platform-engineering · 76 tokens

local-integration-testing

Run end-to-end integration tests with all 15 agents and supervisor in local Docker Compose dev environment. Validates agent discovery, multi-agent routing, checkpoint persistence, and cross-agent follow-up conversations.

caipe-io/ai-platform-engineering · 44 tokens

update-docs

Audit and update all documentation moving parts for ai-platform-engineering. Checks release blog posts, features page, agent docs, homepage version strings, Docusaurus version config, and sidebar completeness. Fixes what is stale and reports what needs manual attention. Use after cutting a release, adding a new agent…

caipe-io/ai-platform-engineering · 70 tokens

docker-compose-first-install

Validate and repair the OSS first-install Docker Compose path. Use when editing docker-compose.yaml, docker-compose.dev.yaml, .env.example, release image tags, Compose profiles, Keycloak/OpenFGA/RAG defaults, or first-launch UI behavior for local all-in-one installs.

caipe-io/ai-platform-engineering · 60 tokens