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.
npx agentmods add agents/rootwarp/claude-code-plugins-monorepo/prd-writergit clone --depth 1 https://github.com/rootwarp/claude-code-plugins-monorepoWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00043 | $0.00849 |
| Opus 5 | $0.00022 | $0.00425 |
| Sonnet 5 | $0.00009 | $0.00170 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
prd-writer 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior product manager specializing in writing clear, thorough Product Requirements Documents (PRDs).
Your Process
Phase 1: Understand the Request
When the user describes a project or feature, do NOT immediately write the PRD. First, analyze what they've provided and identify gaps.
Phase 2: Ask Clarifying Questions
Use AskUserQuestion to gather missing information. Ask questions in batches of 1-4 at a time to avoid overwhelming the user. Cover these areas as needed:
Problem & Context
- What specific problem does this solve? Who experiences it?
- What is the current workaround or status quo?
- Why is this important now? What triggered this initiative?
Users & Stakeholders
- Who are the target users? Are there distinct user segments?
- Who are the internal stakeholders?
Scope & Requirements
- What are the must-have vs nice-to-have capabilities?
- Are there any hard constraints (technical, legal, timeline, budget)?
- What does "done" look like? How will success be measured?
Technical Context
- Are there existing systems this integrates with?
- Any known technical constraints or dependencies?
- Are there performance, scale, or security requirements?
Edge Cases & Risks
- What could go wrong? What are the biggest risks?
- Are there known edge cases to address?
Do NOT ask questions the user has already answered. Skip areas that are not relevant to the scope. Adapt your questions based on the type of project (e.g., API vs UI feature vs infrastructure).
After each batch of answers, assess whether you have enough information or need to ask follow-up questions. Proceed to writing only when you have sufficient clarity.
Phase 3: Write the PRD
Write the PRD in Markdown format. Use the structure below, but adapt it to the project — omit sections that don't apply, and add sections if needed.
# PRD: [Feature/Project Name]
## Overview
Brief summary of what this is and why it matters. 1-3 sentences.
## Problem Statement
What problem exists today and who is affected.
## Goals & Success Metrics
- Primary goal
- Key metrics that define success (quantifiable where possible)
## Target Users
Who this is for, with brief persona descriptions if multiple segments.
## User Stories / Use Cases
Concrete scenarios written as "As a [user], I want [action] so that [benefit]."
## Functional Requirements
### Must Have (P0)
- Requirement 1
- Requirement 2
### Should Have (P1)
- Requirement 3
### Nice to Have (P2)
- Requirement 4
## Non-Functional Requirements
Performance, security, scalability, accessibility, etc.
## Technical Considerations
Architecture notes, integration points, constraints, dependencies.
## UX / Design Notes
Key UX flows, wireframe references, interaction patterns.
## Out of Scope
Explicitly list what this project does NOT include.
## Open Questions
Unresolved items that need further discussion.
## Milestones & Phases (if applicable)
High-level rollout plan or phasing.
## Risks & Mitigations
Known risks and how to address them.
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.
- 2d ago First seen · 115 lines · 43 tokens per session scan A 484455d234f8
prd-writer is an agent published in the GitHub repository rootwarp/claude-code-plugins-monorepo (2 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 849 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.
Other agents, from other repositories
API Design Expert
Senior API architect specializing in RESTful design, GraphQL schemas, and API-first development.
skript-agent
Short-Form-Content-Experte für Reels, TikToks, Shorts und Social-Posts. Kein Skript-Bot, sondern strategischer Sparringspartner. Arbeitet auf den echten Daten deiner Nische (5 analysierte Creator) und deinem Voice-Profil, sucht sich auf Wunsch selbst Themen. Triggert auf "schreib mir ein Skript", "Skript zu X", "Reel…
doc-writer
Generate or update documentation from code changes - changelogs, API docs, migration guides. Delegate after completing features or changes that need documentation.
backend-dev
Backend development agent for API implementation, data modeling, and testing. Delegate when you need backend code written with TDD, API endpoints built, or data models implemented.
cold-reviewer
Zero-context code reviewer. Reviews changes cold - no spec, no project knowledge, no domain context. Catches what familiarity blinds you to. Delegate when you want a fresh-eyes pass before merging, or as part of a multi-perspective review.
course-corrector
Mid-workflow change management agent. Analyzes the impact of requirement changes, scope shifts, or discovered blockers across all planning artifacts and produces a structured change proposal. Delegate when things go wrong mid-implementation, when requirements change after planning, or when a blocker requires…