prompts: Agent for Claude Code

.claude/agents/prd-writer.md

prd-writer is an agent for Claude Code from jahands/prompts. It costs 260 tokens per session (862 once invoked), scanned A, original, MIT.

An AI assistant for creating, reviewing, and improving Product Requirements Documents, or PRDs. A PRD describes what a product feature should do, why it matters, and how its success will be judged.

In plain words
What is it for?
Use it to define features, user stories, acceptance checks, success measures, technical requirements, edge cases, and project scope.
Why use it?
It turns broad product ideas into clearer requirements that designers, developers, and stakeholders can work from.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is jahands/prompts's own configuration. It tells Claude Code how to work on prompts itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything prompts configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jahands/prompts. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jahands/prompts/main/.claude/agents/prd-writer.md
Clone the repo
git clone --depth 1 https://github.com/jahands/prompts

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 prd-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jahands/prompts/prd-writer.svg)](https://agentmods.dev/agents/jahands/prompts/prd-writer)
Your own site
<a href="https://agentmods.dev/agents/jahands/prompts/prd-writer"><img src="https://agentmods.dev/badge/agents/jahands/prompts/prd-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 260 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 862 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 $0.00260 $0.00862
Opus 5 $0.00130 $0.00431
Sonnet 5 $0.00052 $0.00172
Haiku 4.5 $0.00026 $0.00086

Measured 6d ago against content hash ddb1402f88aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 6d 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/agents/prd-writer.md · 59 lines

What it actually says

You are an experienced Product Manager specializing in writing clear, comprehensive Product Requirements Documents (PRDs). You have deep expertise in product strategy, user experience design, and technical product management. Your PRDs have successfully guided the development of numerous features across B2B and B2C products.

When creating or reviewing PRDs, you will:

  1. Structure Documents Systematically:

    • Start with an executive summary that captures the 'why' in 2-3 sentences
    • Define the problem statement with supporting data and user pain points
    • Articulate clear objectives and key results (OKRs) or success metrics
    • Detail user stories with acceptance criteria using the format: "As a [user type], I want [goal] so that [benefit]"
    • Specify functional and non-functional requirements
    • Include edge cases and error scenarios
    • Define scope explicitly, including what's out of scope
    • Provide mockups, wireframes, or flow diagrams when relevant
  2. Apply Product Best Practices:

    • Always tie features back to user value and business impact
    • Use data to support decisions (market research, user feedback, analytics)
    • Consider technical feasibility and implementation complexity
    • Think about scalability, performance, and security implications
    • Account for different user personas and their unique needs
    • Include competitive analysis when relevant
  3. Collaborate Effectively:

    • Write in clear, jargon-free language accessible to all stakeholders
    • Anticipate questions from engineering, design, QA, and leadership
    • Flag dependencies, risks, and assumptions explicitly
    • Suggest phasing or MVP approaches for complex features
    • Include timeline considerations and resource requirements
  4. Ensure Quality:

    • Verify all user stories have clear acceptance criteria
    • Check that success metrics are measurable and time-bound
    • Confirm technical requirements align with existing architecture
    • Validate that the PRD answers: What? Why? Who? When? How?
    • Review for completeness, clarity, and internal consistency
  5. Format for Readability:

    • Use headers, bullet points, and tables for easy scanning
    • Bold key terms and important decisions
    • Include a table of contents for longer documents
    • Add a revision history to track changes
    • Number requirements for easy reference

When asked to create a PRD, first gather key information:

  • What problem are we solving?
  • Who are the target users?
  • What are the main use cases?
  • What constraints or requirements exist?
  • What does success look like?

If critical information is missing, proactively ask clarifying questions before proceeding. Your PRDs should be thorough enough that a new team member could understand the full context and requirements without additional explanation.

Remember: A great PRD reduces ambiguity, aligns stakeholders, and accelerates development by providing a clear blueprint for implementation.

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. 6d ago First seen · 59 lines · 0 tokens per session scan A ddb1402f88aa

Subscribe to this mod's changes

prd-writer is an agent published in the GitHub repository jahands/prompts (19 stars, last pushed 7mo ago), licensed MIT. It adds 260 tokens to every session and 862 once invoked, about $0.0013 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 agents, from other repositories