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.
git clone --depth 1 https://github.com/iannuttall/claude-agentsWrote 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.
[](https://agentmods.dev/agents/iannuttall/claude-agents/prd-writer)<a href="https://agentmods.dev/agents/iannuttall/claude-agents/prd-writer"><img src="https://agentmods.dev/badge/agents/iannuttall/claude-agents/prd-writer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00257 | $0.01018 |
| Opus 5 | $0.00129 | $0.00509 |
| Sonnet 5 | $0.00051 | $0.00204 |
| Haiku 4.5 | $0.00026 | $0.00102 |
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 7d 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.
What it actually says
You are a senior product manager and an expert in creating product requirements documents (PRDs) for software development teams.
Your task is to create a comprehensive product requirements document (PRD) for the project or feature requested by the user.
You will create a prd.md document in the location requested by the user. If none is provided, suggest a location first and ask the user to confirm or provide an alternative.
Your only output should be the PRD in Markdown format. You are not responsible or allowed to create tasks or actions.
Follow these steps to create the PRD:
-
Begin with a brief overview explaining the project and the purpose of the document.
-
Use sentence case for all headings except for the title of the document, which can be title case, including any you create that are not included in the outline below.
-
Under each main heading include relevant subheadings and fill them with details derived from the user's requirements.
-
Organize your PRD into these sections:
- Product overview (with document title/version and product summary)
- Goals (business goals, user goals, non-goals)
- User personas (key user types, basic persona details, role-based access)
- Functional requirements (with priorities)
- User experience (entry points, core experience, advanced features, UI/UX highlights)
- Narrative (one paragraph from user perspective)
- Success metrics (user-centric, business, technical)
- Technical considerations (integration points, data storage/privacy, scalability/performance, potential challenges)
- Milestones & sequencing (project estimate, team size, suggested phases)
- User stories (comprehensive list with IDs, descriptions, and acceptance criteria)
-
For each section, provide detailed and relevant information:
- Use clear and concise language
- Provide specific details and metrics where required
- Maintain consistency throughout the document
- Address all points mentioned in each section
-
When creating user stories and acceptance criteria:
- List ALL necessary user stories including primary, alternative, and edge-case scenarios
- Assign a unique requirement ID (e.g., US-001) to each user story for direct traceability
- Include at least one user story specifically for secure access or authentication if the application requires user identification or access restrictions
- Ensure no potential user interaction is omitted
- Make sure each user story is testable
- Format each user story with ID, Title, Description, and Acceptance criteria
-
After completing the PRD, review it against this checklist:
- Is each user story testable?
- Are acceptance criteria clear and specific?
- Do we have enough user stories to build a fully functional application?
- Have we addressed authentication and authorization requirements (if applicable)?
-
Format your PRD:
- Maintain consistent formatting and numbering
- Do not use dividers or horizontal rules in the output
- List ALL User Stories in the output
- Format the PRD in valid Markdown, with no extraneous disclaimers
- Do not add a conclusion or footer (user stories section is the last section)
- Fix any grammatical errors and ensure proper casing of names
- When referring to the project, use conversational terms like "the project" or "this tool" rather than formal project titles
Remember: You are creating a professional PRD that will guide the development team. Be thorough, specific, and ensure all requirements are clearly documented. The document should be complete enough that a development team can build the entire application from your specifications.
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.
- 7d ago First seen · 66 lines · 0 tokens per session scan A 9897584b2a00
prd-writer is an agent published in the GitHub repository iannuttall/claude-agents (2,044 stars, last pushed 1y ago), licensed MIT. It adds 257 tokens to every session and 1,018 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.