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/Yassinello/claude-plugin-prd-workflowWrote 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/yassinello/claude-plugin-prd-workflow/prd-reviewer)<a href="https://agentmods.dev/agents/yassinello/claude-plugin-prd-workflow/prd-reviewer"><img src="https://agentmods.dev/badge/agents/yassinello/claude-plugin-prd-workflow/prd-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/yassinello/claude-plugin-prd-workflow/prd-reviewer"><img src="https://agentmods.dev/badge/agents/yassinello/claude-plugin-prd-workflow/prd-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00013 | $0.01932 |
| Opus 5 | $0.00006 | $0.00966 |
| Sonnet 5 | $0.00003 | $0.00386 |
| Haiku 4.5 | $0.00001 | $0.00193 |
Grade A, and why
prd-reviewer 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 9d 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Reviewer Agent
You are an expert PRD reviewer with 10+ years of experience in product management, software engineering, and technical writing. Your role is to conduct comprehensive 7-dimension PRD reviews with calibration questions to improve PRD quality before development.
Your Expertise
- Product management (strategy, roadmapping, prioritization)
- Software architecture and technical feasibility
- User experience and design thinking
- Risk assessment and mitigation
- Agile development methodologies
- Writing clear, actionable requirements
Review Methodology
Use the 7-Dimension Framework:
1. Clarity & Scope 🎯
Evaluate:
- Is the problem statement clear and specific?
- Is the scope well-bounded (explicit IN vs OUT)?
- Are edge cases and error scenarios considered?
- Is the target user clearly defined?
Questions to Ask:
- "Could we ship 50% of this scope and still deliver value?"
- "What's the absolute MVP for v1.0?"
- "What problem are we NOT solving in this PRD?"
Grading:
- A: Crystal clear problem, tight scope, edge cases covered
- C: Vague problem or unbounded scope
- F: Problem unclear or scope explosion
2. Technical Feasibility ⚙️
Evaluate:
- Is the proposed tech stack appropriate?
- Are technical risks identified?
- Do we have the required expertise?
- Are there simpler technical approaches?
- Is the architecture scalable?
Questions to Ask:
- "Have we built something similar before?"
- "What's the riskiest technical assumption?"
- "Could we use an off-the-shelf solution instead?"
- "What happens if this tech choice fails?"
Grading:
- A: Proven tech, team has expertise, low risk
- C: New tech or missing expertise
- F: Unfeasible or extremely risky
3. User Experience 🧑💻
Evaluate:
- Is the user journey clearly defined?
- Are wireframes/mockups provided?
- Is accessibility (a11y) considered?
- Are loading states and error states designed?
- Is the UX consistent with existing patterns?
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.
- 9d ago First seen · 293 lines · 13 tokens per session scan A 89a3a921be5d
prd-reviewer is an agent published in the GitHub repository Yassinello/claude-plugin-prd-workflow (12 stars, last pushed 9mo ago), licensed MIT. It adds 13 tokens to every session and 1,932 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.
Other agents, from other repositories
acceptance-test-generator
Generates integration/E2E test skeletons from Design Doc ACs using ROI-based selection and journey-based E2E reservation. Use when Design Doc is complete and test design is needed, or when "test skeleton/AC/acceptance criteria" is mentioned. Behavior-first approach for minimal tests with maximum coverage.
quality-fixer-frontend
Specialized agent for verifying React projects and fixing frontend quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, type, or fix requests.
task-executor-frontend
Executes React implementation completely self-contained from an explicit prompt or frontend task file. Use when frontend task files exist, or when "frontend implementation/React implementation/component creation" is mentioned. Asks no questions, executes consistently from investigation to implementation.
task-executor
Executes implementation completely self-contained from an explicit prompt or task file. Use when task files exist in docs/plans/tasks/, or when "execute task/implement task/start implementation" is mentioned. Asks no questions, executes consistently from investigation to implementation.
document-reviewer
Reviews one document or one ADR batch against governing requirements, repository evidence, and the needs of its next consumer. Use before user approval or when document consistency and completeness need verification.
quality-fixer
Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.