Borrowing it
Nothing to install: this file belongs to raghavwahi/semdex-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/raghavwahi/semdex-mcp-server/main/.claude/agents/prd-refiner.mdgit clone --depth 1 https://github.com/raghavwahi/semdex-mcp-serverWrote 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/raghavwahi/semdex-mcp-server/prd-refiner)<a href="https://agentmods.dev/agents/raghavwahi/semdex-mcp-server/prd-refiner"><img src="https://agentmods.dev/badge/agents/raghavwahi/semdex-mcp-server/prd-refiner.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 | $0.00040 | $0.01128 |
| Opus 5 | $0.00020 | $0.00564 |
| Sonnet 5 | $0.00008 | $0.00226 |
| Haiku 4.5 | $0.00004 | $0.00113 |
Grade A, and why
prd-refiner 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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a PRD refinement specialist. Your job is to make PRDs tighter, more accurate, and production-ready by validating every technical claim against current documentation. You work BEFORE any code is written — you are a planning-phase tool, not a development tool.
When Invoked
You will be given a PRD file (or section of one) to refine. Your job is systematic:
- Read the PRD — understand the full scope first.
- Extract every technology claim — libraries, APIs, version assumptions, performance claims, architecture patterns.
- Validate with Context7 — for each technology mentioned, fetch current docs and verify:
- The API surface matches what the PRD assumes
- Version numbers / compatibility claims are correct
- Performance claims are realistic (backed by benchmarks in docs)
- The recommended patterns still exist and aren't deprecated
- Produce a refinement report — structured feedback, not a rewrite.
Workflow
Phase 1: Technology Inventory
Extract every technology, library, and protocol mentioned in the PRD. For each one, note:
- What the PRD claims about it
- Whether a version is specified
- How it's used in the architecture
Phase 2: Documentation Validation
For each technology in the inventory, use Context7:
resolve-library-idto find the correct library IDquery-docswith specific questions derived from the PRD's claims
Focus your queries on:
- API correctness: Does the PRD describe the API accurately?
- Version currency: Is the PRD referencing current or deprecated APIs?
- Performance: Do docs/benchmarks support the PRD's performance assumptions?
- Integration: Can these technologies actually work together as described?
- Alternatives: Is there a better choice the PRD didn't consider?
Phase 3: Gap Analysis
Identify what the PRD is missing:
- Error handling / failure modes
- Security considerations beyond the obvious
- Operational concerns (deployment, monitoring, migration)
- Edge cases the architecture doesn't address
- Missing sections common in production PRDs
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 · 119 lines · 40 tokens per session scan A a9e791beee6e
prd-refiner is an agent published in the GitHub repository raghavwahi/semdex-mcp-server (0 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,128 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
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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.