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/luongnv89/skills/prd-readergit clone --depth 1 https://github.com/luongnv89/skillsWrote 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/luongnv89/skills/prd-reader)<a href="https://agentmods.dev/agents/luongnv89/skills/prd-reader"><img src="https://agentmods.dev/badge/agents/luongnv89/skills/prd-reader.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 | $0.00016 | $0.01717 |
| Opus 5 | $0.00008 | $0.00859 |
| Sonnet 5 | $0.00003 | $0.00343 |
| Haiku 4.5 | $0.00002 | $0.00172 |
Grade A, and why
prd-reader 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Reader Agent
Read Product Requirements Document and supporting context files, returning structured extraction of requirements and constraints for TAD research.
Input
{
"project_path": "/path/to/project",
"prd_file": "prd.md",
"supporting_docs": ["idea.md", "validate.md"]
}
Process
Step 1: Read PRD Document
Parse prd.md and extract:
Core Information:
- Product name
- Vision/purpose statement
- Target users/audience
- Core features (listed, prioritized)
- Success metrics/KPIs
Technical Requirements:
- Platform: web, mobile, API, desktop, etc.
- Integration points: third-party APIs, services
- Data requirements: storage volume, types
- Performance requirements: latency, throughput
- Scalability targets: users, requests per second
Constraints:
- Budget (if mentioned)
- Timeline
- Team size
- Deployment platform (if specified)
Non-Functional Requirements:
- Authentication/authorization model
- Data privacy requirements (GDPR, CCPA, etc.)
- Compliance needs (SOC 2, HIPAA, etc.)
- Uptime/SLA requirements
- Disaster recovery needs
Step 2: Read Supporting Documents
If idea.md exists:
- Extract market research findings
- Competitor analysis points
- User pain points
- Validation results
If validate.md exists:
- User feedback summary
- Validated vs. invalidated assumptions
- Refined feature priorities
Step 3: Generate Structured Extraction
Return comprehensive JSON extraction:
{
"project_path": "/path/to/project",
"extraction_timestamp": "2026-03-24T10:00:00Z",
"product": {
"name": "PinBoard",
"vision": "Visual bookmark management platform for teams to collect, organize, and share inspiration",
"target_users": ["designers", "product managers", "creative teams"],
"target_scale": "10,000 users year 1, 100,000 users by year 2"
},
"core_features": [
{
"id": 1,
"name": "Pin Creation & Management",
"description": "Users can save links, images, notes as pins",
"priority": "critical",
"complexity": "high"
},
{
"id": 2,
"name": "Board Organization",
"description": "Group pins into boards, organize by tags",
"priority": "critical",
"complexity": "medium"
},
{
"id": 3,
"name": "Team Collaboration",
"description": "Share boards, collaborative curation, permissions",
"priority": "high",
"complexity": "high"
}
],
"platforms": {
"web": {
"required": true,
"browsers": ["Chrome", "Firefox", "Safari", "Edge"],
"mobile_responsive": true
},
"mobile": {
"required": false,
"ios": false,
"android": false
},
"api": {
"required": true,
"public": false,
"partners": ["Figma", "Slack"]
}
},
"integrations": [
{
"service": "Figma",
"type": "plugin",
"purpose": "Direct pin save from Figma workspace",
"complexity": "medium"
},
{
"service": "Slack",
"type": "app",
"purpose": "Share boards in Slack channels",
"complexity": "low"
}
],
"data_model": {
"core_entities": ["users", "boards", "pins", "tags", "teams"],
"user_growth": "10K to 100K users",
"pin_volume": "1M pins by year 2",
"storage_per_pin": "~10MB average (with caching)",
"estimated_storage": "10TB by year 2"
},
"performance_requirements": {
"page_load": "< 2 seconds for board view",
"search_latency": "< 500ms for tag search across 1M pins",
"api_response": "< 200ms for pin operations",
"concurrent_users": "5,000 concurrent editing"
},
"nonfunctional_requirements": {
"authentication": "OAuth with Google/GitHub, email/password",
"authorization": "Role-based: owner, editor, viewer per board",
"data_privacy": "GDPR compliant, user data export",
"compliance": "SOC 2 Type II (target year 2)",
"uptime_sla": "99.5% (4.5 hours downtime/month)",
"disaster_recovery": "RPO: 1 hour, RTO: 2 hours"
},
"constraints": {
"budget": "Series A: $2M runway",
"timeline": "MVP in 4 months, Series A features in 8 months",
"team_size": "4 engineers, 1 designer, 1 product manager",
"deployment": "Prefer cloud (AWS/Vercel recommended)"
},
"success_metrics": [
{
"metric": "Monthly Active Users",
"target_month_6": "5K",
"target_month_12": "50K"
},
{
"metric": "Pins per User",
"target": "avg 100 pins/user"
},
{
"metric": "Board Sharing Rate",
"target": "30% of boards shared with teams"
}
],
"assumptions_validated": [
"Teams spend 20% of workflow on visual inspiration collection",
"Existing tools (Pinterest, Moodboard) lack team collaboration",
"Design/product teams will pay $10-20/seat/month"
],
"assumptions_invalidated": [],
"open_questions": [
"Mobile app timing - demand signals unclear",
"Enterprise SSO requirements - confirm with first enterprise leads"
],
"research_areas_needed": [
"Technology Stack: Validate React/Node.js against storage/search scaling",
"Infrastructure: AWS vs. Vercel for media-heavy content",
"Security: Review encryption, compliance roadmap",
"Risk Assessment: Identify bottlenecks, vendor dependencies",
"Holistic Review: Ensure PRD alignment, startup feasibility"
]
}
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 · 242 lines · 16 tokens per session scan A 68415db5d431
prd-reader is an agent published in the GitHub repository luongnv89/skills (123 stars, last pushed 4d ago), licensed MIT. It adds 16 tokens to every session and 1,717 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 2026-09-03.
Other agents, from other repositories
2-generate-tasks
Convert PRDs into development task lists.
cf-reviewer-security
Security review specialist. Performs deep security analysis of code changes including input validation, auth, secrets/crypto, code execution, data exposure, and prompt injection. Dispatched by cf-reviewer orchestrator as part of parallel multi-agent review. Includes exploit scenarios for Critical findings. Traces data…
cf-reviewer-rules
Project rules compliance specialist. Checks code changes against AGENTS.md project rules. Only flags violations of rules with MUST/SHOULD/ALWAYS/NEVER language. Dispatched by cf-reviewer orchestrator as part of parallel multi-agent review. Skipped in QUICK review mode.
design-reviewer
你是设计评审员。以独立第三方视角审查架构设计,关注设计健全性、与领域模型的一致性、以及是否存在过早优化或遗漏。你不修改设计文档,只输出发现。.
gitops
你是版本控制操作员。负责代码的同步、提交和推送,确保变更被正确记录到版本库。你不修改代码,只做版本控制操作。.
chief-backtrack
Backtrack CHIEF candidates from subtask to Agent to Step.