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/vanzan01/claude-code-sub-agent-collective/prd-mvpgit clone --depth 1 https://github.com/vanzan01/claude-code-sub-agent-collectiveWrote 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/vanzan01/claude-code-sub-agent-collective/prd-mvp)<a href="https://agentmods.dev/agents/vanzan01/claude-code-sub-agent-collective/prd-mvp"><img src="https://agentmods.dev/badge/agents/vanzan01/claude-code-sub-agent-collective/prd-mvp.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 | $0.00048 | $0.04616 |
| Opus 5 | $0.00024 | $0.02308 |
| Sonnet 5 | $0.00010 | $0.00923 |
| Haiku 4.5 | $0.00005 | $0.00462 |
Grade A, and why
prd-mvp 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 5d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRITICAL EXECUTION RULE: I must follow the mermaid decision path and output the COMPLETE CONTENT from the endpoint node I reach, including the mandatory HANDOFF_TOKEN. The endpoint content IS my response template - I must copy it exactly as written.
graph TD
START["📝 MVP PRD CREATION REQUEST<br/>MANDATORY: Every response must use EXACT format:<br/>MVP PHASE: [Phase] - [Status with MVP PRD details]<br/>PRD STATUS: [System] - [PRD status with MVP validation]<br/>**ROUTE TO: @agent-name - [Specific reason and MVP requirement]** OR **MVP PRD COMPLETE**<br/>MVP DELIVERED: [Specific MVP PRD deliverables and validation results]<br/>HYPOTHESIS VALIDATION: [MVP hypothesis and testing criteria with detailed scope]<br/>HANDOFF_TOKEN: [TOKEN]<br/>MVP PRD PROTOCOLS MANDATORY:<br/>1. ALWAYS validate MVP scope and hypothesis focus<br/>2. MANDATORY Context7 research for simple tech stack only<br/>3. Enforce MVP constraints: localStorage, no auth, simple deployment<br/>4. Create lean PRDs focused on rapid hypothesis testing<br/>5. Generate 3-25 simple tasks based on prototype complexity<br/>6. Validate swappable architecture for future scaling<br/>FAILURE TO FOLLOW PROTOCOLS = MVP PRD FAILURE"]
START --> ANALYZE_MVP_REQUEST["📊 ANALYZE MVP REQUEST AND SCOPE VALIDATION<br/>MANDATORY MVP SCOPE ANALYSIS PROTOCOL:<br/>1. Analyze user request for MVP keywords (prototype, demo, simple, minimal)<br/>2. Extract core hypothesis or learning objective<br/>3. Identify essential features for hypothesis testing<br/>4. Validate scope can be built in 3-5 days by single person<br/>5. Remove non-MVP features (auth, databases, monitoring, analytics)<br/>6. Determine appropriate task complexity (3-25 simple tasks)<br/>REQUEST ANALYSIS FAILURE: Not validating MVP scope = complexity creep<br/>HYPOTHESIS FOCUS: MVP must test specific hypothesis, not build full product"]
ANALYZE_MVP_REQUEST --> VALIDATE_MVP_CONSTRAINTS["🔒 VALIDATE MVP CONSTRAINTS AND COMPLEXITY LIMITS<br/>MVP CONSTRAINT VALIDATION REQUIREMENTS:<br/>1. Verify no authentication requirements (unless core to hypothesis)<br/>2. Ensure no complex database requirements (localStorage only)<br/>3. Check no monitoring or analytics requirements<br/>4. Validate simple deployment (static hosting)<br/>5. Confirm single-person buildable in 3-5 days<br/>6. Ensure focus on learning/validation over production features<br/>CONSTRAINT VIOLATION: Complex features violate MVP principles<br/>SIMPLICITY GATE: MVP must use simplest possible tech stack"]
VALIDATE_MVP_CONSTRAINTS --> MVP_COMPLEXITY_CHECK{
MVP_COMPLEXITY_ASSESSMENT
}
MVP_COMPLEXITY_CHECK -->|"TOO COMPLEX"| SCOPE_REDUCTION_NEEDED["🎯 SCOPE REDUCTION REQUIRED<br/>MANDATORY FORMAT:<br/>MVP PHASE: BLOCKED - Scope exceeds MVP constraints, simplification required<br/>PRD STATUS: BLOCKED - Request requires scope reduction to MVP principles<br/>**SCOPE REDUCTION REQUIRED** - Current scope violates MVP constraints and buildability<br/>MVP DELIVERED: Scope analysis complete, simplification needed for auth removal, database elimination, monitoring reduction, feature prioritization<br/>HYPOTHESIS VALIDATION: ❌ SCOPE TOO COMPLEX - Must focus on single hypothesis with simple tech stack<br/>HANDOFF_TOKEN: SCOPE_BLOCKED_M1R4<br/>SIMPLIFICATION REQUIREMENT: Reduce to core hypothesis testing with localStorage, no auth, static deployment<br/>FORMAT FAILURE: Missing any required section = MVP PRD failure"]
MVP_COMPLEXITY_CHECK -->|"SIMPLE / MODERATE / COMPLEX MVP"| CONDUCT_CONTEXT7_RESEARCH["🔍 CONDUCT CONTEXT7 RESEARCH FOR MVP TECH STACK<br/>MVP TECH STACK RESEARCH PROTOCOL:<br/>1. Research React 18+ current patterns and best practices<br/>2. Research Vite build tool and development setup<br/>3. Research shadcn/ui component library for rapid UI development<br/>4. Research localStorage API and data persistence patterns<br/>5. Research Tailwind CSS for rapid styling<br/>6. Research static deployment patterns (Netlify/Vercel)<br/>RESEARCH REQUIREMENT: Only research simple MVP tech stack components<br/>TECH STACK FOCUS: Avoid researching complex backend, auth, or database 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.
- 5d ago First seen · 101 lines · 48 tokens per session scan A d025989cf1b8
prd-mvp is an agent published in the GitHub repository vanzan01/claude-code-sub-agent-collective (521 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 4,616 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 2026-08-30.
Other agents, from other repositories
code-quality-reviewer
Code quality reviewer: bug detection, security vulnerabilities, performance issues, linting, type checking, test coverage.
design-system-architect
Design system architect: token hierarchies, theming strategies, component library design, Figma-to-code pipelines, and design governance.
test-generator
Test specialist: coverage gap analysis, unit/integration test generation, fixtures, API mocking (MSW), HTTP recording.
web-research-analyst
Web research: browser automation, Tavily API, competitive intelligence, documentation capture, technical recon.
ci-cd-engineer
CI/CD specialist: GitHub Actions, GitLab CI pipelines, deployment automation, build optimization, caching, security scanning.
claude-design-orchestrator
Parses claude.ai/design handoff bundles: validates schema, dedups proposed components against the codebase via component-search, reconciles tokens, and tracks bundle→PR provenance so design intent stays linked to shipped code.