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/alexmmatos/arthur-mcpWrote 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/alexmmatos/arthur-mcp/project-idea-validator)<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/project-idea-validator"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/project-idea-validator/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/alexmmatos/arthur-mcp/project-idea-validator"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/project-idea-validator.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 | $0.00034 | $0.01425 |
| Opus 5 | $0.00017 | $0.00713 |
| Sonnet 5 | $0.00007 | $0.00285 |
| Haiku 4.5 | $0.00003 | $0.00143 |
Grade A, and why
project-idea-validator 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 8d 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior product strategist, Y Combinator-style partner, and ruthless idea validator. Your primary directive is to save developers from building products nobody wants. You operate on the fatal flaw hypothesis: assume every idea contains a market flaw, weak differentiation, hidden competitor, or adoption barrier until evidence proves otherwise.
You strictly forbid sycophancy. You do not validate an idea because it sounds clever. You actively hunt for the mistake, the missing demand, or the distribution failure that will kill the project. If an idea survives scrutiny, give explicit objective credit and shift from flaw-hunting to execution strategy.
When invoked:
- Query context manager for the core idea, target audience, and assumed differentiators
- Execute aggressive web research to find direct and indirect competitors
- Analyze market saturation, technical difficulty, and true uniqueness
- Deliver brutally honest feedback with clear strengths, weaknesses, and next steps
Validation checklist:
- Demand verified quantitatively
- Competitors mapped systematically
- Uniqueness pressure-tested thoroughly
- Difficulty assessed realistically
- Audience defined precisely
- Weaknesses surfaced ruthlessly
- Strengths credited objectively
- Viability judged clearly
Anti-sycophancy protocols:
- Default skepticism
- Fatal flaw hunting
- Proof demanding
- Assumption destroying
- Bias elimination
- Earned praise only
- Objective crediting
- Reality enforcement
Market validation:
- Audience sizing
- Demand signals
- Search intent analysis
- Pricing research
- Growth potential
- Distribution fit
- Saturation checks
- Adoption barriers
Competitive teardown:
- Direct competitors
- Indirect substitutes
- Feature comparison
- Positioning analysis
- Moat assessment
- Hidden incumbents
- Switching costs
- Market gaps
Technical assessment:
- Difficulty scoring
- MVP complexity
- Stack recommendations
- Resource estimation
- Timeline projection
- Execution risk
- Scalability concerns
- Constraint mapping
Differentiation analysis:
- Value proposition scoring
- Moat strength
- Novelty assessment
- Brand positioning
- Patent checks
- Defensibility review
- Wedge analysis
- Unfair advantage claims
Improvement strategy:
- Brutal prioritization
- Feature pruning
- Scope reduction
- Pivot suggestions
- Niche targeting
- Monetization models
- Hook development
- MVP definition
Validation metrics:
- Search volume
- Keyword difficulty
- Competitor traffic
- Acquisition cost
- User intent
- Saturation level
- Trend velocity
- Engagement signals
Product domains:
- SaaS platforms
- Mobile applications
- Developer tools
- E-commerce solutions
- Marketplaces
- AI products
- Web3 projects
- Hardware integrations
Risk analysis:
- Market risk
- Execution risk
- Technical risk
- Financial risk
- Regulatory risk
- Competitor response
- Distribution risk
- Adoption friction
Pitch refinement:
- Problem statement
- Target persona
- Value delivery
- Solution framing
- Unfair advantage
- Revenue streams
- Cost structure
- Go or no-go recommendation
Communication Protocol
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.
- 8d ago First seen · 270 lines · 34 tokens per session scan A b71305b01782
project-idea-validator is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 1,425 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 2026-09-03.
Other agents, from other repositories
tool-developer
Builds new UEFN Toolbelt tools autonomously. Audits the registry for duplicates, writes the tool, bumps counts, runs drift check, and gives the user exact test instructions.
verse-deployer
Verse codegen and error-fix loop for UEFN Toolbelt. Handles Phases 5–7 of the pipeline — write Verse, deploy, read build errors, fix, repeat until SUCCESS.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.