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 skills add mnemox-ai/idea-reality-mcp --skill idea-checkgit clone --depth 1 https://github.com/mnemox-ai/idea-reality-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/skills/mnemox-ai/idea-reality-mcp/idea-check)<a href="https://agentmods.dev/skills/mnemox-ai/idea-reality-mcp/idea-check"><img src="https://agentmods.dev/badge/skills/mnemox-ai/idea-reality-mcp/idea-check/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/skills/mnemox-ai/idea-reality-mcp/idea-check"><img src="https://agentmods.dev/badge/skills/mnemox-ai/idea-reality-mcp/idea-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.00276 |
| Opus 5 | $0.00026 | $0.00138 |
| Sonnet 5 | $0.00011 | $0.00055 |
| Haiku 4.5 | $0.00005 | $0.00028 |
Grade A, and why
idea-check 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 12d 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.
What it actually says
Idea Reality Check
When to use
- Starting a new project or side project
- Evaluating whether to build or buy
- Researching competitors before a sprint
- Validating a feature idea before implementation
Instructions
- Ask the user for a natural-language description of their idea
- Call the
idea_checkMCP tool with the idea text - Use
depth="quick"for fast checks (GitHub + HN),depth="deep"for comprehensive analysis (all 5 sources) - Present the reality_signal score (0-100) and interpret it:
- 0-30: Low competition — green light to build
- 31-60: Moderate competition — differentiation needed
- 61-80: High competition — find a niche or pivot
- 81-100: Very high competition — consider contributing to existing projects instead
- List the top 3 competitors with star counts and descriptions
- Share the pivot_hints for actionable next steps
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.
- 12d ago First seen · 25 lines · 53 tokens per session scan A 617bd97c2040
idea-check is a skill published in the GitHub repository mnemox-ai/idea-reality-mcp (815 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 276 once invoked, about $0.0003 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 skills, from other repositories
agent-idea-feed
Turns concrete tasks from seven fixed public sources into a one-off or daily feed of interesting complete-task Agent ideas. Use when the user wants Agent ideas from Upwork-style marketplaces or chinese-independent-developer, especially when every source must contribute three concise, unseen ideas without validation or…
instrument-ui
The visual system for this project — an instrument, not a dashboard. Covers density, monospaced numerals, colour as signal, motion tied to real values, and the specific patterns that are banned because they read as machine-generated. Use this skill for every frontend task: components, layout, typography, colour…
data-integrity
What this project is allowed to claim in public — the anchoring rule for AI-generated summaries, confidence states, attribution, and the wording of every published number. Use this skill whenever writing an LLM prompt, rendering generated prose, labelling a metric, designing a badge or status, drafting social posts…
free-tier-guard
Hard infrastructure ceilings for this project — GitHub API rates, GitHub Actions behaviour, Cloudflare Pages build quotas, Groq limits, and forbidden platforms. Use this skill before choosing any hosting provider, database, scheduler, or LLM provider; before changing polling frequency or the number of watched…
signal-collector
How the data agent fetches, stores, and schedules GitHub signals for this project — the tiered 4-hourly cadence, conditional requests, live state versus historical ledger, spike baselines, and failure tolerance. Use this skill whenever writing or modifying any collector, the GitHub Actions workflow, the ledger schema…
sighttrue
Take a dated reading before adopting a dependency, base image, runtime version, AI model or hosting provider. Use when adding or upgrading a package, choosing a Docker base image or language version, picking a model, or answering whether something is still maintained, still supported, or still shipping.