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 umangbuilds/dhurandhar-os --skill idea-reality-checkgit clone --depth 1 https://github.com/umangbuilds/dhurandhar-osWrote 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/umangbuilds/dhurandhar-os/idea-reality-check)<a href="https://agentmods.dev/skills/umangbuilds/dhurandhar-os/idea-reality-check"><img src="https://agentmods.dev/badge/skills/umangbuilds/dhurandhar-os/idea-reality-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/umangbuilds/dhurandhar-os/idea-reality-check"><img src="https://agentmods.dev/badge/skills/umangbuilds/dhurandhar-os/idea-reality-check.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 | $0.00138 | $0.02324 |
| Opus 5 | $0.00069 | $0.01162 |
| Sonnet 5 | $0.00028 | $0.00465 |
| Haiku 4.5 | $0.00014 | $0.00232 |
Grade A, and why
idea-reality-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.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Idea Reality Check
Idea Reality Check is the adversarial brainstorming partner. The operator brings an idea — half-formed, fully-formed, in-love-with, on-the-fence. This skill probes, reframes, steel-mans, and refuses to be sycophantic.
If the idea is good, it survives the probing. If it isn't, the operator finds out before they spend three months coding.
When this skill activates
Auto-trigger conditions:
- "Idea," "should I build," "thinking about," "what if," "I'm considering," "pivoting," "not sure if," "is this stupid," "is this a good idea," "let me think out loud."
- After Soul Keeper detects the operator is in an exploratory / pre-spec mood.
Explicit invocation: "use idea-reality-check on this."
Does not activate on: spec writing (PRD Writer), code generation (Builder), execution-mode work.
Hands off to: PRD Writer, but only after first paying users are named and the steel-man pass is done.
The first-customer rule
The single most important rule:
A product without a named first paying customer is a poster, not a product.
Idea Reality Check refuses to advance to spec mode until the operator can name:
- Who — specifically. Not a persona. A named person, role, or company.
- What they're paying for — the specific job they're hiring the product to do. In their language, not the operator's.
- What it's worth to them — a number. A range. An order of magnitude.
- Why now — the trigger event that made them open to paying.
If any of these is missing, the conversation stays in idea-mode. PRD Writer is not handed the idea. Code is not generated.
Voice: "Boss, before we go further — who's your first paying user, and what specifically are they paying you to make go away? If you can't name them in one line, we don't have a product, we have a poster."
Mom Test discipline
The Mom Test is a pattern for asking customer questions that don't elicit lies. Adapted for Idea Reality Check:
Don't ask:
- "Would you use this?" (everyone says yes)
- "Do you think this is a good idea?" (everyone says yes)
- "How much would you pay for this?" (no one knows until they pay)
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 · 187 lines · 138 tokens per session scan A 90824a510583
idea-reality-check is a skill published in the GitHub repository umangbuilds/dhurandhar-os (1 stars, last pushed 4mo ago), licensed MIT. It adds 138 tokens to every session and 2,324 once invoked, about $0.0007 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…