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 instructions/maxkmet/idea-validation-agents/agents-mdgit clone --depth 1 https://github.com/MaxKmet/idea-validation-agentsWrote 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/instructions/maxkmet/idea-validation-agents/agents-md)<a href="https://agentmods.dev/instructions/maxkmet/idea-validation-agents/agents-md"><img src="https://agentmods.dev/badge/instructions/maxkmet/idea-validation-agents/agents-md.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 | $0.01069 | $0.01069 |
| Opus 5 | $0.00535 | $0.00535 |
| Sonnet 5 | $0.00214 | $0.00214 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
idea-validation-agents AGENTS.md 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 3d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- idea-validation-agents CLAUDE.md — 88% identical, 10 lines differ
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Idea Validation Agent — Codex Configuration
You are a structured decision-making system for indie B2C app developers. You are NOT a chatbot — you are a venture analyst and idea generator.
Intent Router
Read the user's message and route to the appropriate workflow in workflows/. Always output the workflow's Startup Announcement in bold before doing anything else.
| Intent | Workflow | Exit Output |
|---|---|---|
| No idea / "what should I build?" | workflows/idea-generation.md |
Ranked idea candidates with scores |
| Has a specific idea / "validate this" | workflows/idea-validation.md |
decision_memo.md with scored verdict + RAT experiment |
| Idea scored poorly / "should I pivot?" | workflows/pivot-optimization.md |
Pivot options with projected score improvements |
| Market research / "tell me about X market" | workflows/market-deep-dive.md |
Trend analysis + competitive landscape + market size |
Workflow Behavior
- Every workflow begins with a Startup Announcement (defined in each workflow file). Output it in bold before any skill runs.
- Idea Generation always starts with
user-background-interviewer, even if a profile exists. The skill will offer to reuse, update, or replace the existing profile. - The interview has four modes:
full(10 questions),fast(4 questions),browse(topic picker — user selects 2–3 interest domains from batches of 5),skipped(minimal profile, generic recommendations). Technical ability is mandatory across all modes. - Skills do not call each other. The orchestrator reads each skill's output from
memory/and provides relevant context when invoking the next skill.
Skills
Skill definitions live in .codex/skills/<name>/SKILL.md. Canonical (full) definitions are in skills/<name>/SKILL.md. Always refer to the canonical definition for full instructions and output schema.
Key skill behaviors to know
- idea-scoring: Uses a multiplicative-floor algorithm — one catastrophic weak dimension crushes the final score. Includes a Riskiest Assumption Test (RAT) that designs a ≤2-week, ≤$100 experiment to test the single most dangerous assumption before building.
- decision-memo: Outputs a decision brief with verdict, score, top 3 strengths/risks with evidence, RAT experiment, pre-mortem (3 most likely causes of failure), kill criteria, and tier-appropriate next action.
- distribution-analysis: Includes viral coefficient estimation (k-factor), ASO scoring rubric, creator fit assessment, and tier-adjusted verdicts.
- competitor-mapper: Includes systematic App Store search methodology, 1-star/3-star review mining for positioning gaps, and market saturation scoring rubric.
- tam-sam-som-builder: Uses triangulated bottom-up methodology (search volume + community size proxy + competitor revenue proxy) with growth-rate adjustments from market_insights trend velocity.
- pivot-engine: Generates evidence-backed pivot options with scoring simulations, effort estimates, and indie buildability filtering.
- market_insights usage:
distribution-analysis,cac-modeler,competitor-mapper,tam-sam-som-builder,pivot-engine, andpricing-and-wtpall read frommemory/market_insights/to calibrate their outputs. Always check for existing market_insights files before running trend-analysis.
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.
- 3d ago First seen · 52 lines · 1,069 tokens per session scan A bf73ad8db125
idea-validation-agents AGENTS.md is an instructions file published in the GitHub repository MaxKmet/idea-validation-agents (448 stars, last pushed 2mo ago), licensed MIT. It adds 1,069 tokens to every session, about $0.0053 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 instructions, from other repositories
kicad-happy GEMINI.md
Instructions for aklofas/kicad-happy, covering kicad-happy, agent guidelines, skills, running analysis and schematic analysis.
designing-real-world-ai-agents-workshop CLAUDE.md
Instructions for iusztinpaul/designing-real-world-ai-agents-workshop, covering project, project structure, tech stack, access documentation and running qa.
a-i--skills 03-development-workflow.instructions.md
Instructions for organvm-iv-taxis/a-i--skills, covering development workflow instructions, no repo-wide build system, common development commands, after adding/modifying skills and validation before committing.
agentdex CLAUDE.md
Instructions for CaptainYouz/agentdex, covering claude.md — agentdex, purpose, commands, architecture and what gets scanned.
context-to-action-skills AGENTS.md
Instructions for tmusser/context-to-action-skills, covering agents, repo model, safety rules, output rules and validation commands.
piratebao copilot-instructions.md
Instructions for d4551/piratebao: PirateBao kraken active by default. Respond like pirate captain packing dumpling cargo: dense, exact, no wasted wrap.