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 heyparsadev/claude-idea-validator --skill stage-mapgit clone --depth 1 https://github.com/heyparsadev/claude-idea-validatorWrote 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/heyparsadev/claude-idea-validator/stage-map)<a href="https://agentmods.dev/skills/heyparsadev/claude-idea-validator/stage-map"><img src="https://agentmods.dev/badge/skills/heyparsadev/claude-idea-validator/stage-map/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/heyparsadev/claude-idea-validator/stage-map"><img src="https://agentmods.dev/badge/skills/heyparsadev/claude-idea-validator/stage-map.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 | $0.00197 | $0.02018 |
| Opus 5.5 | $0.00079 | $0.00807 |
| Sonnet 5.5 | $0.00039 | $0.00404 |
| Haiku 4.5 | $0.00020 | $0.00202 |
Grade A, and why
stage-map 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 1mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stage map — where you actually are, and what that stage demands
The lifecycle from The Founder's Playbook: Building an AI-Native Startup (Anthropic, 2026). Four stages, each with one goal, one exit condition, and a characteristic set of ways founders get it wrong.
The premise: AI erased the assumption that each new phase requires a bigger team, a different skill set, and a fresh funding round. The founder's job shifts from individual contributor to orchestrator. What didn't change is the sequence — and the most expensive mistake in the AI era is running a stage ahead of the evidence.
Diagnose before advising
Founders routinely self-report a stage ahead of where their evidence puts them, because building is now so cheap that the artifacts of a later stage appear long before its evidence does. Diagnose from exit criteria, not from what exists.
Ask (batch these, don't interrogate):
- Have you talked to people with this problem who aren't friends or investors? How many?
- Is anything shipped, and does anyone outside your circle use it?
- Do users come back unprompted — without you nudging them?
- Is anyone paying? Do you know your CAC, LTV, and payback period?
- What are you personally doing every day right now?
Then place them by the last exit condition genuinely met, and say so plainly when that's earlier than they assumed. Having a working product does not make someone MVP-stage; having evidence does.
The four stages
Idea — "Is this worth building?"
- Goal: research-oriented validation — solid evidence that a real problem exists and that the proposed solution addresses it, before committing resources to building.
- Exit: problem–solution fit. Yes to all three: (1) the problem is real and specific — you can name who has it, how often, how severely, what they do today; (2) the solution addresses the problem validation revealed, not the one assumed; (3) enough signal that committing to an MVP is a reasoned decision rather than an act of faith.
- Failure modes: mistaking building for validating (a prototype is a conversation prop, not evidence — 42% of startups failed building something nobody wanted, before AI made building free) · premature scaling (agentic tools will refactor a flawed premise with the same enthusiasm as a good one) · loss of objectivity (confirmation bias now comes with a research engine).
- Run it:
/founder-playbook:idea-stage
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 79 lines · 197 tokens per session scan A 8bc5b0b83be0
stage-map is a skill published in the GitHub repository heyparsadev/claude-idea-validator (2 stars, last pushed 2mo ago), licensed MIT. It adds 197 tokens to every session and 2,018 once invoked, about $0.0008 per session on Opus 5.5. 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
first-customer-finder
Find evidence-backed potential first customers, beta users, or design partners from public demand signals. Use for product-specific prospect research, qualified shortlists, source-grounded outreach drafts, and follow-up searches refined by the user's feedback and local prospect history. Does not send outreach…
gingiris-user-interview
A playbook for interviewing users and operating an early product launch, including screening participants, running interviews, testing beta versions, and reviewing churn. It is based on a described process for finding product-market fit, meaning a product consistently meeting a real user need.
gr-user-interview
A framework for interviewing users to discover product-market fit, meaning a strong match between a product and a real user need.
review
5-pass structured code review — correctness, security, performance, readability, consistency.
pr-review
Comprehensive PR review across six dimensions — cost impact, environment drift, ownership gaps, SOC 2 compliance, deprecated API / version hygiene, and rollback feasibility. Each mode inspects the diff and current file state, reports findings with severity, and recommends concrete fixes. Use when preparing a PR for…
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.