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 kumaran-is/claude-code-onboarding --skill ai-launch-checkgit clone --depth 1 https://github.com/kumaran-is/claude-code-onboardingWrote 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/kumaran-is/claude-code-onboarding/ai-launch-check)<a href="https://agentmods.dev/skills/kumaran-is/claude-code-onboarding/ai-launch-check"><img src="https://agentmods.dev/badge/skills/kumaran-is/claude-code-onboarding/ai-launch-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/kumaran-is/claude-code-onboarding/ai-launch-check"><img src="https://agentmods.dev/badge/skills/kumaran-is/claude-code-onboarding/ai-launch-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 | $0.00058 | $0.02003 |
| Opus 5 | $0.00029 | $0.01001 |
| Sonnet 5 | $0.00012 | $0.00401 |
| Haiku 4.5 | $0.00006 | $0.00200 |
Grade A, and why
ai-launch-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 6d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Feature Launch Check
Iron Law: Do not output GO if any checklist item is ❌. A written exception in the Decision Record with an owner and deadline is required for every ⚠️ item. Verbal assertions do not count as evidence for any item.
Run the unified pre-production launch checklist from the AI Playbook (Layer 4 §4.1). This consolidates the pre-flight questions, pre-production gate, kill-switch tests, and adversarial test catalog into one launch review.
Procedure
- Ask the user for the feature slug. Look for the Decision Record at
docs/ai-decisions/<feature-slug>.md.- If it does not exist: stop. Tell the user to run
/ai-decision-recordfirst. Do not proceed without one.
- If it does not exist: stop. Tell the user to run
- Read the Decision Record. Cross-check every item below against what the record says.
- For each checklist item below, ask the user to show evidence, not assert compliance. Examples of evidence:
- "Output Contract implemented" → point to the validation code; read it.
- "Eval set" → point to the file; show the size and a sample.
- "Kill switch tested" → show the test run log.
- Mark each item: ✅ verified / ⚠️ partial / ❌ missing.
- Do not pass the launch check if any item is ❌. Partial is allowed only when the user provides a written exception in the Decision Record with an owner and a deadline.
- Produce a launch decision: GO / NO-GO / GO-WITH-EXCEPTIONS with a written rationale.
The pre-flight (10 questions)
Walk through these first. Any "no" or "I don't know" is a NO-GO.
- 1. Can deterministic code solve this reliably? (If yes → why are we shipping AI?)
- 2. Is the input genuinely unstructured or ambiguous?
- 3. Does AI measurably beat code on accuracy, speed, cost, or UX?
- 4. Is the decision reversible, or is there a downstream verifier?
- 5. Off the critical latency path, or fast fallback exists?
- 6. What's the cost when AI is wrong, and who absorbs it?
- 7. Is human approval required for high-impact outcomes?
- 8. Can every AI output be audited and explained later?
- 9. Enough labeled examples for risk-tiered evaluation?
- 10. Deterministic fallback when AI fails or times out?
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.
- 6d ago First seen · 144 lines · 58 tokens per session scan A 397af9b32b1c
ai-launch-check is a skill published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 2,003 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 2026-09-03.
Other skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.