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 buildfastwithai/gen-ai-experiments --skill launchauditgit clone --depth 1 https://github.com/buildfastwithai/gen-ai-experimentsWrote 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/buildfastwithai/gen-ai-experiments/launchaudit)<a href="https://agentmods.dev/skills/buildfastwithai/gen-ai-experiments/launchaudit"><img src="https://agentmods.dev/badge/skills/buildfastwithai/gen-ai-experiments/launchaudit/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/buildfastwithai/gen-ai-experiments/launchaudit"><img src="https://agentmods.dev/badge/skills/buildfastwithai/gen-ai-experiments/launchaudit.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 | $0.00123 | $0.01489 |
| Opus 5.5 | $0.00049 | $0.00596 |
| Sonnet 5.5 | $0.00025 | $0.00298 |
| Haiku 4.5 | $0.00012 | $0.00149 |
Grade A, and why
launchaudit 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LaunchAudit
Audit the startup as a first-time visitor and launch reviewer. Infer the product before asking questions, inspect the public experience, distinguish evidence from inference, and deliver exact fixes in a standalone report.
Language
- Match the user's language in conversation.
- Write the report in the user's language unless they request another language.
- Preserve product names, URLs, interface labels, and source quotations when accuracy requires it.
Read the references
- Read references/evaluation-framework.md before every audit.
- Read references/report-schema.md before creating the JSON source or HTML report.
Select the mode
standard— Inspect the primary public journey and create the full report. Use by default.quick— Inspect the main page, primary CTA, and most important trust path. Return the verdict and top five fixes.deep— Inspect relevant product, pricing, documentation, trust, install, and conversion paths on desktop and mobile.technical— Emphasize broken paths, metadata, responsive behavior, accessibility signals, console errors, and visible performance risks.before-after— Compare two versions with the same criteria and clearly attribute improvements or regressions.
Do not imply that a public-page audit can verify private analytics, billing, production monitoring, legal compliance, or authenticated product behavior.
Workflow
1. Inspect before asking
- Open the supplied URL or artifact and determine what the startup appears to do, who it serves, the promised outcome, the mechanism, the primary action, and the likely launch stage.
- Prefer the integrated browser for live sites and localhost apps. Inspect visible page state before interacting.
- Follow relevant public navigation and CTA destinations. Do not submit forms, create accounts, begin trials, install software, make purchases, or transmit user data unless the user explicitly authorizes that action.
- Use screenshots when visual hierarchy, responsive behavior, clipping, overlap, or interaction state matters.
- Inspect a supplied repository only when it is in scope. Treat repository findings as product evidence, not proof that production uses the same version.
- Ask only about missing information that would materially change the verdict. The default request should work with only a URL.
What ships with it
5 files 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 · 160 lines · 123 tokens per session scan A e5091be9f267
launchaudit is a skill published in the GitHub repository buildfastwithai/gen-ai-experiments (789 stars, last pushed 1mo ago), licensed MIT. It adds 123 tokens to every session and 1,489 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.