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 AgentlyLabs/founder-skills --skill cro-auditgit clone --depth 1 https://github.com/AgentlyLabs/founder-skillsWrote 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/agentlylabs/founder-skills/cro-audit)<a href="https://agentmods.dev/skills/agentlylabs/founder-skills/cro-audit"><img src="https://agentmods.dev/badge/skills/agentlylabs/founder-skills/cro-audit/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/agentlylabs/founder-skills/cro-audit"><img src="https://agentmods.dev/badge/skills/agentlylabs/founder-skills/cro-audit.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 | $0.00229 | $0.03048 |
| Opus 5 | $0.00114 | $0.01524 |
| Sonnet 5 | $0.00046 | $0.00610 |
| Haiku 4.5 | $0.00023 | $0.00305 |
Grade A, and why
cro-audit 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 11d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRO Audit
Why this skill exists
Two things pass for conversion optimization, and both are worthless.
The first is the checklist. Thirteen principles, twenty-seven tips, "add urgency and social proof" — advice that could be written without ever loading the page. It is unfalsifiable, it applies equally to every site, and it produces a document the founder skims once and never opens again.
The second is the fake win. A test runs for four days, 380 visitors, 4.1% against 3.2%, someone declares a 28% lift and ships it. The confidence interval on that difference runs from −38% to +140%. The number was noise. The team now believes a false thing about their customers and will make the next three decisions from it.
This skill exists to avoid both. Two disciplines do all the work:
- Every finding cites a measurement taken from this page or this account. Not a
principle, not a heuristic — a number, with a key, recorded in
measurements.json. A claim you cannot attach a measurement to is an opinion, and opinions go in a clearly labeled section at the end or nowhere at all. - No lift is asserted without its arithmetic, and no test is proposed without its sample size. If the required sample takes eleven months to accumulate at this site's traffic, the honest recommendation is not to run the test. Saying so is the most valuable output this skill produces, and almost nobody says it.
The uncomfortable consequence, stated up front so it does not come as a surprise in the
report: most sites cannot A/B test. Below roughly 1,000 conversions per month you
cannot detect the effect sizes real changes produce, and pretending otherwise burns
months. For those sites the job is different — ship changes on evidence and judgment,
measure the funnel over long windows, and get your resolution from qualitative sources
instead. references/experiment-design.md gives the threshold arithmetic.
Step 0 — Scope
Establish these before measuring anything. Ask only what you cannot infer.
What ships with it
8 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.
- 11d ago First seen · 240 lines · 229 tokens per session scan A 91c8b8e390dc
cro-audit is a skill published in the GitHub repository AgentlyLabs/founder-skills (2 stars, last pushed 14d ago), licensed MIT. It adds 229 tokens to every session and 3,048 once invoked, about $0.0011 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…