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 a2ngerer/claude_onboarding_agent --skill checkupgit clone --depth 1 https://github.com/a2ngerer/claude_onboarding_agentWrote 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/a2ngerer/claude_onboarding_agent/checkup)<a href="https://agentmods.dev/skills/a2ngerer/claude_onboarding_agent/checkup"><img src="https://agentmods.dev/badge/skills/a2ngerer/claude_onboarding_agent/checkup/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/a2ngerer/claude_onboarding_agent/checkup"><img src="https://agentmods.dev/badge/skills/a2ngerer/claude_onboarding_agent/checkup.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 | $0.00077 | $0.05765 |
| Opus 5 | $0.00039 | $0.02882 |
| Sonnet 5 | $0.00015 | $0.01153 |
| Haiku 4.5 | $0.00008 | $0.00577 |
Grade B, and why
checkup scanned grade B with 1 finding 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 9d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- `./.claude/settings.json` (search for `_onboarding_agent` key) How it starts
The opening of the file, as written. The whole thing — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Checkup — Single Maintenance Entrypoint
/checkup is the single user-facing maintenance entrypoint for an existing Claude setup. It runs /audit-setup internally, weighs findings + meta age + deprecated-model anchors, and either prints a short "fine-as-is" summary, hands off to /upgrade-setup, or invokes /onboarding --rebuild.
Call /checkup whenever you want to know whether your existing setup still matches current best practices. You never need to decide between /audit-setup and /upgrade-setup yourself — /checkup picks the right next step for you.
Power users may still invoke /audit-setup or /upgrade-setup directly when they already know which tool they want. Both skills keep their original behaviour and can be called independently. /checkup remains the canonical path for normal use.
This skill owns one decision: given an existing Claude setup, should the user rebuild it, improve it, or leave it fine-as-is? It then hands off to the appropriate skill. It does not audit (delegates to /audit-setup), does not apply changes (delegates to /upgrade-setup), does not scaffold (delegates to /onboarding).
The skill is a pure router. The only artifact it writes is an append-only line in .claude/checkup-log.md per invocation.
Language
Detect language from the user's first message in this invocation and respond in it throughout. All file content and log lines stay in English (repo language rule).
Argument parsing
The invocation may contain --no-delegate anywhere in the argument string (as a flag, not a value).
- If present: set
no_delegate: true. Stages 1–5 run normally, but Stage 6 prints the verdict and exits without invoking/onboarding,/upgrade-setup, or/audit-setupfor any follow-up. (Testing aid — does not suppress the Stage 3/audit-setupaudit call, which is required for a real verdict.) - Otherwise: set
no_delegate: false.
Any other argument is ignored silently (forward compatibility).
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.
- 9d ago First seen · 405 lines · 77 tokens per session scan B 18dd44500335
checkup is a skill published in the GitHub repository a2ngerer/claude_onboarding_agent (5 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 5,765 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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…