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 onboardinggit 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/onboarding)<a href="https://agentmods.dev/skills/a2ngerer/claude_onboarding_agent/onboarding"><img src="https://agentmods.dev/badge/skills/a2ngerer/claude_onboarding_agent/onboarding/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/onboarding"><img src="https://agentmods.dev/badge/skills/a2ngerer/claude_onboarding_agent/onboarding.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 | $0.00041 | $0.06181 |
| Opus 5 | $0.00020 | $0.03090 |
| Sonnet 5 | $0.00008 | $0.01236 |
| Haiku 4.5 | $0.00004 | $0.00618 |
Grade B, and why
onboarding 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.
- Otherwise, search for the regex `<!--\s*onboarding-agent:start` in `./CLAUDE.md`, `./AGENTS.md`, and the key `"_onboarding_agent"` in `./.claude/settings.json`. If any match, treat as "marker-only" detection (no meta f How it starts
The opening of the file, as written. The whole thing — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Onboarding Agent
Welcome. This skill scans your project, asks you one question, and then configures Claude exactly the way you need it.
Common rationalizations
The following shortcuts look reasonable but break the onboarding contract. Do not take them.
| Rationalization | Why it does not apply |
|---|---|
| "The repo is simple — skip the interview" | Even small setups benefit from an explicit CLAUDE.md section; the interview is 3–7 questions and takes under a minute. |
| "The user seems expert — generate everything at once" | One question at a time is the contract; experts answer fast anyway and can always press Enter without reading the detail. |
| "Skip the scan, I can guess the stack" | The repo scan is cheap and prevents wrong-stack artifacts being generated and then undone. |
| "An existing CLAUDE.md means setup is done" | Existing files get extended with a new delimited section, never skipped or overwritten — Step 1a handles early-exit logic explicitly. |
| "I know the use case from the question — skip Step 3" | Step 3 presents the full option list so the user can correct an inference; bypassing it removes the user's only confirmation gate. |
| "The user picked 'not sure' — just recommend the most common path" | Step 4 runs a short decision tree; it reaches a recommendation in at most 3 questions without defaulting to an arbitrary choice. |
Argument parsing
The invocation may contain --rebuild anywhere in the argument string (as a flag, not a value).
- If present: set
rebuild_mode: true. Step 1a's early-exit is skipped; existing onboarding-agent-managed files are backed up first (see Step 1b), then the normal flow runs and produces fresh artifacts. - Otherwise: set
rebuild_mode: false.
Any other argument is ignored silently.
Step 1: Detect Language
Read the user's first message. Detect the language (e.g., English, German, Spanish, French). Respond in that language for the entire session. All generated file comments also use that language. Technical field names, tool names, and code remain in English regardless of detected language.
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 · 417 lines · 41 tokens per session scan B 6d8563a9182e
onboarding is a skill published in the GitHub repository a2ngerer/claude_onboarding_agent (5 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 6,181 once invoked, about $0.0002 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…