Borrowing it
Nothing to install: this file belongs to ingo-eichhorst/Irrlicht. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ingo-eichhorst/Irrlicht/main/.claude/skills/ir:onboarding-factory/SKILL.mdgit clone --depth 1 https://github.com/ingo-eichhorst/IrrlichtWrote 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/ingo-eichhorst/irrlicht/ir-onboarding-factory)<a href="https://agentmods.dev/skills/ingo-eichhorst/irrlicht/ir-onboarding-factory"><img src="https://agentmods.dev/badge/skills/ingo-eichhorst/irrlicht/ir-onboarding-factory/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/ingo-eichhorst/irrlicht/ir-onboarding-factory"><img src="https://agentmods.dev/badge/skills/ingo-eichhorst/irrlicht/ir-onboarding-factory.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 | $0.00232 | $0.04661 |
| Opus 5 | $0.00116 | $0.02330 |
| Sonnet 5 | $0.00046 | $0.00932 |
| Haiku 4.5 | $0.00023 | $0.00466 |
Grade A, and why
ir:onboarding-factory 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 7d 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 — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Irrlicht onboarding factory — dispatcher
This skill maintains the scenario × agent fixture matrix: for each behavior (a scenario row) and each agent CLI (a column), it judges whether the agent supports it, whether the daemon can observe it, and whether the recording harness can drive it — then captures a live recording and verifies it.
One iron rule: the factory owns replaydata/. The skill is pure
orchestration. It NEVER reads or writes catalog files, cell metadata, specs, or
recordings by hand — every operation is an of call, and of
validates schema + referential integrity before it touches disk. If you find
yourself about to jq, Edit, or Write something under replaydata/, stop:
there is an of verb for it.
Why a dispatcher of subagents. A full onboarding sweep runs hundreds of
shell invocations and dumps every events.jsonl / transcript.jsonl into the
transcript — enough to exhaust the parent's context long before the work is
done. So each cell's work is ONE Agent call that burns its OWN context and
returns a short summary. The parent decides which cells to touch; the
subagents do the work and report back. See
return-contract.md for the shared envelope (≤6 lines, ≤7 for record).
Overnight push-through mode (the maintainer's default for unattended runs)
Triggered by "push through", "everything", "onboard fully", "overnight", or any
unattended / scheduled run. The goal is a valid report and a reviewable PR by
morning, with every cell that can be observed actually observed — not just
the easy ones. Run fully autonomously: never call AskUserQuestion /
ExitPlanMode / block on a prompt mid-run — make the sensible call, document it,
and keep going. Emit a one-line status at each stage boundary; the final PR
body is the morning report.
This is more than the standard sweep. Work three passes until the matrix stops moving:
- Sweep — assess every cell, then record every
pending-recordcell (the normal dispatcher flow described below).
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.
- 7d ago Changed 0f1a1bda22cb
- 12d ago First seen · 340 lines · 232 tokens per session scan A e6e33ec1b425
ir:onboarding-factory is a skill published in the GitHub repository ingo-eichhorst/Irrlicht (98 stars, last pushed yesterday), licensed MIT. It adds 232 tokens to every session and 4,661 once invoked, about $0.0012 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 2026-08-30.
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…