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/create-agent/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/create-agent)<a href="https://agentmods.dev/skills/ingo-eichhorst/irrlicht/create-agent"><img src="https://agentmods.dev/badge/skills/ingo-eichhorst/irrlicht/create-agent/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/create-agent"><img src="https://agentmods.dev/badge/skills/ingo-eichhorst/irrlicht/create-agent.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 | $0.00081 | $0.01868 |
| Opus 5.5 | $0.00032 | $0.00747 |
| Sonnet 5.5 | $0.00016 | $0.00374 |
| Haiku 4.5 | $0.00008 | $0.00187 |
Grade A, and why
ir:onboarding-factory/create-agent 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
create-agent
You run as a focused subagent with no parent context. Do the research yourself (web + file access). This task runs NO recording and invokes NO agent CLI. When done, return only the "Return contract" block.
What this does
Adds a new agent COLUMN to the matrix — the counterpart to create-scenario's
ROW. It does three things, all up front, before any cell is assessed or
recorded:
- Register the column via
of agent add— writesreplaydata/agents/<slug>/metadata.json{id, name, provider, prerequisites[]}and registers the agent in the catalogmeta.min_versionssoof statusand the viewer treat it as onboarded. - Scaffold the interactive driver from the template so
recordhas something to drive. - Predict driver-needs — across the scenario catalog, name the step types
the agent's recipes will need, so the driver gaps are known before the
assess sweep instead of being rediscovered one
recordround-trip at a time.
Prerequisite: the Go adapter (maintainer / code task)
The daemon only observes an agent it has an adapter for. Wiring a new adapter is
a Go change (a package under core/adapters/inbound/agents/<slug>/ exporting
Agent(), plus one line in the All() slice in
core/adapters/inbound/agents/all.go). That
is out of scope for this skill. If no adapter exists yet, say so in notes:
the column can be registered and the driver scaffolded, but recordings can't be
observed until the adapter lands. Don't block — register what you can.
Steps
1. Research the agent
Use web search + fetch on the agent's official site, changelog, and source repo. Determine:
- id — kebab slug (the column key, the
replaydata/agents/<id>/dir). - name — display name (e.g. "Claude Code").
- provider —
anthropic/openai/google/ … (the model vendor). - prerequisites — the human actions a recording needs that the subagent
can't perform: auth mode (subscription vs API key), env vars, a local model
server, a config file. These become
--prereqstrings and are surfaced byof record prereq-checkbefore every recording. Be concrete — "switch the CLI from subscription auth to an API key (ANTHROPIC_API_KEY)" beats "set up auth". - transport shape — does it write an append-only transcript under
$HOME(FilesUnderRoot), one transcript per cwd (FilesUnderCWD), or a structured store / SQLite (ProcessOwnedStore)? This determines what the daemon can see and feeds the driver scaffold + later assessments. Read sibling adapters undercore/adapters/inbound/agents/for the three variants.
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 · 166 lines · 81 tokens per session scan A b133bfe3b51b
ir:onboarding-factory/create-agent is a skill published in the GitHub repository ingo-eichhorst/Irrlicht (101 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 1,868 once invoked, about $0.0003 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
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…