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:fleet/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-fleet)<a href="https://agentmods.dev/skills/ingo-eichhorst/irrlicht/ir-fleet"><img src="https://agentmods.dev/badge/skills/ingo-eichhorst/irrlicht/ir-fleet/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-fleet"><img src="https://agentmods.dev/badge/skills/ingo-eichhorst/irrlicht/ir-fleet.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 | $0.03798 |
| Opus 5.5 | $0.00092 | $0.01519 |
| Sonnet 5.5 | $0.00046 | $0.00760 |
| Haiku 4.5 | $0.00023 | $0.00380 |
Grade A, and why
ir:fleet 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 28d 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Irrlicht fleet — dispatcher over ir:exec
The iron rule: this skill does not re-teach ir:exec. Both rules the
wave-1 fleet broke on 2026-09-20 were already written in
.claude/skills/ir:exec/SKILL.md, in plain imperative English, and three of
three agents broke the first one anyway. A sixth sentence in the same file is
not the fix. Observing what an agent does, and correcting it while it runs, is.
Why a dispatcher. Each ticket's work is one general-purpose Agent that
burns its own context and hands back a short report. The parent spends its
context on scheduling, verification and correction, which is the part no
subagent can do for itself.
What verification means here. Check the claim, not the conclusion. Every wrong answer during the wave-1 run came from a check that confidently answered a different question than the one asked: a wait keyed on a process name that a sibling worktree also matched, an exit marker written to the outer shell instead of the log, and a ref matched by substring against an object id. A verdict in this skill names the command that produced it.
Invocation, and what this refuses
/ir:fleet <N> <N> <N>
/ir:fleet <N>-<N>
Explicit issue numbers only — as a list, or as one contiguous range. A range names its own members, so it does not grow when the tracker does. Refuse each of these, and say which one applies:
- A label, a milestone, or "every ready-for-agent issue". Expanding a query into a work-list is the easy way to dispatch far more work than intended, and the work-list changes under you between one run and the next.
- A ticket with no current
ready-for-agenttriage decision record. Report it and stop for that ticket. Do not infer a plan, and do not run/ir:triageunasked. - Any request to merge. This skill produces ready PRs, exactly as
ir:execdoes.
No agent in the fleet files a GitHub issue. Never put "open a follow-up issue" in a brief: that would reach the tracker without the maintainer ever seeing the instruction that created it.
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.
- 28d ago Changed · +2 lines 8d3dab1083f4
- 1mo ago Changed · +83 lines · +51 tokens per session 5c45edb25b5a
- 1mo ago First seen · 231 lines · 178 tokens per session scan A c1730137f2b3
ir:fleet is a skill published in the GitHub repository ingo-eichhorst/Irrlicht (101 stars, last pushed today), licensed MIT. It adds 229 tokens to every session and 3,798 once invoked, about $0.0009 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 2026-09-21.
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…