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:exec/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-exec)<a href="https://agentmods.dev/skills/ingo-eichhorst/irrlicht/ir-exec"><img src="https://agentmods.dev/badge/skills/ingo-eichhorst/irrlicht/ir-exec/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-exec"><img src="https://agentmods.dev/badge/skills/ingo-eichhorst/irrlicht/ir-exec.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 | $0.00070 | $0.03786 |
| Opus 5.5 | $0.00028 | $0.01514 |
| Sonnet 5.5 | $0.00014 | $0.00757 |
| Haiku 4.5 | $0.00007 | $0.00379 |
Grade A, and why
ir:exec 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 14d 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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute an Approved Issue Plan
Run:
/ir:exec <N>
The command approves the latest /ir:triage design. Follow one path from that
design to a ready PR. Stop when a command fails. Do not invoke the Workflow
tool.
1. Validate the triage contract
Read the issue, all comments, and labels from ingo-eichhorst/Irrlicht. Select
the latest comment that starts with the triage disclaimer. Require all of these
items:
- the
ready-for-agentlabel; ## High-level designwith content;## Testing strategywith content;**Process:**with investigation, review, and simplify values;**Estimate:**with agent-active time and human gates;**Verdict:** ready-for-agent.
If one item is absent, stop before a worktree or assignment exists. Report the
missing item and request /ir:triage #<N>. Do not infer a plan from the issue
body or accept a legacy triage comment.
2. Create the worktree
Check for work already in progress:
gh pr list --repo ingo-eichhorst/Irrlicht --state open --search "<N>" \
--json number,headRefName,title,isDraft
git worktree list | grep -w "<N>"
git ls-remote --heads origin | grep -w "<N>"
On any hit, report the PR, branch, worktree, and WIP state. Stop. Do not create
a second implementation. One exception, for a resume after an interrupted run:
when the caller names an existing worktree for <N> and asks to continue it,
take the resume step in this section instead of stopping. Without that entry
point a caller can only resume by telling an agent to skip this check, which
is an instruction around the skill rather than a path through it.
Create a branch from a frozen current base:
git -C <main-repo> fetch origin main
BASE_SHA=$(git -C <main-repo> rev-parse origin/main)
git -C <main-repo> worktree add -b feat/<N>-<slug> \
.claude/worktrees/<N>-<slug> "$BASE_SHA"
git -C <main-repo> config --local \
"branch.feat/<N>-<slug>.irExecBase" "$BASE_SHA"
<main-repo> is the main checkout:
$(dirname "$(git rev-parse --path-format=absolute --git-common-dir)") — not
--show-toplevel, which answers with the worktree when run inside one (see
ir:fleet, #2045).
What ships with it
1 file 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.
- 14d ago Changed · +5 lines 18b89282cff5
- 28d ago Changed · +3 lines 38d6d2aa3012
- 1mo ago Changed · +53 lines 437f08841acb
- 1mo ago Changed · +56 lines 6abd557f850b
- 1mo ago Changed · +1 lines d91dad6c2226
- 1mo ago Changed · +7 lines 06239ab80acd
- 1mo ago Changed · -974 lines · -88 tokens per session scan C → A 40cb38e737f0
- 1mo ago First seen · 1,218 lines · 158 tokens per session scan C 39290a53d530
ir:exec is a skill published in the GitHub repository ingo-eichhorst/Irrlicht (101 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 3,786 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
antfu-issue-triage
Triage open issues and PRs of the current GitHub repo - find already-fixed, duplicate, and spam items, suggest labels, gauge demand from reactions and comments, then present a table of proposed actions and comments for confirmation before touching anything. Use when asked to triage, organize, clean up, or groom issues…
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
connect
Choose which wiki this session uses, the team project's pages on the Nimbalyst server or the project's local wiki of files, and connect a repository to its team project. Use at the start of a task before any wiki tool, when a wiki tool returns reponotbound, ambiguousproject, pinmismatch, projectnotaccessible…
llxprt-issue-workflow
Use this skill when asked to address, fix, or work on a GitHub issue in the llxprt-code repository. Covers the complete issue lifecycle - branch setup, gh CLI usage, test-first planning, subagent delegation and review loops, the full verification cycle (including the zai-glm-flash smoke test), open code review (ocr)…