Irrlicht: Skill for Claude Code

.claude/skills/ir:triage/SKILL.md

ir:triage is a skill for Claude Code from ingo-eichhorst/Irrlicht. It costs 61 tokens per session (2,475 once invoked), scanned A, original, MIT.

An automated diagnostic process for triaging GitHub issues in the Irrlicht project. Triage means checking whether an issue is clear and ready to implement, without designing the solution.

In plain words
What is it for?
Use it to assess an issue against a readiness rubric, apply a readiness label, assign a complexity level, and produce a plan for a later implementation step.
Why use it?
It helps maintainers separate actionable issues from reports that need more information and estimates the effort and execution plan.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is ingo-eichhorst/Irrlicht's own configuration. It tells Claude Code how to work on Irrlicht itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Irrlicht configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/ingo-eichhorst/Irrlicht/main/.claude/skills/ir:triage/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ingo-eichhorst/Irrlicht

Made for: Claude Code.

Wrote 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.

agentmods badge for ir:triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/ingo-eichhorst/irrlicht/ir-triage/github.svg)](https://agentmods.dev/skills/ingo-eichhorst/irrlicht/ir-triage)
Your own site
<a href="https://agentmods.dev/skills/ingo-eichhorst/irrlicht/ir-triage"><img src="https://agentmods.dev/badge/skills/ingo-eichhorst/irrlicht/ir-triage/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.

agentmods 80×15 button for ir:triage

Your own site · 80×15
<a href="https://agentmods.dev/skills/ingo-eichhorst/irrlicht/ir-triage"><img src="https://agentmods.dev/badge/skills/ingo-eichhorst/irrlicht/ir-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,475 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.02475
Opus 5 $0.00030 $0.01238
Sonnet 5 $0.00012 $0.00495
Haiku 4.5 $0.00006 $0.00248

Measured 4d ago against content hash 9ac6db8de969, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ir:triage 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 4d 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.

.claude/skills/ir:triage/SKILL.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Triage and Plan Irrlicht Issues

Prepare an issue for /ir:exec. Diagnose the issue and make the design, testing, and process choices that execution needs. Do not implement the fix. Pass --repo ingo-eichhorst/Irrlicht to every gh command.

Invocation

  • /ir:triage — process every open issue without a state label.
  • /ir:triage #278 — process one issue.
  • /ir:triage #278 #277 — process several issues.

For a sweep, enumerate issues with no state role:

gh issue list --repo ingo-eichhorst/Irrlicht --state open --limit 200 \
  --json number,labels --jq '.[] | select(
    [.labels[].name] | any(. == "needs-triage" or . == "needs-info" or
      . == "ready-for-agent" or . == "ready-for-human" or . == "wontfix") | not
  ) | .number'

Process issues one at a time. Skip an already-triaged issue during a sweep. Always re-triage an explicitly named issue. Edit the prior AI triage comment instead of appending another one.

Start every comment with:

> *This was generated by AI during triage.*

Workflow

  1. Read the issue and all comments.
  2. Inspect the cited code, nearby tests, architecture boundaries, and applicable frontends. Do not run tests or change files.
  3. Check readiness and hard blockers.
  4. Choose one high-level design and one testing strategy.
  5. Set complexity, process, estimate, labels, and milestone.
  6. Post the assessment and apply metadata in one issue edit.

Treat a dismissal such as “already fixed,” “self-heals,” or “not relevant” as an assumption until code, a command, or a cited PR verifies it. Mark an unchecked dismissal as assumed. Do not use it to reduce scope or risk.

Readiness

Score each axis with or and one evidence-based sentence.

Axis Pass condition
Scope The affected behavior and likely components are bounded.
Specification No external or hard-to-reverse decision remains.
Verifiability A concrete signal can distinguish success from failure.
Observability Existing or small new instrumentation can expose that signal.
Context Relevant code and prior work are cited or directly findable.
Independence No unresolved issue, PR, credential, or human decision blocks work.
Reversibility The change is local and can be reverted safely.

Read the full file on GitHub · 257 lines

Changes

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.

  1. 4d ago Changed · -309 lines · -72 tokens per session 9ac6db8de969
  2. 10d ago First seen · 566 lines · 133 tokens per session scan A 917d7c16ebe3

Subscribe to this mod's changes

ir:triage is a skill published in the GitHub repository ingo-eichhorst/Irrlicht (98 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 2,475 once invoked, about $0.0003 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.

Related

Other skills, from other repositories