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:doc-review/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-doc-review)<a href="https://agentmods.dev/skills/ingo-eichhorst/irrlicht/ir-doc-review"><img src="https://agentmods.dev/badge/skills/ingo-eichhorst/irrlicht/ir-doc-review/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-doc-review"><img src="https://agentmods.dev/badge/skills/ingo-eichhorst/irrlicht/ir-doc-review.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 | $0.00117 | $0.02895 |
| Opus 5 | $0.00059 | $0.01448 |
| Sonnet 5 | $0.00023 | $0.00579 |
| Haiku 4.5 | $0.00012 | $0.00290 |
Grade A, and why
ir:doc-review 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 11d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ir:doc-review — Objective Documentation Audit
Goal: audit every in-scope documentation surface against three axes — understandability (U), completeness (C), validity (V) — and fix every finding directly, in place. Filing a GitHub issue is the fallback for the rare finding that can't be safely applied (see step 7) — it is not the default outcome of a finding.
The audit must be reproducible: every finding is binary (a named criterion failed), anchored to a verbatim quote at a location, scored by a fixed severity rubric, and stamped with a stable finding-ID. Two runs on an unchanged tree must converge on the same findings.
Two companion files define the objective parts. Read both before auditing and apply them literally — never invent criteria, never grade on subjective grounds (tone, elegance, "feels unclear"):
references/rubric.md— the criteria (U1–U6, C1–C4, V1–V6), the severity rubric, the finding-ID recipe, and a worked pass/fail example per criterion. This is the contract.references/inventory-sources.md— the bash recipes that derive the authoritative inventories (adapters, CLI flags, env vars, routes, states, events, relay frames, version) from code each run. Axes C and V check docs against these inventories, never against memory.
Inputs
--report-only— run the full audit and print per-surface findings, but change nothing and file nothing. Use this first, and for the convergence check.- An optional path or glob — limit the audit to matching surfaces (default: all in-scope).
ir:release Step 4b runs this fix-by-default workflow on every release (#834, #837), so drift
can't silently accumulate the way the stale "no hooks" claim once did.
Workflow
1. Locate the repo root and confirm gh
Work from git rev-parse --show-toplevel. Confirm the repo is ingo-eichhorst/Irrlicht
(gh repo view --json nameWithOwner) and gh auth status succeeds. If --report-only, the
gh auth check is optional.
What ships with it
2 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.
- 11d ago First seen · 188 lines · 117 tokens per session scan A a4ac206f3686
ir:doc-review is a skill published in the GitHub repository ingo-eichhorst/Irrlicht (98 stars, last pushed today), licensed MIT. It adds 117 tokens to every session and 2,895 once invoked, about $0.0006 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…