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:test-mac/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-test-mac)<a href="https://agentmods.dev/skills/ingo-eichhorst/irrlicht/ir-test-mac"><img src="https://agentmods.dev/badge/skills/ingo-eichhorst/irrlicht/ir-test-mac.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 64 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 139 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 140 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Rogue Agent · line 102 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 141 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00155 | $0.02986 |
| Opus 5 | $0.00077 | $0.01493 |
| Sonnet 5 | $0.00031 | $0.00597 |
| Haiku 4.5 | $0.00015 | $0.00299 |
Grade B, and why
ir:test-mac scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
them into the shared `~/.claude/settings.json`, which repoints production's How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build & Run the macOS Dev Stack
The procedure is a script. Run it — do not reimplement it inline.
cd "$(git rev-parse --show-toplevel)" # the paths below are repo-root-relative
.claude/skills/ir:test-mac/test-mac.sh [MODE] [TARGET] # defaults: replace full
.claude/skills/ir:test-mac/test-mac.sh --help # the full contract
Both arguments are optional and may be given in either order. This file says
which arguments to pass and what they cost; test-mac.sh is the only place
the steps themselves live, and restore-prod.sh beside it is the teardown
half of the same workflow.
Why a script and not fenced blocks to copy out (#1855): every step branches on
MODE/TARGET/PORT/DEV_HOME/SOCK, and each fenced block an agent copies
out runs in a fresh shell. A value dropped between blocks failed silently —
an empty $PORT made the daemon bind 127.0.0.1: (invalid), an empty $SOCK
turned the socket cleanup into a no-op that reported nothing. One script is one
variable scope, and that whole class is gone.
Picking the arguments
Default to replace full — don't ask. Change an axis only when the user
actually asked for it.
- MODE=
separateonly on an explicit request:/ir:test-mac separate, "alongside production", "don't touch production". - TARGET=
daemon/macosonly when the user asked to restart one component: "just restart the daemon", "rebuild the mac app only".
MODE
replace(default) — take over from production. Kills the running production app + daemon (and any dev instance), then runs the freshly built dev binaries on the production port 7837 with the production state dir (noIRRLICHT_HOMEoverride). Because it is on 7837 it receives the statusline quota feed and sees the same on-disk sessions/cost data — it behaves like production but runs your dev code. There is one instance afterward, and the Swift app is installed directly into/Applications/Irrlicht.apprather than a separate bundle, since a human only ever looks at one running app. Destructive — see Tearing down.separate— a dev instance that coexists with production. The dev daemon binds port 7838 and stores its state under a worktree-localIRRLICHT_HOME; the dev app is assembled at/tmp/IrrlichtDev.appand connects to 7838 viaIRRLICHT_DAEMON_PORT. Production stays up untouched on 7837. Since #1178 the Claude Code hooks and statusline feed follow the daemon's own bind address, so the dev daemon receives them — but it installs them into the shared~/.claude/settings.json, which repoints production's hooks at 7838 until production restarts.
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.
- 8d ago First seen · 146 lines · 155 tokens per session scan B 45f80a73eebc
ir:test-mac is a skill published in the GitHub repository ingo-eichhorst/Irrlicht (97 stars, last pushed today), licensed MIT. It adds 155 tokens to every session and 2,986 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.