Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/ingo-eichhorst/irrlicht/recordnpx skills add ingo-eichhorst/Irrlicht --skill recordgit 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/record)<a href="https://agentmods.dev/skills/ingo-eichhorst/irrlicht/record"><img src="https://agentmods.dev/badge/skills/ingo-eichhorst/irrlicht/record.svg" alt="Measured on agentmods" 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 | $0.00106 | $0.05873 |
| Opus 5 | $0.00053 | $0.02936 |
| Sonnet 5 | $0.00021 | $0.01175 |
| Haiku 4.5 | $0.00011 | $0.00587 |
Grade B, and why
ir:onboarding-factory/record 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
(`~/.claude/settings.json`, `~/.codex/hooks.json`, …), because a dev daemon How it starts
The opening of the file, as written. The whole thing — 450 lines — stays where its author put it; the contents beside it link to each section on GitHub.
record
You run as a focused subagent with no parent context. This verb DRIVES A LIVE AGENT CLI and SPENDS API TOKENS — auth is set up out-of-band, so run it without ceremony (no key checks, no "this will spend money" prompts). It must be serialized: only one
recordruns against the live daemon at a time. When done, return only the "Return contract" block.
Preconditions
-
The cell is assessed and on a recordable route. Read it:
of status --agent <agent> --scenario <scenario> --json- route
record/record-known-failing→ proceed. - route
driver-gap→ port the step first (Step 2), then proceed. - route
frozen→ STOP, returnstatus: frozen(nothing to record).
- route
-
Prerequisites met.
of record prereq-check --agent <agent>lists the human actions a recording needs (auth mode, env vars, a mock, a local model server). If one is unmet and you can't satisfy it, STOP and returnstatus: prereq_blockednaming the exact blocker — never ask the dispatcher. -
Clean
replaydata/tree. The recording precheck refuses a dirtyreplaydata/(re-records must be deliberate commits). If the assessment isn't committed yet, that's the dispatcher's ordering bug — returnstatus: infra_failwith that note. -
A recording daemon is up — attached OR coexisting. Which one is a decision you make per run, not a default:
-
Attach (
--attach, against the user's runningirrlichd --record) when you are re-recording an adapter the running daemon already ships, and that daemon is genuinely in--recordmode. The dashboard stays connected and the session shows up live. -
Coexist — an isolated daemon built from this branch, on its own
IRRLICHT_HOMEand port — when either half of that is false:IRRLICHT_ONBOARD_HOME=/tmp/irr-onb \ IRRLICHT_ONBOARD_BIND_ADDR=127.0.0.1:7838 \ IRRLICHT_PERMISSION_MODE=grant-all \ of record run --agent <agent> --scenario <scenario>
-
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.
- 4d ago First seen · 450 lines · 106 tokens per session scan B 8df67121b961
ir:onboarding-factory/record is a skill published in the GitHub repository ingo-eichhorst/Irrlicht (96 stars, last pushed today), licensed MIT. It adds 106 tokens to every session and 5,873 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…