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 skills add theredbluepill/arc-interactive --skill generate-arc-game-gifgit clone --depth 1 https://github.com/theredbluepill/arc-interactiveWrote 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/theredbluepill/arc-interactive/generate-arc-game-gif)<a href="https://agentmods.dev/skills/theredbluepill/arc-interactive/generate-arc-game-gif"><img src="https://agentmods.dev/badge/skills/theredbluepill/arc-interactive/generate-arc-game-gif/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/theredbluepill/arc-interactive/generate-arc-game-gif"><img src="https://agentmods.dev/badge/skills/theredbluepill/arc-interactive/generate-arc-game-gif.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.01660 |
| Opus 5 | $0.00000 | $0.00830 |
| Sonnet 5 | $0.00000 | $0.00332 |
| Haiku 4.5 | $0.00000 | $0.00166 |
Grade A, and why
generate-arc-game-gif 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Generate ARC game preview GIFs (assets/{stem}.gif)
Use this skill when adding or refreshing 64×64 registry GIFs in assets/, or when checking whether a game’s HUD is suitable for markdown previews.
What a registry GIF must show
Preview GIFs are not random motion clips. They should tell a human (and an agent reading the table) how the game progresses and how you lose or fail a check.
- Advancing levels — The capture should include multiple levels where the game has them (e.g. early level(s) cleared, then at least one harder / later level so difficulty ramps). Level changes must read clearly on the final 64×64 frame: HUD updates (
RenderableUserDisplay.update), optional brief hold/pause in capture timing viaregistry_gif_overrides.json/registry_gif_lib—not by faking pixels outside the game. - One or two failed cases — Include 1–2 segments that show failure:
GAME_OVER, a wasted resource (e.g. checks/blurs/steps hitting zero), a failed test with visible HUD feedback, wrong flag, etc. Failures must be visible in the shipped game UI (colors, bars, icons drawn inrender_interface), not only as a caption or external annotation. - Everything reads through
RenderableUserDisplay— Cursors, pings, “bad” states, counters, and lose-adjacent feedback live in the game’sRenderableUserDisplay(and whateverstep()passes intoupdate). The recorder (render_arc_game_gif.py→registry_gif_lib) only steps the env and saves frames; it does not replace a missing HUD.
If the stock recorder cannot yet hit “late level + two fails” for a stem, first ensure the UI exposes those states clearly, then extend registry_gif_overrides.json / shared registry_*_gif.py / registry_gif_lib so the same script still drives the GIF.
Single script (repo)
All capture flows go through scripts/render_arc_game_gif.py:
| Mode | Command |
|---|---|
| Registry (multi-level + fails when configured) | uv run python scripts/render_arc_game_gif.py --stem wl01 |
Batch in GAMES.md order |
uv run python scripts/render_arc_game_gif.py --from pb01 --through bn03 |
| Pending (quick motion only; not a full registry spec) | uv run python scripts/render_arc_game_gif.py --pending --pending-all |
| Pending + one stem | uv run python scripts/render_arc_game_gif.py --pending --pending-game ju01 |
Fill GAMES.md preview column after pending |
add --fill-games-md |
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 · 73 lines · 0 tokens per session scan A 320aa6cad66b
generate-arc-game-gif is a skill published in the GitHub repository theredbluepill/arc-interactive (55 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,660 tokens. 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
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.