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/bloombooks/bloomdesktop/game-theme-previewnpx skills add BloomBooks/BloomDesktop --skill game-theme-previewgit clone --depth 1 https://github.com/BloomBooks/BloomDesktopWrote 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/bloombooks/bloomdesktop/game-theme-preview)<a href="https://agentmods.dev/skills/bloombooks/bloomdesktop/game-theme-preview"><img src="https://agentmods.dev/badge/skills/bloombooks/bloomdesktop/game-theme-preview.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 5.1 | $0.00097 | $0.01983 |
| Opus 5 | $0.00048 | $0.00992 |
| Sonnet 5 | $0.00019 | $0.00397 |
| Haiku 4.5 | $0.00010 | $0.00198 |
Grade A, and why
game-theme-preview 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 5d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Game Theme Preview & Contrast Fix
Outcome
Every part of every Bloom game theme is verifiable at a glance - each element rendered in its resolved colors with a WCAG ratio under it - and every low-contrast spot gets an AI-curated, palette-aware fix that the human approves element-by-element in the page itself. The agent then applies the approved colors and re-verifies. Also: a one-shot CLI to check the contrast of any two colors.
When To Use
- You changed colors in
src/content/templates/template books/Games/gamesThemes.less. - Someone reports a game element (dashed drop target, draggable, button, checkbox) is hard to see against the background.
- A tester wants to scroll through all themes and confirm they look good.
- You need the WCAG contrast ratio between two colors.
The canonical loop (do it this way)
This is the agreed process. The generator measures, validates, and visualizes; the agent chooses the colors (fitting each theme's palette and name); the human approves each change; the agent applies and re-verifies.
- Measure. Generate the preview from the source LESS and publish it:
(py ".github/skills/game-theme-preview/generate_preview.py" <out.html><out.html>in the session scratchpad). Publish with the Artifact tool; the nav chips show each theme's issue count. - Curate (agent judgment, not just the algorithm). For each flagged element, dump the
theme's resolved palette and failing checks (call
build()per theme), then pick a color that a designer eyeballing the whole theme would choose:- reuse a color the theme already uses (text, header, an existing outline),
- honor the theme's name/identity (keep coral-reef coral, cherry-blossom pink),
- prefer one upstream change that fixes several checks (e.g. deepening
--game-primary-colorslightly), and note when one variable feeds another, - keep intentional translucency (darken / raise alpha rather than going opaque).
Write the picks to a curated JSON file (scratchpad - it's a per-review input, not a
repo asset):
theme -> "Component title|check label" -> [ {label, why, changes:[[var,value],...]} ]
- Validate + visualize. Re-run with the curated file as the 3rd argument:
Each curated pick renders first as a blue Recommended option with its rationale, in context, and is held to the same whole-element validation as a generated one - invalid picks are dropped, never shipped. Mechanical alternatives appear below as fallbacks. Republish to the same Artifact URL.py generate_preview.py out.html "<path>/gamesThemes.less" curated.json - Human approves. The user ticks the options they want and clicks Copy approved changes; they paste back an apply-ready block.
- Apply + re-verify. Edit the named
.bloom-page.game-theme-*block(s) ingamesThemes.less(one variable per line, with a short comment + the issue id). Re-run the generator against the edited file and confirm the affected theme's nav chip is clean and no other theme regressed.
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.
- 5d ago First seen · 132 lines · 97 tokens per session scan A 8c42c3249585
game-theme-preview is a skill published in the GitHub repository BloomBooks/BloomDesktop (44 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 1,983 once invoked, about $0.0005 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
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).
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
playtest-report
Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.
unity-manual-component
Manually add, configure, reorder, and copy components on GameObjects using Unity Editor UI. For one-off Inspector workflows that do not need REST automation.
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…