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/rab-icon-grid-processingnpx skills add BloomBooks/BloomDesktop --skill rab-icon-grid-processinggit 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/rab-icon-grid-processing)<a href="https://agentmods.dev/skills/bloombooks/bloomdesktop/rab-icon-grid-processing"><img src="https://agentmods.dev/badge/skills/bloombooks/bloomdesktop/rab-icon-grid-processing.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 | $0.00062 | $0.01979 |
| Opus 5 | $0.00031 | $0.00989 |
| Sonnet 5 | $0.00012 | $0.00396 |
| Haiku 4.5 | $0.00006 | $0.00198 |
Grade A, and why
rab-icon-grid-processing 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 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.
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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RAB Icon Grid Processing
Outcome
Turn incoming icon artwork into usable Reading App Builder icon assets that are visually legible at app-icon size, stored in the layout Bloom expects, and validated before broad rollout.
When To Use
- You receive a grid, sprite sheet, or batch of candidate icon images for Reading App Builder.
- The icons are technically valid PNGs but look too small because of excessive transparent padding.
- The icons are stored one-per-folder and need to be flattened into a single bundled icon directory.
- Bloom's RAB icon discovery code needs to be updated to match an asset-layout change.
- You want to try one or two sample icons first before touching the entire set.
Default Assumptions
- Target icons should remain square PNGs with transparent backgrounds.
- A 512x512 master icon is the safest working size when repadding or regenerating icon art.
- Unless the user says otherwise, name outputs
bloom-app-icon-<number>. - In this repo, bundled App Builder icons live under
DistFiles/appbuilder-icons. - If the asset layout changes, update both the backend discovery path and the tests in the same pass.
- Prefer process tasks or direct scripts over bash-heavy image tooling if the shell environment is unstable.
Inputs To Confirm
- What is the incoming source: a grid image, sprite sheet, flat PNG batch, or folder-per-icon bundle?
- Is the task visual-only, layout-only, or both?
- Should the agent run a one-or-two-icon pilot first, or has the user already approved a full batch?
- Are filenames already the desired final IDs, or do they need renaming?
- Does Bloom code currently assume the old bundled layout?
- What is the narrowest validation available after the change?
Core Workflow
- Inspect the incoming asset set. Determine whether the source is a single grid, a sprite sheet, flat PNG files, or a folder-per-icon layout.
- Identify the controlling problem before editing. Decide whether the main issue is splitting, transparent padding, directory layout, naming, or code compatibility.
- Start with a representative sample. Pick one or two icons that clearly show the problem and use them as a reversible pilot.
- If the icons are already individual files but too padded, crop to visible alpha bounds. Measure visible pixels using alpha, trim the transparent border, then redraw onto a square transparent canvas with a consistent margin.
- If the assets are stored one-per-folder, flatten them only after checking for filename collisions. Move the PNGs into the target root, remove emptied folders, and keep the filename-based identity stable.
- If the source is a grid or sprite sheet, split it into individual transparent PNGs before any crop-and-repad pass. Use the grid cell geometry or visible bounds consistently across the full batch.
- Validate the pilot visually before batch rollout. Open the updated sample icons and confirm they read better without clipping or awkward framing.
- Only after the pilot succeeds, run the same transformation across the remaining icons.
- If Bloom code depends on the old asset layout, update the code path and tests in the same change.
- Finish with the narrowest executable validation available and note any unrelated blockers separately.
What ships with it
3 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.
- 4d ago First seen · 144 lines · 62 tokens per session scan A 911ba96c11da
rab-icon-grid-processing is a skill published in the GitHub repository BloomBooks/BloomDesktop (44 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 1,979 once invoked, about $0.0003 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.
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…