Borrowing it
Nothing to install: this file belongs to paulrobello/claude-office. 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/paulrobello/claude-office/main/.claude/skills/desk-accessory/SKILL.mdgit clone --depth 1 https://github.com/paulrobello/claude-officeWrote 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/paulrobello/claude-office/desk-accessory)<a href="https://agentmods.dev/skills/paulrobello/claude-office/desk-accessory"><img src="https://agentmods.dev/badge/skills/paulrobello/claude-office/desk-accessory/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/paulrobello/claude-office/desk-accessory"><img src="https://agentmods.dev/badge/skills/paulrobello/claude-office/desk-accessory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.03048 |
| Opus 5.5 | $0.00021 | $0.01219 |
| Sonnet 5.5 | $0.00011 | $0.00610 |
| Haiku 4.5 | $0.00005 | $0.00305 |
Grade A, and why
desk-accessory 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 1mo 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 — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Desk Accessory Generator
Create desk accessories for the Claude Office Visualizer using Nano Banana MCP for AI image generation and ImageMagick for transparency and tinting preparation.
Philosophy: Tintable Variety
Desk accessories should be grayscale or white so they can be tinted with different colors at runtime. This allows a single sprite to represent many color variations across different desks, adding visual variety without generating multiple sprites.
Before generating, ask:
- Is this a unique item (one-of-a-kind) or a common item (appears on multiple desks)?
- If common: make it WHITE/GRAYSCALE for tinting
- If unique: colors can be baked in
Key Principle: White for Tinting
CRITICAL: Unless the item is unique (only appears once), generate it as WHITE or GRAYSCALE so it can be tinted programmatically.
Why this matters:
- A white coffee mug can become blue, pink, green, gold via tinting
- A red stapler can ONLY be red - no variety
- Tinting multiplies the sprite's colors with the tint color
- White (0xFFFFFF) × any tint = that tint color
- Gray gives shaded/dimensional tinting results
Key Principle: Facing Direction
CRITICAL: All desk items should face NORTH-WEST (away from the viewer). The game uses a top-down perspective where the user views characters and items from behind/above. Items should be oriented so their "front" faces away from the camera toward the top-left of the screen.
Prompt Templates
Scaling Guidance
IMPORTANT: Generated images (1024px) are scaled down to ~128px for use in the game. Include guidance in your prompts to ensure details survive scaling:
- Request thick lines and bold shapes
- Ask for chunky pixel art style
- Avoid fine details that will disappear at small sizes
- Add explicit note: "this will be scaled down significantly, use thick prominent features"
Common Desk Items (Tintable - WHITE/GRAYSCALE)
Pixel art [ITEM], 16-bit retro game style, WHITE colored, simple clean design,
facing north-west, on solid magenta background #FF00FF, game sprite asset,
centered composition, no shadows on background, clean edges,
chunky pixel art with thick lines and bold shapes, this will be scaled down significantly so use thick prominent features
What ships with it
1 file 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.
- 1mo ago First seen · 315 lines · 53 tokens per session scan A 326e22ae06ef
desk-accessory is a skill published in the GitHub repository paulrobello/claude-office (590 stars, last pushed 12d ago), licensed MIT. It adds 53 tokens to every session and 3,048 once invoked, about $0.0002 per session on Opus 5.5. 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…