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/recca0120/code-quest/extension-ui-referencenpx skills add recca0120/code-quest --skill extension-ui-referencegit clone --depth 1 https://github.com/recca0120/code-questWhat 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 | $0.00061 | $0.01123 |
| Opus 5 | $0.00030 | $0.00562 |
| Sonnet 5 | $0.00012 | $0.00225 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade A, and why
extension-ui-reference 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 2d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extension UI Reference — Live Inspection with MCP
Extension Folder
/Users/user/Desktop/anthropic.claude-code-2.1.45-darwin-arm64/
├── src/
│ ├── core/main.js ← 核心邏輯（~70k 行，可讀性高，首選）
│ ├── core/runtime.js ← esbuild helper
│ ├── modules/ ← 第三方 npm 模組（210 個）
│ └── module-map.json ← 模組索引
├── extension.js ← bundled（94k 行，備案，不優先讀）
├── webview/index.js ← webview React app (compiled)
└── .vscode/
└── launch.json ← "Run Extension" debug config
讀程式碼時以 src/core/main.js 為主，extension.js 為備案。
src/core/main.js 經過 webcrack + prettier + normalize，class/method 名保留，可讀性遠高於 bundled extension.js。
Step 1: Launch Extension in Debug Mode
Use MCP debugmcp start_debugging to launch the extension:
tool: start_debugging
fileFullPath: /Users/user/Desktop/anthropic.claude-code-2.1.45-darwin-arm64/extension.js
workingDirectory: /Users/user/Desktop/anthropic.claude-code-2.1.45-darwin-arm64
configurationName: Run Extension
This opens a new VS Code Extension Development Host window with the Claude Code UI.
Step 2: Inspect the Live UI
Option A — VS Code Developer Tools (visual inspection)
In the Extension Development Host window:
- Help → Toggle Developer Tools (opens Chromium DevTools)
- Use Element Inspector to click any UI element and see its CSS classes and computed styles
- Look for class patterns like
camelCase_randomHash(e.g.,menuPopup_pZbgXw,fileItem_pZbgXw) - Check the Styles panel for actual computed CSS values
Option B — evaluate_expression (programmatic)
After start_debugging, use evaluate_expression to query the extension host context.
To inspect webview content (if accessible from extension host):
// Get computed styles of a specific element
getComputedStyle(document.querySelector('.menuPopup_pZbgXw'))
Step 3: Map Extension CSS → cc-office Design Tokens
| Extension CSS Variable | cc-office Token / Class |
|---|---|
--app-menu-background |
bg-surface |
--app-input-border |
border-border |
--app-primary-foreground |
text-text |
--app-secondary-foreground |
text-text-muted |
--app-list-active-background |
hover:bg-white/5 |
--corner-radius-large (8px) |
rounded-lg |
--app-list-border-radius (4px) |
rounded |
--app-list-item-padding (4px 8px) |
py-1 px-2 |
--app-monospace-font-family |
font-mono |
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.
- 2d ago First seen · 107 lines · 61 tokens per session scan A b097e1255a16
extension-ui-reference is a skill published in the GitHub repository recca0120/code-quest (11 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 1,123 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…