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 zhouwei713/WorkBuddy-Dream-Skin --skill workbuddy-skin-makergit clone --depth 1 https://github.com/zhouwei713/WorkBuddy-Dream-SkinWrote 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/zhouwei713/workbuddy-dream-skin/workbuddy-skin-maker)<a href="https://agentmods.dev/skills/zhouwei713/workbuddy-dream-skin/workbuddy-skin-maker"><img src="https://agentmods.dev/badge/skills/zhouwei713/workbuddy-dream-skin/workbuddy-skin-maker/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/zhouwei713/workbuddy-dream-skin/workbuddy-skin-maker"><img src="https://agentmods.dev/badge/skills/zhouwei713/workbuddy-dream-skin/workbuddy-skin-maker.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 | $0.00089 | $0.01241 |
| Opus 5 | $0.00044 | $0.00620 |
| Sonnet 5 | $0.00018 | $0.00248 |
| Haiku 4.5 | $0.00009 | $0.00124 |
Grade A, and why
workbuddy-skin-maker 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 12d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WorkBuddy Skin Maker
Build image responsive WorkBuddy skins while preserving the external CDP injection boundary. Treat automated and visual audits as release gates.
Required reading
- Read the project
AGENTS.md,README.md,docs/ARCHITECTURE.md,docs/DEVELOPMENT.md, anddocs/THEME-SCHEMA.mdbefore editing. - Read design workflow before selecting a palette, layout, surface opacity, or decoration.
- Read strict audit contract before testing, auditing, or reporting completion.
Safety boundary
- Keep all styling in the external CDP injector and project assets.
- Never edit the WorkBuddy installation, executable,
app.asar, signatures, or updater. - Bind CDP only to a loopback address and verify that its listener belongs to the selected
WorkBuddy.exe. - Keep decorative nodes pointer transparent and hidden wherever they could cover chat, settings, dialogs, or artifacts.
- Preserve the cleanup routine, reinjection idempotency, active theme backup, and normal restore path.
- Do not let audit automation send messages, create content, save settings, grant authorization, upgrade an account, or sign out.
- Preserve unrelated user changes in a dirty workspace.
Workflow
1. Establish the baseline
- Locate the project root from this Skill directory.
- Inspect
VERSION,CHANGELOG.md, active theme state, relevant selectors, and existing audit scripts. - Run static validation before editing. Use
scripts/run-strict-audit.ps1 -StaticOnlyfrom this Skill. - Capture a baseline screenshot for every affected page and state.
- Record the WorkBuddy version, active theme ID, appearance, window size, and CDP port.
2. Derive the visual direction
- Analyze every supplied image for luminance, saturation, subject location, visual density, mood, and safe areas.
- Select
appearance: lightfor bright campus, youth, pastel, botanical, soft portrait, and similar imagery unless measured contrast proves another mode is stronger. - Select
appearance: darkfor night, deep sea, gilded banquet, cyber, dramatic stage, and similar imagery. - Derive UI surfaces from the image mood. Avoid forcing every image into one dark shell.
- Design the decoration as a theme specific companion. Give it depth, asymmetry, subtle motion, and responsive positioning. Keep it subordinate to task content.
- Declare the intended hierarchy for background, hero, panels, reading surfaces, artifact shelf, composer, and decoration before coding.
What ships with it
4 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.
- 12d ago First seen · 93 lines · 89 tokens per session scan A 02e1ea3bf115
workbuddy-skin-maker is a skill published in the GitHub repository zhouwei713/WorkBuddy-Dream-Skin (24 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 1,241 once invoked, about $0.0004 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.