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 JonathandNidhog/dsh-plugin-wallpaper-engine-codex --skill wallpaper-enginegit clone --depth 1 https://github.com/JonathandNidhog/dsh-plugin-wallpaper-engine-codexWrote 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/jonathandnidhog/dsh-plugin-wallpaper-engine-codex/wallpaper-engine)<a href="https://agentmods.dev/skills/jonathandnidhog/dsh-plugin-wallpaper-engine-codex/wallpaper-engine"><img src="https://agentmods.dev/badge/skills/jonathandnidhog/dsh-plugin-wallpaper-engine-codex/wallpaper-engine/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/jonathandnidhog/dsh-plugin-wallpaper-engine-codex/wallpaper-engine"><img src="https://agentmods.dev/badge/skills/jonathandnidhog/dsh-plugin-wallpaper-engine-codex/wallpaper-engine.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 | $0.00062 | $0.00767 |
| Opus 5.5 | $0.00025 | $0.00307 |
| Sonnet 5.5 | $0.00012 | $0.00153 |
| Haiku 4.5 | $0.00006 | $0.00077 |
Grade A, and why
wallpaper-engine 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wallpaper Engine Skin for Codex
Use the plugin's codex_skin MCP tools. This plugin changes the Codex window, never the Windows desktop wallpaper.
Workflow
- Call
codex_skin_statusfirst. - If
bridge.debug.availableis false, callcodex_skin_launch_instructions. Explain that the user must close Codex and relaunch it with the bundled script, then continue in a new task. - Call
codex_skin_list_sourcesbefore applying a skin. Resolve the request to an exact returnedid; ask the user only if multiple plausible matches remain. - Call
codex_skin_applywith that exact id. Keep video muted unless the user explicitly asks for sound. - Call
codex_skin_removewhen the user wants the normal Codex appearance restored. - Use
codex_skin_generate_native_themewhen the user wants a supported color/font theme or cannot use the dynamic bridge.
Rendering expectations
- Small video files render inline. Videos over the compression threshold are automatically transcoded into a full-duration, hardware-friendly cached MP4 before Blob playback. Files still over the Blob limit use a decoded animation sequence, with the project preview as the final fallback.
- Web, Scene, and Application projects use their preview image because their local files cannot be loaded safely from Codex's
app://renderer. - The dynamic skin is experimental because Codex does not expose a public background-image plugin API. The launcher enables a loopback-only Chrome DevTools endpoint and does not modify installed Codex files.
- The selected skin and adjustment settings persist under LocalAppData. When Codex is launched with the bundled loopback debug launcher, the MCP bridge automatically restores the last enabled skin; ending a task must not remove it.
- A normal Codex launch without the debug flag cannot accept a dynamic skin. If status reports the bridge unavailable, give the bundled launcher steps; after relaunch, wait for automatic restoration before asking the user to select the wallpaper again.
- Report
renderMode,fallbackKind, andusedPreviewFallbackhonestly after apply. Describeframesas a decoded animation sequence, not direct video playback. - Keep
showControlsenabled by default. Tell the user that “皮肤调整” selects a local video and controls fit mode, zoom, position, panel opacity, background scrim, and blur. - The controls panel stays open across a video switch. It shows indeterminate progress while preparing/transcoding, measured 0–100% progress while transferring, green on completion, and red on failure.
- Video and frame playback pause automatically while the Codex window is unfocused, minimized, or hidden, and resume when it becomes active.
- Transcoding writes only to the plugin cache under local application data and never changes a Wallpaper Engine source project. Report compression size and resolution when available.
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 · 40 lines · 62 tokens per session scan A bf1b7aa37fb8
wallpaper-engine is a skill published in the GitHub repository JonathandNidhog/dsh-plugin-wallpaper-engine-codex (0 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 767 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 2026-08-31.
Other skills, from other repositories
use-wsl
Use one wslexec call per user-requested non-interactive Linux execution when Windows-native Codex needs WSL. Preserve the project working directory and never probe or retry automatically.
work
Inspect, draw, model, edit, batch, export, import, or automate Vectorworks 2024/2025 through MCP on Windows 11. Use for CAD/BIM tasks involving geometry, walls, floor plans, text, dimensions, properties, classes, layers, worksheets, symbols, doors, windows, slabs, roofs, or drawing files.
diagnose
Diagnose Vectorworks MCP runtime, companion checkout, native bridge, listener, capability, or Codex integration failures on Windows 11. Use when tools are missing, Vectorworks hangs, ping/preflight fails, setup stopped working, or bridge readiness is unclear.
setup
Set up or repair the Vectorworks MCP companion runtime and Codex plugin on Windows 11. Use when the user asks to connect Codex to Vectorworks, install or update vectorworks-mcp, configure the native bridge or Python fallback, or fix missing first-run setup.
ping
Check whether Vectorworks 2024/2025 on Windows 11 is reachable and safe for CAD operations through the native bridge or Python dialog fallback. Use when the user says ping Vectorworks, test the MCP connection, verify the bridge, or asks whether Vectorworks is ready.
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…