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 xnydl/codex-dream-skin --skill macosgit clone --depth 1 https://github.com/xnydl/codex-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/xnydl/codex-dream-skin/macos)<a href="https://agentmods.dev/skills/xnydl/codex-dream-skin/macos"><img src="https://agentmods.dev/badge/skills/xnydl/codex-dream-skin/macos.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 5.1 | $0.00070 | $0.00544 |
| Opus 5 | $0.00035 | $0.00272 |
| Sonnet 5 | $0.00014 | $0.00109 |
| Haiku 4.5 | $0.00007 | $0.00054 |
Grade A, and why
codex-dream-skin-studio 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 8d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Dream Skin Studio
This file is an optional Codex capability entry. The delivery is a complete standalone project; users do not need to install it as a Skill.
Workflow
- Run
Install Codex Dream Skin.commandfrom the complete project folder. - Run
Customize Codex Dream Skin.command, choose an image in Finder, and enter a theme name. - Verify the live result with
Verify Codex Dream Skin.command. A pass requires a visible native sidebar and composer, no horizontal overflow, non-interactive decoration, and—on the home route—a continuous wallpaper with live native heading, project controls, and any suggestion cards exposed by the current Codex version. - Restore the official appearance with
Restore Codex Dream Skin.command.
Guardrails
- Never modify the official
.app,app.asar, or its code signature. - Use the official Codex app's signed Node.js runtime only after validating its signature, Team ID, architecture, and minimum version.
- Bind CDP to loopback, verify that the listener belongs to Codex, and reject non-Codex renderer targets.
- Preserve all native cards, navigation, project selectors, task content, composer controls, and keyboard focus.
- Theme images must be UI-free wallpapers. Paint one 16:9 image continuously across the window; keep home expressive and task routes quieter.
appearance: autofollows Codex/native or system appearance rather than image brightness. - Keep decoration at
pointer-events: none. - Require explicit authorization before restarting an already-running Codex instance.
- Stop an injector only when its recorded PID, executable, command line, and start time all match.
Key resources
README.md: user installation and customization guide.scripts/injector.mjs: CDP connection, injection, removal, verification, and screenshots.assets/dream-skin.css: live native interface styling.assets/renderer-inject.js: idempotent DOM integration and cleanup.scripts/doctor-macos.sh: signed-runtime, payload, and optional live-session self-check.references/qa-inventory.md: release and visual acceptance criteria.
What ships with it
60 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.
- .gitignore 114 B
- agents/openai.yaml 282 B
- assets/dream-skin.css 39 KB
- assets/portal-hero.png 1626 KB
- assets/renderer-inject.js 33 KB runs code
- assets/theme.json 794 B
- CHANGELOG.md 8.6 KB
- CLIENT_DEPLOY_PROMPT.md 4.7 KB
- Customize Codex Dream Skin.command 299 B
- Install Codex Dream Skin.command 120 B
- Install Menu Bar.command 83 B
- LICENSE 1.1 KB
- menubar/codex_dream_skin.10s.sh 4.7 KB runs code
- NOTICE.md 2.0 KB
- package.json 238 B
- presets/generate-presets.mjs 10 KB runs code
- presets/generate-ssyai-preset.mjs 4.5 KB runs code
- presets/preset-amber-dusk/background.jpg 117 KB
- presets/preset-amber-dusk/theme.json 798 B
- presets/preset-cyber-neon/background.jpg 127 KB
- presets/preset-cyber-neon/theme.json 798 B
- presets/preset-forest-mist/background.jpg 115 KB
- presets/preset-forest-mist/theme.json 794 B
- presets/preset-midnight-aurora/background.jpg 119 KB
- presets/preset-midnight-aurora/theme.json 800 B
- presets/preset-sakura-dawn/background.jpg 104 KB
- presets/preset-sakura-dawn/theme.json 799 B
- presets/preset-ssyai-dream/background.jpg 179 KB
- presets/preset-ssyai-dream/theme.json 932 B
- presets/README.md 4.6 KB
- README.md 7.5 KB
- references/acceptance-report-2026-07-15.md 1.5 KB
- references/asset-provenance.md 927 B
- references/incident-review.md 1.2 KB
- references/qa-inventory.md 3.0 KB
- references/runtime-notes.md 1.7 KB
- Restore Codex Dream Skin.command 329 B
- scripts/apply-from-menubar-macos.sh 2.6 KB runs code
- scripts/common-macos.sh 23 KB runs code
- scripts/customize-theme-macos.sh 3.1 KB runs code
- scripts/doctor-macos.sh 1.8 KB runs code
- scripts/image-metadata.mjs 4.6 KB runs code
- scripts/injector.mjs 33 KB runs code
- scripts/install-dream-skin-macos.sh 4.2 KB runs code
- scripts/install-menubar-macos.sh 3.5 KB runs code
- scripts/load-image-theme-macos.sh 4.8 KB runs code
- scripts/pause-dream-skin-macos.sh 2.3 KB runs code
- scripts/restore-dream-skin-macos.sh 2.4 KB runs code
- scripts/stage-theme.mjs 4.4 KB runs code
- scripts/start-dream-skin-macos.sh 5.5 KB runs code
- scripts/status-dream-skin-macos.sh 5.2 KB runs code
- scripts/switch-theme-macos.sh 3.5 KB runs code
- scripts/theme-config.mjs 11 KB runs code
- scripts/verify-dream-skin-macos.sh 844 B runs code
- scripts/write-theme.mjs 6.3 KB runs code
- Start Codex Dream Skin.command 317 B
- tests/image-metadata.test.mjs 3.0 KB runs code
- tests/injector-bootstrap.test.mjs 3.1 KB runs code
- tests/renderer-inject.test.mjs 20 KB runs code
- tests/run-tests.sh 32 KB runs code
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.
- 8d ago First seen · 37 lines · 70 tokens per session scan A f6c84211d70e
codex-dream-skin-studio is a skill published in the GitHub repository xnydl/codex-dream-skin (54 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 544 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
imagegen-frontend-web
Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not…
brandkit
Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional…
openclaw-brand
Apply OpenClaw visual identity to logos, typography, imagery, voice, documents, presentations, social graphics, and launch materials. Use when the task changes brand identity rather than ordinary product UI or public-page composition.
visualize
Render a polished visual inline in the chat as part of your answer — a diagram, a chart, an interactive explainer, or a UI mockup. Load it proactively whenever an explanation would land better as a picture than as prose. Do not wait to be asked.
vellum-avatar
Customize the assistant's avatar - build a native character, upload an image, or generate one with AI.
json-canvas
An Obsidian skill for generating JSON Canvas files. JSON Canvas is a file format for arranging connected boxes and other elements on a visual canvas.