Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/DKeken/codex-skills-alternativenpx agentmods add skills/dkeken/codex-skills-alternative/creative-polishWrote 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/dkeken/codex-skills-alternative/creative-polish)<a href="https://agentmods.dev/skills/dkeken/codex-skills-alternative/creative-polish"><img src="https://agentmods.dev/badge/skills/dkeken/codex-skills-alternative/creative-polish/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/dkeken/codex-skills-alternative/creative-polish"><img src="https://agentmods.dev/badge/skills/dkeken/codex-skills-alternative/creative-polish.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 | $0.00091 | $0.00960 |
| Opus 5 | $0.00046 | $0.00480 |
| Sonnet 5 | $0.00018 | $0.00192 |
| Haiku 4.5 | $0.00009 | $0.00096 |
Grade A, and why
creative-polish 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 9d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creative — Generative Polish
Turn a selected draft into a final, production-ready asset. This is the LAST stage — it only runs on an already-chosen visual. Polishing before a concept is locked wastes effort; this skill assumes the creative direction is settled and now it's about execution quality.
When to use
- A concept has been chosen (from explore/scene/shot/ads/offer) and needs finishing.
- An image has fixable flaws: artifacts, bad hands/text, off composition, wrong aspect.
- Conforming a winner to final delivery specs (size, ratio, color).
When NOT to use
- The concept isn't locked yet — polishing many candidates is wasteful; lock first.
- You need new concepts → the relevant explorer skill.
- The image is fundamentally wrong (bad composition at the core) — regenerate upstream instead of patching.
Inputs (ask only what's missing)
- The selected source image (path or reference).
- Target spec: final aspect/size, where it'll be used, brand constraints.
- What to improve — specific issues, or run a full pass.
Workflow
- Diagnose the source. List concrete issues: artifacts, extra fingers/garbled text, composition imbalance, color cast, soft focus, wrong aspect, distracting background.
- Decide per issue: edit (inpaint/region fix via an image-edit tool) when only a region is wrong — it keeps the rest stable; regenerate (re-prompt with stronger constraints + source as reference) when the issue is structural.
- Apply passes in order: structural fixes → composition/crop → color grade → text legibility → final sharpen/export. Save iterations to
./creative/polish/<NN>.pngso you can roll back. - Conform to final aspect/size for the target medium.
- Show before/after and confirm it meets spec.
Worked example
Source: chosen hero from creative-shot, but has a duplicated keycap, blurry legend text, slightly cool cast, and is 1:1 but the hero slot needs 16:9.
issues: [duplicated keycap top-row] [legend text soft] [too cool ~-300K] [need 1792x1024]
passes:
1. edit (inpaint): remove duplicate keycap, rebuild row — region fix, rest untouched
2. regen-region: sharpen legend text, pass exact legends verbatim
3. grade: warm +250K, lift shadows slightly
4. crop/extend to 1792x1024 (outpaint left/right of product)
before: ./creative/shot/hero-34.png after: ./creative/polish/hero-final.png
verify: keycaps correct, text crisp, neutral-warm, 1792x1024 ✓
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.
- 9d ago First seen · 62 lines · 91 tokens per session scan A da85e4e9a2a7
creative-polish is a skill published in the GitHub repository DKeken/codex-skills-alternative (15 stars, last pushed 3mo ago), licensed MIT. It adds 91 tokens to every session and 960 once invoked, about $0.0005 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
threejs-interaction
Three.js interaction - raycasting, controls, mouse/touch input, object selection. Use when handling user input, implementing click detection, adding camera controls, or creating interactive 3D experiences.
create-video-seedance-2-fal
Generate a single 4-15s vertical video clip with ByteDance Seedance 2.0 reference-to-video via fal.ai. Multi-image reference (avatar + product + setting), native lip-synced VO + ambient audio (generate-audio on by default), internal multi-cut handling within one render. Routes through the GooseWorks FAL proxy (bills…
playwright-recording
Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.
seedance-2-5
Generate 4-30 second cinematic video with ByteDance Seedance 2.5 through fal.ai, Volcengine Ark, Runway, or ComfyUI Partner Nodes. Use for long single generations, synchronized audio, and large multimodal reference sets (up to 30 images, 10 videos, and 10 audio clips). Also covers the 2.5 prompt contract: section…
threejs-shaders
Three.js shaders - GLSL, ShaderMaterial, uniforms, custom effects. Use when creating custom visual effects, modifying vertices, writing fragment shaders, or extending built-in materials.
threejs-textures
Three.js textures - texture types, UV mapping, environment maps, texture settings. Use when working with images, UV coordinates, cubemaps, HDR environments, or texture optimization.