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/DorianSchlede/nexus-templatenpx agentmods add skills/dorianschlede/nexus-template/gemini-refine-imageWrote 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/dorianschlede/nexus-template/gemini-refine-image)<a href="https://agentmods.dev/skills/dorianschlede/nexus-template/gemini-refine-image"><img src="https://agentmods.dev/badge/skills/dorianschlede/nexus-template/gemini-refine-image/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/dorianschlede/nexus-template/gemini-refine-image"><img src="https://agentmods.dev/badge/skills/dorianschlede/nexus-template/gemini-refine-image.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 | $0.00019 | $0.00403 |
| Opus 5 | $0.00010 | $0.00201 |
| Sonnet 5 | $0.00004 | $0.00081 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
gemini-refine-image 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 10d 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.
What it actually says
Refine Image with Gemini
Iteratively refine previously generated images.
Usage
cd 03-skills/google-gemini-image
# First, generate an image
uv run python gemini-generate-image/scripts/generate_image.py "a castle on a hill"
# Then refine it (uses last generated image)
uv run python gemini-refine-image/scripts/refine_image.py "add a dragon flying above"
# Or refine a specific image
uv run python gemini-refine-image/scripts/refine_image.py "make it sunset" --image castle.png
Options
| Option | Description |
|---|---|
prompt |
Refinement instructions |
--image |
Specific image to refine (default: last generated) |
--output |
Output filename (default: auto-generated) |
Examples
# Iterative refinement workflow
uv run python gemini-generate-image/scripts/generate_image.py "a cozy cabin"
# -> generated_20260131_123456.png
uv run python gemini-refine-image/scripts/refine_image.py "add snow on the roof"
# -> refined_20260131_123500.png
uv run python gemini-refine-image/scripts/refine_image.py "add smoke from chimney"
# -> refined_20260131_123530.png
uv run python gemini-refine-image/scripts/refine_image.py "add northern lights in sky"
# -> refined_20260131_123600.png
How It Works
- Takes the last generated/refined image (or specified image)
- Sends it to Gemini with your refinement prompt
- Returns the refined version
- The refined image becomes the new "last image" for further iteration
Part of google-gemini-image integration
What ships with it
1 file 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.
- 10d ago First seen · 60 lines · 19 tokens per session scan A 693cbbe3687d
gemini-refine-image is a skill published in the GitHub repository DorianSchlede/nexus-template (8 stars, last pushed 7mo ago), licensed MIT. It adds 19 tokens to every session and 403 once invoked, about $0.0001 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 2026-08-31.
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.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
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).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.