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 ultrathink-art/agentbrush --skill agent-brushgit clone --depth 1 https://github.com/ultrathink-art/agentbrushWrote 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/ultrathink-art/agentbrush/agent-brush)<a href="https://agentmods.dev/skills/ultrathink-art/agentbrush/agent-brush"><img src="https://agentmods.dev/badge/skills/ultrathink-art/agentbrush/agent-brush/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/ultrathink-art/agentbrush/agent-brush"><img src="https://agentmods.dev/badge/skills/ultrathink-art/agentbrush/agent-brush.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 | $0.00048 | $0.01562 |
| Opus 5 | $0.00024 | $0.00781 |
| Sonnet 5 | $0.00010 | $0.00312 |
| Haiku 4.5 | $0.00005 | $0.00156 |
Grade A, and why
agent-brush 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentBrush — Image Editing for AI Agents
Image processing toolkit with background removal, green screen processing, border cleanup, text rendering, compositing, resizing, validation, and format conversion.
Quick Reference
All commands follow: agentbrush <command> <input> <output> [options]
Background Removal (edge-based flood fill — NEVER threshold-based)
# Remove black background
agentbrush remove-bg input.png output.png --color black --threshold 25
# Remove white background with edge smoothing
agentbrush remove-bg input.png output.png --color white --smooth
# Remove custom color background
agentbrush remove-bg input.png output.png --color "24,242,41" --threshold 40
Green Screen Removal (multi-pass pipeline)
# Standard green screen removal
agentbrush greenscreen input.png output.png
# With upscale + halo cleanup
agentbrush greenscreen input.png output.png --upscale 3 --halo-passes 20
Exits 1 when green survives enclosed by artwork (a see-through slit, a gap between two limbs, a window in a prop). Edge flood fill can only reach the field connected to the border, so an enclosed pocket structurally cannot be removed — it prints as a coloured bar inside the artwork. The error names its bbox and pixel count; the output file is still written so it can be repaired.
# Audit an existing cutout (key sampled from the pre-removal file = hard gate)
agentbrush validate trapped-green cutout.png --source original.png
# No source file left? Chroma heuristic — WARNING only, it also matches
# deliberate green artwork (terminal screens, foliage, matrix rain)
agentbrush validate trapped-green cutout.png
# Enclosed green really is artwork:
agentbrush greenscreen input.png output.png --allow-trapped-green
Border Cleanup (edge artifact removal)
# Remove white border artifacts from AI-generated images
agentbrush border-cleanup input.png output.png --passes 15 --threshold 185
# Full cleanup: white border + green halo + alpha smoothing
agentbrush border-cleanup input.png output.png --passes 15 --green-halo-passes 20 --alpha-smooth
What ships with it
11 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.
- references/product-specs.md 4.0 KB
- references/troubleshooting.md 6.1 KB
- scripts/add_text.py 3.4 KB runs code
- scripts/border_cleanup.py 1.5 KB runs code
- scripts/composite.py 3.0 KB runs code
- scripts/convert.py 1.5 KB runs code
- scripts/generate.py 1.5 KB runs code
- scripts/greenscreen.py 1.7 KB runs code
- scripts/remove_bg.py 1.5 KB runs code
- scripts/resize.py 1.6 KB runs code
- scripts/validate.py 2.6 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.
- 9d ago First seen · 187 lines · 48 tokens per session scan A d1ad0b67b478
agent-brush is a skill published in the GitHub repository ultrathink-art/agentbrush (9 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 1,562 once invoked, about $0.0002 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.