Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add aiocean/claude-plugins/plugin install aio-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/aiocean/claude-plugins/aio-remove-background)<a href="https://agentmods.dev/skills/aiocean/claude-plugins/aio-remove-background"><img src="https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-remove-background/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/aiocean/claude-plugins/aio-remove-background"><img src="https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-remove-background.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 | $0.00109 | $0.01792 |
| Opus 5.5 | $0.00044 | $0.00717 |
| Sonnet 5.5 | $0.00022 | $0.00358 |
| Haiku 4.5 | $0.00011 | $0.00179 |
Grade A, and why
aio-remove-background 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aio-remove-background — RMBG-2.0 alpha matting → PNG RGBA cutout
Tách nền ảnh thành PNG RGBA cutout bằng RMBG-2.0 (BiRefNet) — alpha matte mềm bám sát silhouette, kể cả tóc/khói/glow. Pipeline đóng cứng (không tham số fiddle): matting → despill (color unmixing khử ánh nền hắt lên mép) → erode 1px.
Engine-agnostic. Ảnh nguồn từ đâu cũng được — chụp thật, screenshot, render từ
gpt-image / Imagen / SDXL / FLUX / Grok. Không phụ thuộc nền phải phẳng. Nếu ảnh có
nền phẳng (vd flat-magenta #FF00FF key từ render), despill còn ăn thêm — mép
sạch nhất.
Environment
- python3: !
which python3 2>/dev/null || echo "NOT INSTALLED" - Pillow: !
python3 -c "import PIL" 2>/dev/null && echo "installed" || echo "NOT INSTALLED" - numpy: !
python3 -c "import numpy" 2>/dev/null && echo "installed" || echo "NOT INSTALLED" - torch: !
python3 -c "import torch" 2>/dev/null && echo "installed" || echo "NOT INSTALLED" - transformers: !
python3 -c "import transformers" 2>/dev/null && echo "installed" || echo "NOT INSTALLED" - HF auth: !
hf auth whoami 2>/dev/null || huggingface-cli whoami 2>/dev/null || echo "NOT LOGGED IN (cần cho RMBG-2.0 gated repo)" - Script: !
echo "${CLAUDE_PLUGIN_ROOT}/skills/aio-remove-background/scripts/chroma-key.py"
Quick start
RB="${CLAUDE_PLUGIN_ROOT}/skills/aio-remove-background/scripts"
python3 $RB/chroma-key.py input.png output.png
python3 $RB/chroma-key.py render-magenta.png sprite.png # despill on (default)
python3 $RB/chroma-key.py photo.jpg cutout.png --no-despill # nền không phẳng → không cần despill
python3 $RB/chroma-key.py input.png out.png --model ZhengPeng7/BiRefNet # MIT, không gated
Output luôn là PNG RGBA — auto thêm .png nếu thiếu đuôi.
Hợp đồng
| Tham số | Bắt buộc | Ý nghĩa |
|---|---|---|
<input> |
✅ | Ảnh nguồn bất kỳ (PNG/JPG/WEBP). |
<output.png> |
✅ | Path PNG RGBA. Script auto thêm .png nếu thiếu. |
--despill / --no-despill |
⬜ | Mặc định bật. Khử ánh nền hắt lên mép (color unmixing dựa trên alpha và màu góc). Nền lộn xộn (ảnh chụp) → tắt vì sample 4 góc không còn nghĩa. |
--model |
⬜ | Mặc định briaai/RMBG-2.0 (CC BY-NC 4.0, gated). Thương mại → ZhengPeng7/BiRefNet (MIT, không gated). |
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.
- 1mo ago First seen · 107 lines · 109 tokens per session scan A 4315846ff9aa
aio-remove-background is a skill published in the GitHub repository aiocean/claude-plugins (4 stars, last pushed 28d ago), licensed MIT. It adds 109 tokens to every session and 1,792 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
eval-hooks
Audit Claude Code and Codex hooks for validity, safety, and correctness across settings.json, hooks.json, config.toml, plugin, and skill or agent frontmatter hooks. Resolves each command, checks event names, handler types, matchers, exit-code and JSON decision strategy, and timeouts against each host's documented…
design-patterns
Detect, suggest, and evaluate GoF design patterns in TypeScript/JavaScript codebases. Use when refactoring code, applying singleton/factory/observer/strategy patterns, reviewing pattern quality, or finding stack-native alternatives for React, Angular, NestJS, and Vue.
eval-agents
Audit custom subagent definitions for Claude Code (.claude/agents/.md) and Codex (.codex/agents/.toml): loadability against the native schema, description overlap, model tier, tool scope, and headless-safe instructions. Use when onboarding to a project with agents, after adding or importing agents, or when the parent…
eval-skills
Audit a project or library of skills for metadata, trigger boundaries, workflow completion criteria, local resource closure, instruction economy, tool scope, effort, and routing evidence. Use before shipping skills, after importing a skill collection, or when a skill triggers too often or not at all.
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
source-command-audit-whitepapers
Audit version freshness, FR/EN parity, and metadata quality of all whitepapers and recap cards.