background-remove

An image-processing tool that cuts the background away from a photo or graphic and saves the subject on a transparent background. It can use an AI model for complex images or a simpler method for clean white backgrounds.

In plain words
What is it for?
Use it to isolate products, people, icons, or other subjects, including processing multiple images in a folder. It outputs PNG or WebP files.
Why use it?
It avoids manual selection and erasing around a subject. The result can be placed over different backgrounds without a visible rectangle.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/michaelboeding/skills/background-remove
Any agent
npx skills add michaelboeding/skills --skill background-remove
Clone the repo
git clone --depth 1 https://github.com/michaelboeding/skills

Made for: Claude Code, Codex.

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,444 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00057 $0.01444
Opus 5 $0.00028 $0.00722
Sonnet 5 $0.00011 $0.00289
Haiku 4.5 $0.00006 $0.00144

Measured 2d ago against content hash 418541707d73, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

background-remove 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/background_remove.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/background-remove/SKILL.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Background Remove Skill

Remove backgrounds from images using AI (rembg/U2-Net) or built-in methods.

Output: PNG or WebP with transparent background.

Quick Examples

User Says What Happens
"Remove the background from this photo" AI removes background, outputs PNG
"Make this image transparent" Removes background, preserves subject
"Cut out the product from this image" Isolates subject with clean edges
"Remove backgrounds from all images in /photos" Batch processes multiple images
"Quick background removal, white background" Uses fast built-in method

Prerequisites

  • rembg - AI-based background removal (recommended)

    pip install rembg
    # Or with GPU acceleration (faster, requires CUDA)
    pip install rembg[gpu]
    
  • Pillow - Required for image processing

    pip install Pillow
    

The first run will download the U2-Net model (~170MB) which is cached for future use.

Methods

Method Description Best For
rembg AI-based using U2-Net model Complex images, photos, products (default)
builtin White-to-transparent conversion Icons, graphics with clean white backgrounds

Workflow

Step 1: Gather Requirements (REQUIRED)

Use the AskUserQuestion tool for each question. Ask ONE question at a time.

Q1: Image Source

"Which image(s) should I remove the background from?

Please provide the file path or paste the image."

Wait for response.

Q2: Method (Optional)

"Which removal method?

  • AI (rembg) - Best quality, works on any image (default)
  • Built-in - Faster, best for white backgrounds"

Wait for response. Default to AI if user doesn't specify.

Q3: Output Location (Optional)

"Where should I save the result?

  • Same location with _nobg suffix (default)
  • Custom path"

Wait for response.

Step 2: Execute Background Removal

Single image:

python3 ${SKILL_PATH}/skills/background-remove/scripts/background_remove.py \
  -i "/path/to/image.jpg" \
  -o "/path/to/output.png"

Read the full file on GitHub · 207 lines

Files

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.

Changes

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.

  1. 2d ago First seen · 207 lines · 57 tokens per session scan A 418541707d73

Subscribe to this mod's changes

background-remove is a skill published in the GitHub repository michaelboeding/skills (24 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 1,444 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens