agentmods.dev

froggo-mission-control: Skill for Claude Code

.claude/skills/image-cutout/SKILL.md

image-cutout is a skill for Claude Code from ProfFroggo/froggo-mission-control. It costs 51 tokens per session (3,673 once invoked), scanned B, original, Apache-2.0.

High-quality programmatic background removal — covers tool selection by use case, SAM 2 maximum quality pipeline, BiRefNet-HD, alpha matting for hair/fur, FBA Matting, edge refinement, and output best practices.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is ProfFroggo/froggo-mission-control's own configuration. It tells Claude Code how to work on froggo-mission-control itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything froggo-mission-control configures →

not rated 2repo 6mo ago B scan 51 tokens original Apache-2.0
View source ↗ ProfFroggo/froggo-mission-control
Reuse

Borrowing it

Nothing to install: this file belongs to ProfFroggo/froggo-mission-control. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ProfFroggo/froggo-mission-control/dev/.claude/skills/image-cutout/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ProfFroggo/froggo-mission-control

Made for: Claude Code.

Wrote 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.

agentmods badge for image-cutout

README.md
[![agentmods](https://agentmods.dev/badge/skills/proffroggo/froggo-mission-control/image-cutout/github.svg)](https://agentmods.dev/skills/proffroggo/froggo-mission-control/image-cutout)
Your own site
<a href="https://agentmods.dev/skills/proffroggo/froggo-mission-control/image-cutout"><img src="https://agentmods.dev/badge/skills/proffroggo/froggo-mission-control/image-cutout/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.

agentmods 80×15 button for image-cutout

Your own site · 80×15
<a href="https://agentmods.dev/skills/proffroggo/froggo-mission-control/image-cutout"><img src="https://agentmods.dev/badge/skills/proffroggo/froggo-mission-control/image-cutout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,673 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00051 $0.03673
Opus 5.5 $0.00020 $0.01469
Sonnet 5.5 $0.00010 $0.00735
Haiku 4.5 $0.00005 $0.00367

Measured today against content hash 7d7f1fdb48c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

image-cutout scanned grade B with 2 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 today.

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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

response = requests.post( 'https://api.remove.bg/v1.0/removebg',

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

wget https://dl.fbaipublicfiles.com/segment_anything_2/072824/sam2_hiera_large.pt
.claude/skills/image-cutout/SKILL.md · 409 lines

How it starts

The opening of the file, as written. The whole thing — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Image Cutout (Background Removal)

When to Use This Skill

Any time a task involves:

  • Removing a background from a photo, product image, or illustration
  • Creating transparent-background PNGs for UI, marketing, or compositing
  • Preparing subject isolations for further design work (collages, mockups, overlays)
  • Batch-processing image assets

Always output PNG with alpha channel. Never output JPEG for cutouts.

Quality Tiers

Tier Approach When to use
Maximum SAM 2 + FBA Matting Hero shots, complex hair, precise control
Excellent rembg birefnet-hd + alpha matte High-res assets, portraits, products
Good / fast rembg birefnet-general Batch, standard web assets
Paid API remove.bg / PhotoRoom API Client deliverables where quality is non-negotiable
Browser/Edge @imgly/background-removal Frontend / Node.js pipelines

Default pick for ALL work: SAM 2 + FBA Matting. This is the mandatory default — always use it unless there is a specific reason not to (e.g. no Python environment, tight deadline, batch of 50+ images). Never default to rembg when doing a single cutout. rembg is a fallback, not a default.

Tool Selection by Use Case

Use case Best tool Quality
Products / hard edges rembg (birefnet-general) Excellent
Portraits, standard res rembg (birefnet-general) + alpha matte Excellent
High-res portraits / large images rembg (birefnet-hd) + alpha matte Superior
Hair / fur / fine detail — maximum quality SAM 2 + FBA Matting Best possible
Batch / CI pipeline rembg (birefnet-general) loop Fast
Maximum quality, paid remove.bg or PhotoRoom API Reference
Browser / Edge runtime @imgly/background-removal (WASM) Good

Python — rembg (primary approach)

Install

pip install rembg[gpu] pillow  # GPU (CUDA) — fastest
pip install rembg pillow       # CPU — no GPU needed

Read the full file on GitHub · 409 lines

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. today First seen · 409 lines · 51 tokens per session scan B 7d7f1fdb48c8

Subscribe to this mod's changes

image-cutout is a skill published in the GitHub repository ProfFroggo/froggo-mission-control (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 51 tokens to every session and 3,673 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-07.

Related

image-cutout compared with skills from other repositories

image-cutout next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
image-cutoutProfFroggo/froggo-mission-controlSkill26mo agoApache-2.0B51Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143ktodayMITA103Claude Code