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/alejandro-ventures/llm-agnostic-icm-frameworknpx agentmods add skills/alejandro-ventures/llm-agnostic-icm-framework/background-removeWrote 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/alejandro-ventures/llm-agnostic-icm-framework/background-remove)<a href="https://agentmods.dev/skills/alejandro-ventures/llm-agnostic-icm-framework/background-remove"><img src="https://agentmods.dev/badge/skills/alejandro-ventures/llm-agnostic-icm-framework/background-remove/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/alejandro-ventures/llm-agnostic-icm-framework/background-remove"><img src="https://agentmods.dev/badge/skills/alejandro-ventures/llm-agnostic-icm-framework/background-remove.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 | $0.01269 |
| Opus 5.5 | $0.00008 | $0.00508 |
| Sonnet 5.5 | $0.00004 | $0.00254 |
| Haiku 4.5 | $0.00002 | $0.00127 |
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 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
background-remove
Inputs
| Source | Location | Why |
|---|---|---|
| Images | input/ |
source photos to process (copy reference images here first) |
Model selection — the decision tree
The right choice depends on image type, subject matter, and how much detail matters. Tested against close-up portraits with patterned backgrounds; results transfer reasonably well elsewhere.
| Model | Use when... | Time (on this box) | Notes |
|---|---|---|---|
u2net_human_seg (default) |
portraits, busts, people, fashion shots | ~1.5 s | Best balance of speed + clean edges for human subjects. Shoulders preserve up to ~80% image height on standard portrait framing. |
u2net_human_seg --post-process=false |
you need the most shoulder coverage and can accept fuzzier edges | ~1.2 s | Disables rembg's mask-tightening pass, which is what chews into shoulders. Edge pixels go from crisp to semi-transparent (500K+ partial-alpha transitions). Visualize with checkerboard composites before committing. |
u2net_human_seg --alpha-matting |
hair, fine boundaries, feathered edges matter more than speed | ~1.8 s | Adds alpha matting post-process for smoother gradient edges. Worth it on close-ups where individual strands are visible. +30% time vs default. |
u2netp |
you just need something fast and clean enough | ~0.3 s | Smallest, fastest model. Quality visibly lower at fine boundaries. Good for thumbnails or quick previews; not recommended for final output on detailed portraits. |
sam |
extreme quality is worth the cost, and subject is complex/non-human (animals, objects) | ~4–10 s | Segment Anything produces clean masks but still truncates shoulders on close-up portrait framing (body covers only ~65% of image height). Useful for non-portrait subjects; skip for people. |
Default recommendation
Use u2net_human_seg --post-process as your first pass. It handles 80%+ of close-up portrait work reliably and runs in ~1.5 s. Only change defaults when the user tells you something specific looks off.
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 · 73 lines · 19 tokens per session scan A 722925bd83cc
background-remove is a skill published in the GitHub repository alejandro-ventures/llm-agnostic-icm-framework (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 1,269 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
agent-engineering-expert
Build LLM agents that use tools safely: tool design, the agent loop, memory, MCP servers, multi-agent orchestration, sandboxing and prompt-injection defence. Use when the user mentions AI agents, tool use or function calling, MCP or Model Context Protocol, autonomous workflows, multi-agent systems, LangChain or…
junjo-evaluation
Turn a developer's product-quality objective into a complete Junjo Studio-backed evaluation workflow. Use when a coding agent needs to establish a baseline, design or generate typed cases, run or resume application-owned Node, Workflow, or Agent targets, inspect outcomes and exact trace evidence, compare a candidate…
junjo-openai-agents
Add Junjo's optional OpenAI Agents SDK integration to an application. Use when a coding agent needs to install junjo[openai-agents], expose a native Junjo Workflow or Agent as an OpenAI function tool, send standard OpenAI Agent and nested Junjo spans through one application-owned OpenTelemetry provider, declare an…
junjo-function-review
Execute the Junjo FunctionReview proof with Codex reasoning and optional Studio diagnostics. Use when asked to run the Junjo coding-agent example or validate its subagent workflow.
writing-workspace-jobs
Author FSM workspace jobs. Use when creating, editing, or debugging jobs, signals, or FSM workflows in workspace.yml.