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 devkindhq/ideogram-ai-toolkit --skill remove-background-workflowgit clone --depth 1 https://github.com/devkindhq/ideogram-ai-toolkitWrote 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/devkindhq/ideogram-ai-toolkit/remove-background-workflow)<a href="https://agentmods.dev/skills/devkindhq/ideogram-ai-toolkit/remove-background-workflow"><img src="https://agentmods.dev/badge/skills/devkindhq/ideogram-ai-toolkit/remove-background-workflow/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/devkindhq/ideogram-ai-toolkit/remove-background-workflow"><img src="https://agentmods.dev/badge/skills/devkindhq/ideogram-ai-toolkit/remove-background-workflow.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 | $0.00128 | $0.01261 |
| Opus 5.5 | $0.00051 | $0.00504 |
| Sonnet 5.5 | $0.00026 | $0.00252 |
| Haiku 4.5 | $0.00013 | $0.00126 |
Grade A, and why
remove-background-workflow scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`image_upload_id`: call `upload_image(filename=...)`, run the returned curl command in the How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remove Background Workflow
This skill orchestrates remove_background as its core call, pulling in upload_image,
get_recent_generations, and get_generation_status as supporting tools depending on how
the source image gets resolved. It's a thin orchestration workflow around a single MCP
call, not a prompt-composition skill — there's no composition-spec-format.md/
panel-anatomy.md-style reference here.
This skill handles exactly one image per invocation. If the user asks for several images at
once, run the workflow below once per image and report each result separately —
remove_background itself only accepts one source per call.
Before you start
Read references/background-removal-patterns.md before running step 2 of the workflow
below. It covers the single-source rule (why image_response_id and image_upload_id can
never both be set), the private/public default, and how to handle the running/pending
envelope some calls return instead of an immediate result.
Workflow
1. Resolve the source image
Figure out what the user means by "this image" before calling anything:
- A response from earlier this session — if the user is pointing at something just
generated or edited, pull the
response_idfromstructured_content.response_idson the priorgenerate_image/edit_image/etc. call. - A freshly attached local file — run the
upload_imageflow first to mint animage_upload_id: callupload_image(filename=...), run the returned curl command in the sandbox, and read the response'sidfield — notimage_url— as theimage_upload_id. - A vague reference ("the logo from earlier," "that last one") with no id yet in
context — call
get_recent_generationsand match by description and recency. If more than one plausible candidate exists, ask the user which one they mean rather than guessing.
Never pass both image_response_id and image_upload_id in the same call — exactly one of
the two, based on which path above resolved the source.
What ships with it
5 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.
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 · 100 lines · 128 tokens per session scan A 0c999bddb120
remove-background-workflow is a skill published in the GitHub repository devkindhq/ideogram-ai-toolkit (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 128 tokens to every session and 1,261 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
mangou-ai-motion-comics
Manages AI motion comic production projects with YAML assets and storyboards. Use when users need to initialize Mangou projects, edit storyboard or asset YAML, generate images or videos, split grid shots, stitch final videos, or debug task backfill.
gpt-image
Generate or edit images with GPT Image 2 or 2.5 through the packaged CLI and Reference Gallery. Use for image requests including imprecise 'GPT 2.5' model names, posters, typography, reference edits, and inpainting; resolve the model choice before generation.
get-prompt-from-image
Analyze user-provided reference images and reverse-engineer high-fidelity AI image-generation prompts. Use when the user asks to recreate, imitate, reverse-engineer, or extract prompts from photographs, illustrations, 3D renders, products, characters, landscapes, typography, logos, posters, or other visual references.…
soul
Embody this digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become the person—opinions, voice, worldview.
vastai-sdk
Vast.ai Python SDK — high-level API for GPU instances, volumes, serverless endpoints, and billing.
videoagent-image-studio
Tired of juggling 8 API keys? This skill gives you one-command access to Midjourney, Flux, Ideogram, and more, with zero setup. Use when you want to generate any image without worrying about API keys.