agentmods.dev

aisee:image-object

aisee:image-object is a skill for Claude Code, Codex from AISEE-LAB/aisee-plugin. It costs 110 tokens per session (1,855 once invoked), scanned A, original, MIT.

A workflow for extracting reusable objects from an existing image, such as a product or person, and saving cutouts, masks, repaired backgrounds, and image variants. A mask is a shape that marks which pixels belong to the selected object.

In plain words
What is it for?
Use it to remove backgrounds, isolate objects, refine selections, repair areas behind removed objects, export transparent or padded versions, and prepare selected assets for later design or implementation work.
Why use it?
It separates image editing work from image generation and keeps the original, intermediate files, and exported assets organized. It also avoids overwriting existing results unless explicitly allowed.

Skill for Claude CodeCodex

Part of the aisee-plugin plugin — 14 skills shipped together

not rated 11 2mo ago A scan 110 tokens original MIT
View the source file AISEE-LAB/aisee-plugin
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/aisee-lab/aisee-plugin/aisee-image-object
Any agent
npx skills add AISEE-LAB/aisee-plugin --skill aisee-image-object
Clone the repo
git clone --depth 1 https://github.com/AISEE-LAB/aisee-plugin

Made for: Claude Code, Codex.

Or install aisee-plugin, the plugin that ships this one along with the rest of its 14 skills.

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 aisee:image-object

README.md
[![agentmods](https://agentmods.dev/badge/skills/aisee-lab/aisee-plugin/aisee-image-object.svg)](https://agentmods.dev/skills/aisee-lab/aisee-plugin/aisee-image-object)
Your own site
<a href="https://agentmods.dev/skills/aisee-lab/aisee-plugin/aisee-image-object"><img src="https://agentmods.dev/badge/skills/aisee-lab/aisee-plugin/aisee-image-object.svg" alt="Measured on agentmods" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,855 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 $0.00110 $0.01855
Opus 5 $0.00055 $0.00928
Sonnet 5 $0.00022 $0.00371
Haiku 4.5 $0.00011 $0.00186

Measured 5d ago against content hash 0ccf27a1da44, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aisee:image-object 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 5d ago.

The scan reads SKILL.md. This mod also ships 42 executable files (scripts/check_dependencies.py, scripts/export_runner.py, scripts/extract_object.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.

plugins/aisee-plugin/skills/aisee-image-object/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

aisee:image-object

把一张输入图处理成可复用对象素材、mask、背景修补图、导出变体和图层包。凡是“基于已有图片提取素材、切出素材、生成透明对象、修补背景或局部重绘”的执行流程，都归本 skill 管理。它是图片处理 workflow，不是图片生成或设计规范 skill；skill 目录只保存说明、模板和脚本，项目产物写入目标项目目录。

适用输入

  • 本地 PNG/JPG/WebP、已有 mask/alpha、或 aisee:design-assets 生成的纯色/绿幕主体图。
  • 抠图、去背景、对象分割、点选/框选、mask refine、透明切图、圆角/padding 导出、背景修补或图层拆分。
  • 从截图、海报、参考图或产品图提取一个或多个可复用对象素材。
  • 需要把过程文件整理成单图 workspace、source.json、导出变体或 Image Gen 局部优化 handoff。

边界

必须：

  • 使用单图 workspace 管理产物，默认输出到 aisee/docs/image-objects/<name>/。
  • source.json 是 GUI、CLI、模型 backend、导出和 handoff 的共同合同。
  • 每次处理都明确 scope；原始 mask/cutout/background 与导出变体分开保存。
  • 去背景优先成熟模型；背景修补优先 LaMa / IOPaint，OpenCV 只作显式低质量 fallback。
  • SAM/SAM2、LaMa、BiRefNet 等作为可选 backend；运行环境优先复用全局配置，不重复配置重依赖。
  • 局部重绘或 Image Gen handoff 只携带相关 source/mask/bbox/cutout/scope 和保护约束。
  • 可复用素材进入项目级视觉资产库时，只把 export/cutout/enhanced 路径和用途交给 aisee:design-assets 登记。

不要：

  • 不生成参考图、StyleSpec 或全局设计提示词；这些交给 aisee:design-assets。
  • 不直接写入 Figma 或实现前端页面。
  • 不把 GUI 对象备注、整个 source.json、全部缩略图或 preview-cache/ 默认塞进大模型提示。
  • 不默认覆盖 workspace 内已有产物，除非用户明确要求或传入 --force。
  • 不保存、输出或提交 API Key、令牌、Cookie、证书等敏感信息。

OpenSpec 接入

当对象素材进入 OpenSpec change：

  • ui-contract.md 只引用 cutout、mask、export、enhanced 或图层包路径和使用范围。
  • source-map.md 记录 IMG/OBJECT/MASK 与 PAGE、PAT、FR、tasks 和文件路径关系。
  • tasks.md 只记录素材接入、边缘复核、背景验证、截图比对或人工验收。
  • 不复制完整 source.json、过程图、mask 历史或 workspace 索引正文。

Phase 0 — 读取上下文

先定位目标项目目录：用户给了项目路径就用该路径，否则使用当前工作目录。

静默收集已有对象处理产物：

rg --files aisee/docs/image-objects 2>/dev/null | head -80
rg --files | rg '(^|/)source\.json$|mask.*\.png$|cutout.*\.png$' | head -80

扫描必须遵守 .gitignore。优先使用 rg --files；如果 rg 不可用，fallback find 必须显式排除 .git、依赖目录、构建产物、缓存目录和生成产物，不要把无效文件当作 workspace 事实。

如果已有 workspace，先读取 source.json，避免重复命名、重复导出或覆盖用户手工修正的 mask。

Phase 1 — 选择最小闭环

按用户意图选择最小流程，并只读取相关 reference：

  • workspace、source.json、目录命名：读 references/source-json.md、references/output-layout.md
  • 素材提取、端到端流程：读 references/asset-extraction.md、references/workflows.md
  • 依赖、模型 backend、GUI：读 references/dependencies.md、references/model-backends.md、references/gui-design.md
  • 导出选项、透明切图、图层包：读 references/export-options.md

Read the full file on GitHub · 121 lines

Files

What ships with it

59 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.

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. 5d ago First seen · 121 lines · 110 tokens per session scan A 0ccf27a1da44

Subscribe to this mod's changes

aisee:image-object is a skill published in the GitHub repository AISEE-LAB/aisee-plugin (11 stars, last pushed 2mo ago), licensed MIT. It adds 110 tokens to every session and 1,855 once invoked, about $0.0006 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.

Creative and mediaOpenSpecagentaicodexcompound-engineeringsoftware-engineering
Related

Other skills, from other repositories

openase-platform

Platform operations for tickets, projects, and runtime coordination inside OpenASE.

PacificStudio/openase · 18 tokens

deploy-coolify-review-env

Create or update a branch-scoped Coolify review environment with one command, and delete it with one command. Use when a ticket must deploy a preview before human review, while keeping the workflow simple and fast.

PacificStudio/openase · 49 tokens

land

Land an OpenASE PR by syncing with main, resolving conflicts, waiting for CI, addressing review feedback, and squash-merging when green.

PacificStudio/openase · 30 tokens

push

Push current branch changes to origin and create or update the corresponding pull request for OpenASE; use when asked to push, publish updates, or create a pull request.

PacificStudio/openase · 35 tokens

local-bootstrap-cli-auth-debug

Diagnose and repair OpenASE CLI access in local bootstrap mode. Use when protected openase commands fail because the CLI is missing a local human session, has a stale /.openase/human-session.json, is missing CSRF state, or needs a fresh openase auth bootstrap login.

PacificStudio/openase · 68 tokens

ticket-workpad

Maintain the persistent ticket work log comment on the current ticket and use it as the execution log.

PacificStudio/openase · 23 tokens