Harness Anything is a collection of tools that lets AI agents control office, research, and design applications through command-line interfaces and Windows automation. It supports tasks such as editing WPS or Microsoft Office files, managing Zotero research workflows, creating Illustrator graphics, and generating data-driven presentations.
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 yb2460/harness-anything --skill cli-anything-photoshopgit clone --depth 1 https://github.com/yb2460/harness-anythingWrote 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/yb2460/harness-anything/cli-anything-photoshop)<a href="https://agentmods.dev/skills/yb2460/harness-anything/cli-anything-photoshop"><img src="https://agentmods.dev/badge/skills/yb2460/harness-anything/cli-anything-photoshop/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/yb2460/harness-anything/cli-anything-photoshop"><img src="https://agentmods.dev/badge/skills/yb2460/harness-anything/cli-anything-photoshop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00043 | $0.01609 |
| Opus 5.5 | $0.00017 | $0.00644 |
| Sonnet 5.5 | $0.00009 | $0.00322 |
| Haiku 4.5 | $0.00004 | $0.00161 |
Grade A, and why
cli-anything-photoshop 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI-Anything Photoshop
通过 Windows COM 自动化接口操控 Adobe Photoshop 的命令行工具。
前置条件
- Windows 10/11
- Adobe Photoshop 2023+ (需注册 COM 接口)
- Python 3.10+ 及
pywin32包
安装
cd photoshop-harness/agent-harness
pip install -e .
安装后可使用 cli-anything-photoshop 命令。
命令结构
cli-anything-photoshop [--json] [--project <path>] [--dry-run] <command-group> <command> [options]
全局选项
| 选项 | 描述 |
|---|---|
--json |
以 JSON 格式输出（供 AI Agent 解析） |
--project <path> |
自动打开或创建 PSD 项目文件 |
--dry-run |
执行命令但不保存到磁盘 |
命令组
project — 项目管理
| 命令 | 选项 | 描述 |
|---|---|---|
new <path> |
-w width, -h height, -r resolution, -m mode, -b bg-color |
创建新 PSD |
open <path> |
打开 PSD 文件 | |
save [path] |
保存文档 | |
close |
--no-save |
关闭文档 |
document — 文档操作
| 命令 | 选项 | 描述 |
|---|---|---|
info |
文档信息 | |
resize |
-w width, -h height, -r resolution |
调整尺寸 |
canvas |
-w width, -h height, -a anchor |
调整画布 |
crop |
--left --top --right --bottom |
裁切 |
rotate |
-a angle |
旋转画布 |
flip |
-d direction |
翻转画布 |
mode |
-m mode |
更改色彩模式 |
trim |
-t type |
裁切边缘 |
layer — 图层操作
| 命令 | 选项 | 描述 |
|---|---|---|
add |
-n name, -t type, -o opacity, -b blend |
添加图层 |
delete |
-n name |
删除图层 |
duplicate |
-n name, --new-name name |
复制图层 |
rename |
--old name, --new name |
重命名 |
show / hide |
-n name |
显示/隐藏 |
opacity |
-n name, -o opacity |
设置透明度 |
blend |
-n name, -m mode |
设置混合模式 |
list |
列出所有图层 | |
reorder |
-n name, -p position |
调整顺序 |
merge |
-n name, --with-layer name |
合并图层 |
selection — 选区操作
| 命令 | 选项 | 描述 |
|---|---|---|
all |
全选 | |
none |
取消选区 | |
invert |
反转选区 | |
feather |
-r radius |
羽化 |
expand |
-p pixels |
扩展 |
contract |
-p pixels |
收缩 |
border |
-w width |
边框选区 |
rect |
--left --top --right --bottom |
矩形选区 |
fill |
-c color, -o opacity |
填充选区 |
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 · 151 lines · 43 tokens per session scan A cb4e9df4cdc6
cli-anything-photoshop is a skill published in the GitHub repository yb2460/harness-anything (2,590 stars, last pushed 18d ago), licensed MIT. It adds 43 tokens to every session and 1,609 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
get-context
Mandatory design-brief gate for clarifying the product and outcome. Use before ideation, image-to-code builds, redesigns, or product UI work to clarify missing product information and play back the brief before proceeding.
frontend
Builds, styles, and polishes anything drawn with HTML, CSS, or SVG: web UI, pages, components, HTML reports rendered to PDF or print, figures, PNG/SVG diagrams, slides, and images for Notion or Slack. Use for any styling, layout, animation, or visual-quality task, or when asked to make something look or feel a certain…
deck-graphify-dark
A dark slide-deck template for AI tools, developer tools, and knowledge graphs, using gradients, floating blurred shapes, graph diagrams, code styling, and glass-like cards.
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…
omd-apply
A skill that applies a project's DESIGN.md file as visual and brand guidance for interface work. It covers components, colors, fonts, layout, copy, motion, and visual assets.