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 agentmods add skills/peterkrueck/claude-code-development-kit/image-editnpx skills add peterkrueck/Claude-Code-Development-Kit --skill image-editgit clone --depth 1 https://github.com/peterkrueck/Claude-Code-Development-KitWhat 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 | $0.00095 | $0.01140 |
| Opus 5 | $0.00048 | $0.00570 |
| Sonnet 5 | $0.00019 | $0.00228 |
| Haiku 4.5 | $0.00010 | $0.00114 |
Grade A, and why
image-edit 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 2d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Edit — Crop, Resize & Transform
Precision image manipulation using Python/Pillow. This skill exists because macOS sips has unreliable crop offset behavior and visual inspection alone leads to bad coordinates — images often have hundreds of pixels of invisible padding that throws off naive crops.
Setup
The scripts need Pillow and numpy. Create a temp venv on first use:
python3 -m venv /tmp/imgcrop && /tmp/imgcrop/bin/pip install Pillow numpy -q
This only needs to happen once per session. The venv at /tmp/imgcrop persists until reboot.
The Golden Rule: Measure Before You Cut
Never guess crop coordinates from visual inspection. Images routinely have large invisible regions — transparent padding, solid-color borders, or dead space — that make visual estimates wildly wrong.
Always run the analysis script first to get exact pixel coordinates of where the actual content lives.
Workflow
Step 1 — Visual inspection
Use the Read tool to look at the image. Understand what's in it and what the user wants to focus on.
Step 2 — Analyze content bounds
Run the bundled analysis script to find where content actually lives:
/tmp/imgcrop/bin/python3 .claude/skills/image-edit/scripts/analyze_bounds.py <image_path>
This outputs JSON with:
content_bounds— exact pixel coordinates of non-background contentpadding— how much dead space exists on each sidesuggested_square_crops— pre-calculated crop regions at different zoom levels:tight_head(35%) — face/head closeupupper_body(55%) — head through chest/armsthree_quarter(75%) — head through waistfull(100%) — entire subject
Use --threshold to adjust sensitivity (default 30).
Step 3 — Calculate crop coordinates
Use the analysis output to compute exact crop coordinates:
- Headroom: Add 40-70px above the content top
- Centering: Center horizontally on the content's center-x, not the image's center
- Aspect ratio: For square crops, use
max(width, height)as the side length - Clamping: Ensure the crop region doesn't extend beyond image dimensions
What ships with it
2 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.
- 2d ago First seen · 117 lines · 95 tokens per session scan A 99c8df81adfa
image-edit is a skill published in the GitHub repository peterkrueck/Claude-Code-Development-Kit (1,380 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 1,140 once invoked, about $0.0005 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.