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/hmaurus/masterclaude/splitnpx skills add hmaurus/masterclaude --skill splitgit clone --depth 1 https://github.com/hmaurus/masterclaudeWhat 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 | $0.00151 | $0.01688 |
| Opus 5 | $0.00076 | $0.00844 |
| Sonnet 5 | $0.00030 | $0.00338 |
| Haiku 4.5 | $0.00015 | $0.00169 |
Grade A, and why
split 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 yesterday.
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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Split
Ferramenta para dividir imagens em múltiplas partes independentes: grade regular, faixas horizontais/verticais, e auto-detecção de elementos em fundo uniforme.
Usa Pillow + numpy + OpenCV (headless) em virtualenv isolado em ~/venvs/image-split/.
Setup
Verificar se já está instalado
test -f ~/venvs/image-split/bin/python && ~/venvs/image-split/bin/python -c "import PIL; import numpy; print('OK')" || echo "PRECISA_INSTALAR"
Instalar (se necessário)
bash ${CLAUDE_PLUGIN_ROOT}/skills/split/scripts/setup.sh
Uso
~/venvs/image-split/bin/python ${CLAUDE_PLUGIN_ROOT}/skills/split/scripts/split.py INPUT --OPERAÇÃO [OPÇÕES]
Cada operação gera múltiplos arquivos em uma pasta de saída. Por padrão cria <nome>_split/ ao lado do arquivo original.
Referência rápida
| Operação | Flag | Exemplo | Resultado |
|---|---|---|---|
| Grade | --grid CxR |
--grid 4x3 |
12 pedaços (4 col × 3 linhas) |
| Faixas horiz. | --split-h N |
--split-h 3 |
3 faixas de cima para baixo |
| Faixas vert. | --split-v N |
--split-v 2 |
2 faixas esquerda para direita |
| Auto-detect | --auto-split |
--auto-split |
N elementos detectados |
Grid (grade regular)
--grid CxR divide a imagem em C colunas × R linhas.
# Sprite sheet 4 colunas × 3 linhas = 12 sprites
~/venvs/image-split/bin/python ${CLAUDE_PLUGIN_ROOT}/skills/split/scripts/split.py sprites.png --grid 4x3
# Collage 2×2
~/venvs/image-split/bin/python ${CLAUDE_PLUGIN_ROOT}/skills/split/scripts/split.py collage.jpg --grid 2x2
Arquivos de saída seguem o padrão: {nome}_r{linha}_c{coluna}.{ext}
Split horizontal
--split-h N divide em N faixas horizontais iguais (cortes de cima para baixo).
# Banner longo → 3 partes iguais
~/venvs/image-split/bin/python ${CLAUDE_PLUGIN_ROOT}/skills/split/scripts/split.py banner.jpg --split-h 3
Arquivos de saída: {nome}_strip_{n}.{ext}
Split vertical
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.
- yesterday First seen · 163 lines · 151 tokens per session scan A 05153f5f9122
split is a skill published in the GitHub repository hmaurus/masterclaude (2 stars, last pushed 1mo ago), licensed MIT. It adds 151 tokens to every session and 1,688 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…