Cut — Development skill for Claude Code
Get an answer under its word limit without gutting it.
How to install Cut
Installs to ~/.claude/commands/calebnewtonusc-apply-kit-cut.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/calebnewtonusc/apply-kit/HEAD/.claude/commands/cut.md -o ~/.claude/commands/calebnewtonusc-apply-kit-cut.md Restart Claude Code, or start a new session, for it to be picked up.
What Cut does
description: Get an answer under its word limit without gutting it argument-hint: [org name and question number]
Cut $1 to its limit. Run `tools/count.sh` for the count before and after and report what it says. Do not estimate a word count.
Order of cuts
Take from the top of this list first. Stop as soon as you are under.
- The closing reflection. "What it changed about how I think." Everyone writes it and it reads most like everyone.
- Adverbs and hedges. Really, ver
Alternatives in Development
- Working Memory — This is your working memory 192 ★
- Edgee — Official Edgee CLI to interract with Edgee's Agent Gateway 127 ★
- Cut Video — Claude Code skill: tighten long recordings — remove silences, ums, dead air 92 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
P Unsummarizable
Make writing unsummarizable — strip all fluff so no word can be cut without losing an idea
Ks Idol Mv
Write an original tribute song for your idol, then cut a word-synced lyric MV from real news photos and offici
Claude Code Intelligence
Local-first usage intelligence for Claude Code: an OTLP receiver, transcript parsing and quota tracking that a
Lcc
Compact coding-agent context without summarizing it away. Verbatim, offline, with a receipt and recall for eve
Noise Budget
Cut wasted token spend without skipping real bugs. Distinguish IMPOSSIBLE work (tech-mismatch CVEs, encoded re
Critique Adversarial
/critique-adversarial — Hostile cut-editor for articles. Reads the full piece first, maps the thesis spine, th
Related Agents
Lesson Window Reader
Reads one 10-minute window of a raw lesson take against the shooting script and proposes every content cut in
AI Cost Optimizer
Audits an LLM application or AI agent for token cost and rate-limit risk, using its usage logs and code, and r
Deep Review Guard Bypass
Traces guard functions (permission, capacity, rate-limit, validation) to find any code path that reaches a pro