SK

singhharsh1708/kitbash

Developer tools

このページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。 原文を見る

10 stars 品質 77 トレンド 32Apache-2.0

The package manager and compiler for AI agent skills — write once, run in Claude Code, Cursor, Codex, Copilot, Gemini CLI, and more

概要

Kitbash is a compiler for AI agent skills that measures what a skill costs your context window every session — before you install it. You write the skill once in one open format (KSF) and compile it to the native format of ten coding agents — Claude Code, Cursor, Copilot, Zed, Cline, Devin, Gemini CLI, Aider, the vendor-neutral .agents/skills/ path, and the AGENTS.md floor — plus an opt-in eleventh target, the Agent Plugins v1.0 package format. While compiling, it measures each output's cost: the tokens the skill parks in context on every request, whether or not it ever gets used. In a repo that already has .claude/ and .cursor/, that last command prints: The identical instructions cost ~40 standing tokens on a target that lazy-loads and ~560 on one that can't — a , charged before the skill is ever invoked, on every agent that has no lazy mode. A separate unmanifested fixture measures 19 against 885, a 47× gap. One real third-party skill from the skills.

README

以下は原文 README の抜粋です。原文を見る。

Kitbash

Kitbash is a compiler for AI agent skills that measures what a skill costs your context window every session — before you install it.

You write the skill once in one open format (KSF) and compile it to the native format of ten coding agents — Claude Code, Cursor, Copilot, Zed, Cline, Devin, Gemini CLI, Aider, the vendor-neutral .agents/skills/ path, and the AGENTS.md floor — plus an opt-in eleventh target, the Agent Plugins v1.0 package format. While compiling, it measures each output’s standing cost: the tokens the skill parks in context on every request, whether or not it ever gets used.

npm install -g kitbash      # or: brew install singhharsh1708/tap/kitbash
kitbash init
kitbash preview gh:singhharsh1708/kitbash/examples/skills/prereview   # read it first — nothing is written
kitbash install gh:singhharsh1708/kitbash/examples/skills/prereview
kitbash compile

In a repo that already has .claude/ and .cursor/, that last command prints:

→ .claude/skills/prereview/SKILL.md
→ .claude/commands/prereview.md
→ .cursor/rules/prereview.mdc
→ AGENTS.md
ℹ prereview → agentsmd: agentsmd is eager and cannot lazy-load, so this skill adds ~560 tokens standing every session (a lazy target pays 0; declared limit 60)
compiled 1 skill for 3 targets
  8 more target(s) available — add agents, zed, copilot, … under [project].targets in kitbash.toml, or create their agent dirs.

The ℹ line is why this is a compiler, not a converter

The identical instructions cost ~40 standing tokens on a target that lazy-loads and ~560 on one that can’t — a 14× per-session tax, charged before the skill is ever invoked, on every agent that has no lazy mode. A separate unmanifested fixture measures 19 against 885, a 47× gap. One real third-party skill from the skills.sh convention carries ~5,044 tokens of instructions, which compile to ~5,101 standing tokens on an eager target.

Those numbers are measured, not asserted: the method and the full per-target table are in docs/benchmarks/README.md, and npm run bench inside packages/cli regenerates them. A converter would translate the format and stop. Kitbash reads the skill and tells you what it will cost you. I have not found another tool that surfaces that number.

GitHub で README 全文を見る

推奨ツール

別のキーワードを試すか、フィルタを外してください。

インストール

npx skillfish add singhharsh1708/kitbash
MCP 初心者?mcpskill.org のガイドから始めましょう →