00200200

Tokencut — AI skill for Claude Code

AI community

Reduce verbose AI coding output with a local CLI and MCP server.

How to install Tokencut

This entry records only its repository, not the path inside it, so there is no exact command to give. Open 00200200/tokencut and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Tokencut does

Reduce verbose AI coding output with a local CLI and MCP server. Targeted reads, output budgets, and recoverable context for Claude Code and Codex.

Alternatives in AI

AIHawk — Open-source AI browser agent: describe any task in plain language and it autonomously browses, clicks, types a 30.3k ★
Peekaboo — Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, o 3.2k ★
Squeez — Hook-based token compressor for 5 AI CLI hosts (Claude Code, Copilot CLI, OpenCode, Gemini CLI, Codex CLI) 188 ★

README

High-performance context compression engine and universal MCP server.
Reduces token consumption by 60–85% across Claude Desktop, ChatGPT macOS, Cursor, Claude Code, and terminal CLI without degrading reasoning or losing tracebacks.

Failure isolation: assertion failures and full tracebacks are retained while repetitive terminal noise is compacted.

The Context Accumulation Problem

AI coding agents (Claude Code, Cursor, Codex, Gemini CLI) run inside multi-turn conversation sessions. Every executed command, test runner output, and inspected file is appended to the conversation history and resent on every subsequent tur