token-guard

Name: token-guard
Author: yurukusa

yurukusa ★ 7

Token-guard is a Claude Code plugin that monitors and controls token consumption through hooks that warn on large file reads (100KB+), limit unique file reads per session, estimate token budgets, and cap subagent spawns. The plugin uses extracted operational data from 800+ hours of autonomous operation to provide consumption guardrails.

DevOps Code Review runs shell

Install

> /plugin marketplace add yurukusa/cc-safe-setup/tree/HEAD/plugins/token-guard

> /plugin install token-guard

Source: https://github.com/yurukusa/cc-safe-setup/tree/HEAD/plugins/token-guard

What it's made of

4 hooks

Commands: 0
Agents: 0
Skills: 0
MCP servers: 0
Hooks: 4 · PostToolUse, PreToolUse

What it needs & plugs into

API keys: CC_TOKEN_BLOCK CC_TOKEN_BUDGET
Paid services: none detected
External tools: ""))}catch(e){}})' %s print((d.get("tool_input") process.stdin.on(data,d=>s+=d).on(end,()=>{try{process.stdout.write(String((JSON.parse(s).tool_input stat { {}).file_path } })
Talks to: nothing external detected

Analyzed 2026-10-07. Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.

Is this your plugin?

Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (yurukusa).