subagent-context

Name: subagent-context
Author: msshives-gif

msshives-gif ★ 2

This Claude Code plugin monitors subagent context window usage by hooking into SubagentStop, PreToolUse, and PostToolUse events, then reports token counts back to the orchestrating agent with warnings and optional blocking when context exceeds configurable thresholds. It prevents performance degradation by warning before re-tasking full agents and can optionally deny or ask confirmation before sending work to agents near their context limits.

Project Management Productivity No API key detected runs shell

Install

> /plugin marketplace add msshives-gif/claude-plugins/tree/HEAD/plugins/subagent-context

> /plugin install subagent-context

Source: https://github.com/msshives-gif/claude-plugins/tree/HEAD/plugins/subagent-context

What it's made of

3 hooks

Commands: 0
Agents: 0
Skills: 0
MCP servers: 0
Hooks: 3 · PostToolUse, PreToolUse, SubagentStop

What it needs & plugs into

API keys: none
Paid services: none detected
External tools: python python3
Talks to: nothing external detected

Analyzed 2026-10-17. 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 (msshives-gif).