Governor: A Claude Code Plugin to Cut Token Waste via Output Compression, Context Slimming, and Tool Filtering

✍️ OpenClawRadar📅 Published: May 2, 2026🔗 Source
Governor: A Claude Code Plugin to Cut Token Waste via Output Compression, Context Slimming, and Tool Filtering
Ad

Governor is a Claude Code plugin that tackles token and context bloat beyond simple style compression. It reduces output tokens, shrinks recurring memory files like CLAUDE.md, filters noisy build/test logs, and adds planning guardrails to prevent scope drift. It's installed as a Claude Code plugin, exposing a /governor:* command namespace.

Quick Start

bash install.sh --force

Restart Claude Code, then run:

/governor:status
/governor:audit
/governor:compress CLAUDE.md

Governor auto-starts in compact professional mode. Toggle with /governor:on and /governor:off.

Benchmarks

Small local benchmarks with Sonnet (non-interactive, no tools):

  • Output tokens (three technical prompts): Control avg 989 tokens → Governor avg 440 tokens (55.5% savings). Caveman-style gives 44.9% savings.
  • Memory compression: 1877-token file → 838 tokens (55.4% savings) with medium compression.
  • Tool output filtering: Synthetic pytest -vv noisy output of 54,314 estimated tokens → 1,726 tokens (96.8% blocked) with preserved failure lines.
Ad

Key Features

  • Always-on compact mode via SessionStart and UserPromptSubmit hooks.
  • Professional memory compression: /governor:compress CLAUDE.md rewrites verbose files while preserving code blocks, inline code, paths, URLs, headings, tables, warnings, and env vars. A quality guard rejects low-savings compressions and restores the backup.
  • Tool-output filtering: Summarizes noisy Bash/test/build output but preserves failure signals.
  • Telemetry ledger: /governor:status reports blocked tokens, failures, compactions.
  • Prompt guidance: Soft suggestions for vague broad prompts.
  • Plan and drift guard: /governor:plan creates an implementation contract; /governor:guard checks current changes against it.
  • Portable rule snippets: Compact-mode rules included for Codex, Gemini, Cursor, Windsurf, and Cline.

Commands

  • /governor:on / /governor:off – Enable/disable response compression
  • /governor:status – Usage dashboard and waste heat map
  • /governor:audit – Find bloated memory/rule files
  • /governor:compress CLAUDE.md – Compress memory files
  • /governor:full – Next Bash command returns full output
  • /governor:plan / /governor:guard – Scope management
  • /governor:benchmark – Explain benchmark results

Installation

# Local development
claude --plugin-dir .

One-line local install

bash install.sh --force

From repository

gh repo clone 0xhimanshu/governor cd governor bash install.sh --force

Heavy Claude Code users should try Governor if they struggle with context bloating, broad task drift, or noisy logs eating their quota. It's a serious alternative to style-only token savers.

📖 Read the full source: HN AI Agents

Ad

👀 See Also

CodeLedger: Open-source Claude Code plugin tracks token usage and background agents
Tools

CodeLedger: Open-source Claude Code plugin tracks token usage and background agents

CodeLedger is an open-source MCP server plugin for Claude Code that automatically tracks token usage across projects, identifies background agents, and provides cost optimization recommendations based on analysis of local JSONL session files.

OpenClawRadar
VidLens MCP Server: Persistent YouTube Knowledge Base for Claude
Tools

VidLens MCP Server: Persistent YouTube Knowledge Base for Claude

VidLens is a free, open-source MCP server that indexes YouTube content locally with semantic embeddings, treating videos as a persistent knowledge base rather than extracting temporary transcripts. It provides 41 tools across 10 modules for searching, analyzing, and retrieving video content.

OpenClawRadar
Axe: A 12MB CLI for Single-Purpose LLM Agents
Tools

Axe: A 12MB CLI for Single-Purpose LLM Agents

Axe is a lightweight Go binary that runs focused AI agents defined in TOML files. It treats agents like Unix programs, supporting stdin piping, sub-agent delegation, and multi-provider LLM integration.

OpenClawRadar
Open-source framework for persistent AI agent memory with local storage and graph-based retrieval
Tools

Open-source framework for persistent AI agent memory with local storage and graph-based retrieval

A developer has been building an open-source framework for persistent AI agent memory that stores data locally as Markdown files, uses wiki-links as graph edges, and implements Git for version control. The system features four-signal retrieval and graph-aware forgetting based on ACT-R cognitive science.

OpenClawRadar