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

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 --forceRestart Claude Code, then run:
/governor:status
/governor:audit
/governor:compress CLAUDE.mdGovernor 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 -vvnoisy output of 54,314 estimated tokens → 1,726 tokens (96.8% blocked) with preserved failure lines.
Key Features
- Always-on compact mode via
SessionStartandUserPromptSubmithooks. - Professional memory compression:
/governor:compress CLAUDE.mdrewrites 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:statusreports blocked tokens, failures, compactions. - Prompt guidance: Soft suggestions for vague broad prompts.
- Plan and drift guard:
/governor:plancreates an implementation contract;/governor:guardchecks 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
👀 See Also

LivingAgents.ai: A Web-Based AI Agent Simulation Using Claude API
LivingAgents.ai is a web-based simulation where every agent is powered by the Claude API, performing actions like foraging, trading, crafting, attacking, reproducing, and dying permanently, with each action requiring a real LLM call.

Peers MCP Server Connects AI Coding Sessions for Collaboration
Peers is a local MCP server that connects Claude Code and Codex sessions, allowing them to discover each other, collaborate through shared scratchpads, share artifacts like diffs and test reports, and hand off session context as structured markdown.

How AI assistants fetch web pages: Nginx log analysis of ChatGPT, Claude, Gemini and others
A developer tested five major AI assistants by prompting them with unique URLs and monitoring Nginx logs, revealing distinct retrieval patterns: ChatGPT, Claude, and Perplexity use dedicated user-agents while Gemini answered from its index without fetching.

Tendr Skill Adds CLI-Based Long-Term Memory with Hierarchy to Reduce Token Usage
A new OpenClaw skill separates reasoning from execution for long-term memory operations, using a CLI tool to handle structural changes deterministically. It supports wikilinks and explicit semantic hierarchy across files to reduce token consumption and prevent error accumulation.