espresso

---

The Problem

Every AI coding agent produces verbose output by default. "Sure! I'd be happy to help. Let me walk you through this step by step..." That's tokens you pay for, time you waste reading, and context window you burn.

Fixing it requires configuring multiple tools, writing rules, setting up hooks. Most developers don't bother.

What Espresso Does

Installs once. Detects what you already have. Adds only what's missing.

What gets configured	Savings	How
Output rules	40-60%	Enforces 120 char lines, forbidden openers/closers, result-first, no filler
Global rules	context savings	Creates ~/.claude/rules/ — Exa search, clean git, GitNexus, project rules
GitNexus	fewer file reads	Configures MCP server + auto-reindex hook (if GitNexus binary installed)
Caveman ultra	~75%	Sets compressed conversation mode (if Caveman plugin installed)
RTK hook	60-90% CLI	Adds CLI output compression hook (if RTK binary installed)

Detection-first: Espresso checks what's already configured and skips it. Never overwrites your existing rules or config. Never installs duplicates.

---

Before / After

Without Espresso:
  Sure! I'd be happy to help you with that. The issue you're
  experiencing is likely caused by a misconfiguration in your
  authentication middleware. Let me explain what's happening and
  walk you through the solution step by step...

With Espresso:
  Bug in auth middleware. Token expiry check uses `<` not `<=`. Fix:

Same information. 70-85% fewer tokens with the full stack.

---

Install

Claude Code (in the Claude Code prompt)

3 commands. Type them inside Claude Code, not in a regular terminal.

/plugin marketplace add mirkobozzetto/espresso
/plugin install espresso@espresso
/reload-plugins

Or from a regular terminal:

claude plugin marketplace add mirkobozzetto/espresso
claude plugin install espresso@espresso

Then restart Claude Code. First session auto-configures the full stack.

Cursor / Windsurf / Copilot / Codex / Others

These agents don't have plugin hooks. One command in your project root:

curl -sL https://raw.githubusercontent.com/mirkobozzetto/espresso/main/AGENTS.md > AGENTS.md

Codex, Cursor, Windsurf, Copilot, Amp, and Devin read AGENTS.md natively. You get the output rules (40-60% savings) but not the full stack auto-install.

---

Exa MCP — Web Search for Your Agent

Espresso rules enforce Exa as the only web search tool. Exa is a free hosted MCP — no API key required.

Agent	Setup
Claude Code	claude mcp add --transport http exa https://mcp.exa.ai/mcp
Codex	Add exa MCP in .codex/config.toml with URL https://mcp.exa.ai/mcp
Cursor	Add to ~/.cursor/mcp.json: {"mcpServers": {"exa": {"url": "https://mcp.exa.ai/mcp"}}}
VS Code	Add to .vscode/mcp.json: {"servers": {"exa": {"type": "http", "url": "https://mcp.exa.ai/mcp"}}}
Claude Desktop	Settings → Connectors → search "Exa" → click +

Free plan includes generous rate limits. For production use, add your API key:

• Get one at exa.ai/dashboard
• Add header: "x-api-key": "YOUR_KEY" to MCP config

Docs: docs.exa.ai/docs/reference/exa-mcp

---

Optional Companions

Espresso auto-configures these if already installed. Install them for maximum savings:

npm install -g gitnexus                     # Code intelligence — knowledge graph for your codebase
brew install rtk-ai/tap/rtk                 # CLI output compression (60-90%)

/install-plugin JuliusBrussee/caveman       # Conversation compression (~75%)

Restart your agent after installing any of these. Espresso detects and configures on next session.

What each companion does

GitNexus — builds a knowledge graph of your codebase (functions, classes, call chains, execution flows). Instead of Claude grepping through files to understand code, it queries the graph. Fewer file reads = fewer tokens. Espresso configures the MCP server and adds an auto-reindex hook that keeps the index fresh after every session.

RTK (Rust Token Killer) — transparent proxy that compresses CLI output before it enters context. git status, npm test, docker ps output shrinks 60-90%. You run commands normally — RTK intercepts and compresses automatically via hook.