# Reduce agent token burn on repo-scale coding commands with the rtk CLI proxy

> Use rtk when an agent keeps wasting context on noisy shell output from large repos and you need smaller command responses before the model sees them.

- Skill: `agentskillexchange/reduce-agent-token-burn-on-repo-scale-coding-commands-with-t` (Agent Skill)
- Install (CLI): `npx skillmds@latest add agentskillexchange/reduce-agent-token-burn-on-repo-scale-coding-commands-with-t`
- Raw SKILL.md: https://api.skillmd.com/api/skills/agentskillexchange/reduce-agent-token-burn-on-repo-scale-coding-commands-with-t/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: agentskillexchange (https://skillmd.com/u/agentskillexchange)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/agentskillexchange/reduce-agent-token-burn-on-repo-scale-coding-commands-with-t

---


# Reduce agent token burn on repo-scale coding commands with the rtk CLI proxy

Use rtk when an agent keeps wasting context on noisy shell output from large repos and you need smaller command responses before the model sees them.

## Prerequisites

A shell-heavy coding-agent workflow, a supported agent such as Claude Code, Codex, Cursor, Gemini CLI, or Cline/Roo, and permission to install a local RTK hook or call rtk directly.

## Installation

No source-backed install or usage instructions could be extracted automatically. Review the upstream project before running this skill in a sensitive workflow.

- Source: https://github.com/rtk-ai/rtk

## Documentation

- https://www.rtk-ai.app/guide

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/reduce-agent-token-burn-on-repo-scale-coding-commands-with-the-rtk-cli-proxy/)