rtk-ai/rtk

Feature request: configurable default flags for `rtk read` and `rtk grep`

Open

#2,091 创建于 2026年5月25日

在 GitHub 查看
 (2 评论) (0 反应) (0 负责人)Rust (2,914 fork)batch import
area:configenhancementhelp wantedpriority:medium

仓库指标

Star
 (48,085 star)
PR 合并指标
 (平均合并 11天 1小时) (30 天内合并 45 个 PR)

描述

Problem

When using RTK with an AI assistant (Claude Code), the flags -l aggressive (for rtk read) and --ultra-compact (for rtk grep) dramatically improve token savings — but they must be specified manually on every call.

Measured impact over real sessions:

  • rtk read without flag: ~1-6% savings (101 calls wasted)
  • rtk read -l aggressive: ~80% savings
  • rtk grep without flag: ~50% savings
  • rtk grep --ultra-compact: ~80% savings

Because these flags cannot be set as defaults, savings depend entirely on the AI assistant's behavior — which is inconsistent across sessions due to context resets. Average adoption sits at ~55% despite explicit instructions in CLAUDE.md.

Proposed Solution

Add a [defaults] section to config.toml allowing users to set default flags per command:

[defaults]
read_level = "aggressive"       # equivalent to -l aggressive on every rtk read
grep_ultra_compact = true       # equivalent to -u on every rtk grep

贡献者指南