Token导航 LogoToken导航TokenDH.com
研究检索external-servicegithub未标认证来源可访问clear审计通过

ecomodeecomode 搜索

Agent Skill

ecomode 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

903

周安装

38

GitHub Stars

31,965

下载量

316
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

3

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:ecomode(ecomode 搜索)
来源仓库:https://github.com/yeachan-heo/oh-my-claudecode
仓库路径:skills/ecomode
安装命令:
npx skills add https://github.com/yeachan-heo/oh-my-claudecode --skill ecomode
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/yeachan-heo/oh-my-claudecode --skill ecomode

简介

模型路由优化器,优先选择低成本推理层级以提升效率。

  • 自动降级机制:HIGH 级仅用于必要任务,LOW 级默认使用 haiku 模型。
  • 作为修饰模式运行,不独立生效,需配合其他执行流程使用。
  • 不持久化状态,不支持并行或强制委派,仅限核心调度层激活。
  • ecomode 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Ecomode Skill

Token-efficient model routing. This is a MODIFIER, not a standalone execution mode.

What Ecomode Does

Overrides default model selection to prefer cheaper tiers:

Default TierEcomode Override
HIGH (opus)MEDIUM (sonnet), HIGH only if essential
MEDIUM (sonnet)LOW (haiku) first, MEDIUM if fails
LOW (haiku)LOW (haiku) - no change

What Ecomode Does NOT Do

  • Persistence: Use ralph for "don't stop until done"
  • Parallel Execution: Use ultrawork for parallel agents
  • Delegation Enforcement: Always active via core orchestration

Combining Ecomode with Other Modes

Ecomode is a modifier that combines with execution modes:

CombinationEffect
eco ralphRalph loop with cheaper agents
eco ultraworkParallel execution with cheaper agents
eco autopilotFull autonomous with cost optimization

Ecomode Routing Rules

ALWAYS prefer lower tiers. Only escalate when task genuinely requires it.

DecisionRule
DEFAULTStart with LOW tier (Haiku) for most tasks
UPGRADEEscalate to MEDIUM (Sonnet) when LOW tier fails or task requires multi-file reasoning
AVOIDHIGH tier (Opus) - only for planning/critique if essential

Agent Selection in Ecomode

FIRST ACTION: Before delegating any work, read the agent reference file:

Read file: docs/shared/agent-tiers.md

This provides the complete agent tier matrix, MCP tool assignments, and selection guidance.

Ecomode preference order:

// PREFERRED - Use for most tasks
Task(subagent_type="oh-my-claudecode:executor-low", model="haiku", prompt="...")
Task(subagent_type="oh-my-claudecode:explore", model="haiku", prompt="...")
Task(subagent_type="oh-my-claudecode:architect-low", model="haiku", prompt="...")

// FALLBACK - Only if LOW fails
Task(subagent_type="oh-my-claudecode:executor", model="sonnet", prompt="...")
Task(subagent_type="oh-my-claudecode:architect-medium", model="sonnet", prompt="...")

// AVOID - Only for planning/critique if essential
Task(subagent_type="oh-my-claudecode:planner", model="opus", prompt="...")

Delegation Enforcement

Ecomode maintains all delegation rules from core protocol with cost-optimized routing:

ActionDelegate ToModel
Code changesexecutor-low / executorhaiku / sonnet
Analysisarchitect-lowhaiku
Searchexplorehaiku
Documentationwriterhaiku

Background Execution

Long-running commands (install, build, test) run in background. Maximum 20 concurrent.

Token Savings Tips

  1. Batch similar tasks to one agent instead of spawning many
  2. Use explore (haiku) for file discovery, not architect
  3. Prefer executor-low for simple changes - only upgrade if it fails
  4. Use writer (haiku) for all documentation tasks
  5. Avoid opus agents unless the task genuinely requires deep reasoning

Disabling Ecomode

Ecomode can be completely disabled via config. When disabled, all ecomode keywords are ignored.

Set in ~/.claude/.omc-config.json:

{
  "ecomode": {
    "enabled": false
  }
}

State Management

Ecomode state is tracked in .omc/state/ecomode-state.json.

When work is complete, run /oh-my-claudecode:cancel for clean state cleanup.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Claude Code

28.64%
按下载量换算91

OpenCode

21.89%
按下载量换算69

Gemini CLI

18.09%
按下载量换算57

Antigravity

12.41%
按下载量换算39

Cursor

8.44%
按下载量换算27

Codex

3.86%
按下载量换算12

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。

来源信息

继续浏览同类 Skills