Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add an8079/take-skills --skill ecomodegit clone --depth 1 https://github.com/an8079/take-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/an8079/take-skills/ecomode)<a href="https://agentmods.dev/skills/an8079/take-skills/ecomode"><img src="https://agentmods.dev/badge/skills/an8079/take-skills/ecomode.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01190 |
| Opus 5 | $0.00000 | $0.00595 |
| Sonnet 5 | $0.00000 | $0.00238 |
| Haiku 4.5 | $0.00000 | $0.00119 |
Grade A, and why
ecomode scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
ecomode
极简高效执行模式 — 最小化 token 消耗，最大化输出质量的激进执行策略
触发词
ecomode, 高效模式, 省 token, 极简执行, 轻量模式
概述
ecomode 是一种激进的高效执行模式，目标是在最短的对话轮次内完成任务，同时最小化 token 消耗。适用于简单明确的任务、批量操作、或者在 token 预算紧张时使用。
核心原则
1. 零废话原则
- 直接执行，不解释过程
- 输出精简，核心结论优先
- 减少过渡性语言（"好的"、"让我来"）
- 用代码/列表代替自然语言
2. 单次完成原则
- 任务一次性完成，不拆分成多轮
- 写完即运行验证
- 失败后直接修复，不解释为什么失败
3. 最小化工具原则
- 用最少的工具调用完成任务
- 避免过度分析（时间敏感任务直接做）
- 优先使用已有能力而非重复造轮子
4. 质量底线
- 代码可运行（最基本的质量标准）
- 不以牺牲正确性换取速度
- 安全问题不过度妥协
执行策略
任务分类处理
| 任务类型 | 策略 | 原因 |
|---|---|---|
| 简单文件编辑 | 直接写，不确认 | 确定性高 |
| 简单命令执行 | 直接执行，不汇报 | 确定性高 |
| 中等复杂度 | 先做，再报告 | 边做边调整 |
| 高复杂度 | 快速计划后执行 | 需要方向但不过度分析 |
| 未知领域 | 边做边查 | 探索式执行 |
激进工作流
Before (标准模式):
分析需求 → 制定计划 → 确认方案 → 开始执行 → 中途汇报 → 完成 → 总结
(6+ 轮对话)
After (ecomode):
需求 → 直接执行 → 完成报告
(1-2 轮对话)
工具使用优先级
- 优先用内置工具 — 减少自定义代码
- 直接写文件 — 不用解释
- exec 直接执行 — 不用解释命令
- 批量操作 — 一次搞定多个文件
- 子 agent 异步执行 — 交给后台处理
ecomode 指令集
/ecomode:start
激活 ecomode，告知 Agent 进入高效模式，后续回复将极度精简。
/ecomode:batch [文件列表]
批量处理多个文件，不逐一确认。
/ecomode:emergency [任务]
紧急任务模式，跳过所有检查直接执行。
/ecomode:report
在 ecomode 中生成简洁完成报告。
ecomode 决策树
任务进入
↓
是否简单明确？（有明确输入输出）
↓ 是
直接执行 → 验证 → 完成
↓ 否
是否复杂但有方向？
↓ 是
快速计划（<5行） → 执行 → 完成
↓ 否
是否探索性任务？
↓ 是
边做边查 → 快速迭代 → 完成
报告格式（ecomode 专用）
标准报告:
## 完成报告
**任务:** [一句话描述]
**状态:** ✅ 完成 / ⚠️ 部分完成 / ❌ 失败
**输出:** [文件/变更列表]
**变更:** [3行以内的核心变更]
**问题:** [如有，简洁描述]
拒绝报告:
❌ 无法完成: [具体原因]
💡 建议: [替代方案]
适用场景
✅ 适合 ecomode:
- 批量文件修改
- 简单脚本生成
- 文档格式调整
- 代码片段替换
- 重复性任务
- 紧急 bug 修复
❌ 不适合 ecomode:
- 架构设计决策（需要充分讨论）
- 安全关键变更（需要审核）
- 涉及多方依赖的系统设计
- 用户需要详细解释的任务
注意事项
- 保持质量底线 — 速度不能牺牲代码正确性
- 安全不过度妥协 — 注入风险仍需规避
- 记录关键决策 — 完成后补充必要注释
- 紧急情况可回退 — /ecomode:end 结束高效模式
激活方式
当用户说 "快一点"、"省点 token"、"简单点处理" 时自动激活
当任务明显属于简单批量操作时自动激活
用户显式使用 /ecomode 命令时激活
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 150 lines · 0 tokens per session scan A e57a391399bd
ecomode is a skill published in the GitHub repository an8079/take-skills (4 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,190 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…