DSH Market
Z

Zerotoken Skill

by phoenixlucky · phoenixlucky/zerotoken-skill

InstallableSkillcopy into placefresh

让 Agent 高效又守纪律 — 不止省 token:ZeroToken 压缩无效上下文/推理/输出;尉缭子十原则约束权限边界、单一指令、先谋后动、验证先于结束;附 Unicode 编码规范、搜索规范、六种任务模式。More than token savings: ZeroToken efficiency + AI coding discipline for Reasonix / Codex / OpenCode / Hermes

Install Zerotoken Skill

Not a bundle: drop the SKILL.md directory into one of the skill roots DSH scans. No `dsh plugin add`, no build step.

This is a skill, not a bundle. Skills are not installed with dsh plugin add — a skill is a directory containing SKILL.md that DSH discovers by scanning its skill roots. Clone it into one of those roots and it is available on the next session.

Clone into your user skill root ($DSH_HOME/skills)

mkdir -p ~/.dsh/skills
git clone https://github.com/phoenixlucky/zerotoken-skill.git ~/.dsh/skills/zerotoken-skill
RankRootPath
100project-dsh<project>/.dsh/skills
200project-agents<project>/.agents/skills
300customcustomSkillDirs in your config
400user-dsh$DSH_HOME/skills (default ~/.dsh/skills)
500user-agents$DSH_AGENTS_HOME/skills (default ~/.agents/skills)

Lower rank wins when two roots hold a skill with the same name. Put it in a project root instead of the user root when it should only apply to one repository.

Prerequisites

API key
Not required.
Network access
Not required at runtime.
Language
Python

Install check

Every field the verdict was derived from, so you can re-derive it yourself

Field checkedResultWeightWhat the spec says about it
lifecycleScriptspassinfono install-time scripts
entityTypepassinfoskill is not installed via `dsh plugin add`
Verdict reason
skill uses its own install path, so bundle checks do not apply
package.json read
package.json
Rules applied from
docs/user/develop/basic/publish.md
Checked at
2026-08-15

From the README

Excerpt as published by the author, plain text, unedited

**让 Agent 用最少的 token 做最准的事** > ⚔️ **将军受命,君必先谋于庙,行令于廷,君身以斧钺授将。曰:左、右、中军皆有分职;若逾分而上请者死;军无二令,二令者诛;留令者诛;失令者诛。** > > 💬 **用不完,根本用不完,妈妈再也不用担心我缺 token 了。** > **ZeroToken Skill** 是一套为 AI Agent 设计的**提示词纪律规范**——在不降低回答准确性的前提下,压缩无效上下文、无效解释、无效工具调用和无效输出,从而大幅降低 token 消耗和响应延迟。 > > 它解决的核心问题是:Agent 在任务中经常过度读取、过度思考、过度输出,导致一次对话消耗成千上万不必要的 token。ZeroToken Skill 通过一套可执行的**模式决策表 + 行为约束 + 工具链策略**,让 Agent 在每一个任务环节都有明确的"省 token 行为准则"。 > > 🎯 **目标:** 用最精准的提示,做最少的往返,产最精炼的结果。 > > ✅ **适用于:** Reasonix / Codex CLI / OpenCode / Hermes / Cline 等主流 Agent 工具。一次学习,全平台受益。 请依次阅读并安装以下 Skill。 - **ZeroToken Skill** — phoenixlucky,Token 高效约束:最少 token 和精准提示完成任务,减少无效输出 - 地址:https://github.com/phoenixlucky/zerotoken-skill 请根据上面每个 Skill 的「安装指令」完成安装。

Topics

GitHub topics on this repository

More in Agent Codex Reasonix Session

Ranked by similarity inside the cluster, not alphabetically