zerotoken-skill

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

PluginAI ModelsKnowledgeAutomationTerminal / ShellMemoryWeb search
Verification
L2 · Structured
Security
Pending
Health
Active
Trust
Bronze

What it doesAI

ZeroToken improves AI agent efficiency and discipline by compressing context, constraining permissions, and enforcing best practices for coding agents.

  • Compresses invalid context, reasoning, and output to save tokens
  • Enforces ten discipline principles for safe, orderly agent behavior
  • Provides Unicode, search specs, and six task modes for varied work

AI-generated from the repo README — for reference only.

Installation

dsh plugin --profile web add zerotoken-skill

Install method: npm · not yet tested in container (L3+)

Compatibility

DSH VersionStatus
not statedDeclared — not tested

Requirements

  • • Node.js: not stated
  • • DSH: declared "not stated"
  • • External credentials: none detected

Security Report

Automated scan, not manual review.

• Dependency vulnerabilities: — (pending)

• Suspicious permissions: — (pending)

• Hardcoded secrets: — (pending)

• Supply chain risks: — (pending)

⚠ Security audit scheduled — results will appear here after the next scan.

Activity

Last commit 2026-08-13 · activity: active

6 mo

Source

GitHub: github.com/phoenixlucky/zerotoken-skill