中文

← Back to list

dsh-rule-engine

DeepSeek Harness Other Low risk

Rules execution engine for dsh: parses AGENTS.md, hard-blocks rule-violating tool calls, text-based B/D rule auditing, /guard command, version-guard for versioned files, and free-zone support (engine skips free-zone sections).

dsh 规则执行引擎：解析 AGENTS.md、硬拦违反规则的工具调用、文本纠察与审计、/guard 命令、版本化文件守卫、自由区域支持（引擎跳过自由区内容）。

How to install

DeepSeek Harness dsh plugin add dsh-rule-engine

About

dsh-rule-engine DSH 规则执行引擎 v3 的插件实现。它把 ~/.dsh/AGENTS.md 当作唯一真相源，自动解析规则四要素与执行等级，再通过「工具守卫 + 文本检测 + 时序检查 + 审计台账」执行用户规则，而不是内置一套与用户无关的安全清单。 项目背景 这个项目来自一个非常具体的个人需求： 作者是**零编程基础**用户，但极其重视规则的制定、执行、遵守与复盘。 作者发现：规则如果只写在文本里、靠模型“自觉”执行，会反复失效（例如时间词写错、内联命令违规、交付前漏验证等）。 因此核心思路是：**规则的执行不能只靠自觉，要尽量靠插件在机制层强制**。 本插件所有规则均从 AGENTS.md 动态解析，规则增删改后无需重写插件。 当前实现基于已有的 AGENTS.md 规则体系拓展，社区暂无类似插件供参考（大概率为该等约束可能限制开发自由性，不适用于专业编程人员），**可能存在大量不完备、误判或边界问题**。欢迎任何使用者提出调整建议、提交 issue 或 PR。项目仍处于“可运行但需要持续打磨”的阶段。 功能分层 阶段 1 容器：解析 AGENTS.md 全部规则 → 理解产物（rule-understanding.json 可生成） 阶段 2 匹配机 + 工具守卫 + 文本检测 阶段 3 时序检查 + 授权询问集成 阶段 4 D 级自证调度 + /guard…

GitHub ↗

Recommendation signals

51 Tool quality · Based on stars, downloads, maintenance, security and docs
– User interest · Adjusted by in-site views, install copies and download clicks
51 Overall
0views
0unique visitors
0install copies
0download clicks
0outbound clicks

Meta

License
MIT
Language
JavaScript
GitHub stars
1
mo. downloads
0
Last push
2026-08-17
Created
2026-08-15

Links

GitHub ↗ npm ↗ Homepage ↗ Report issue ↗

Basic safety check

Findings
None
Sources
curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
Topics
dsh-plugin

Related plugins

DeepSeek Harness New
Score60

dsh-auto-review

PerryLink/dsh-auto-review

Second-model auto-review on the approval answerer chain: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default.

☆ 33 ↓ – Other ↗
DeepSeek Harness
Score57

dsh-passwords

slywalker2006/dsh-passwords

Turns DeepSeek Harness into a server-grade multi-tenant platform: remote access + auto HTTPS, subuser permissions & token/daily quotas, sandbox enforcement, encrypted auth & audit log.

☆ 11 ↓ 528 Other ↗
DeepSeek Harness
Score57

dsh-permissions

940842546/dsh-permissions

Claude Code-style permission rules engine: hard/deny/ask/allow tiers with a hard tier above full access, workspace-scoped rules, wildcard path protection, and a visual staged editor; rules persist in settings.yaml.

☆ 0 ↓ 209 Other ↗
DeepSeek Harness
Score56

dsh-permission-rules

PerryLink/dsh-permission-rules

Claude Code-style declarative permission rules: ordered allow/deny/ask YAML rules matching tool names, arguments, workspace paths, and agent identity on the tools/pre-execute waterfall, with full session-log audit, dry-run mode, and hot reload.

☆ 8 ↓ 530 Other ↗