by PerryLink
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).
# Add to your Claude Code skills
git clone https://github.com/PerryLink/dsh-auto-reviewGuides for using ai agents skills like dsh-auto-review.
Last scanned: 10/5/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-10-05T11:12:56.375Z",
"npmAuditRan": false,
"pipAuditRan": true,
"promptInjectionRan": true
}See how dsh-auto-review compares with popular alternatives.
dsh-auto-review is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by PerryLink. Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided). It has 253 GitHub stars.
Yes. dsh-auto-review passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/PerryLink/dsh-auto-review" and add it to your Claude Code skills directory (see the Installation section above).
dsh-auto-review is primarily written in TypeScript. It is open-source under PerryLink on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh dsh-auto-review against similar tools.
No comments yet. Be the first to share your thoughts!
From $49 · 30 days · terms & refunds
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM lists this project for discovery and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Automated security scan — not a certification.
让第二个模型在审批链上替你裁决——人类零点击,危险操作零漏网。
面向 DeepSeek Harness 的第二模型 AI 审批插件:当动作越过沙箱边界,一个只读审查子代理读取证据并返回带理由的裁决,默认失败关闭。
安装 · 配置 · FAQ · 简体中文 · English · Español · Português · हिन्दी
dsh plugin --profile <name> add dsh-auto-review
社区插件,与 DeepSeek 官方无关。唯一仓库:https://github.com/PerryLink/dsh-auto-review(Gitee 为镜像)。
当某个动作越过沙箱边界,dsh-auto-review 把审批决定交给第二个模型:一个只读审查子代理读取真实工作区(经 read/glob/grep 白名单)、已流式传出的工具调用参数(敏感值已脱敏)、请求理由与你的风险规则,返回结构化裁决 { decision, reason, riskLevel }——人类无需批准任何事,也没有任何不安全的东西蒙混过关。拒绝裁决会把理由反馈给调用模型,让代理学会原因而不是盲目重试;每一次决策都能从会话日志重建。
结构:认领漏斗 —— 四道认领闸门把越界请求逐层收窄,只有 ai 策略进入只读审查室(agent 子代理或本地 Phocinae),最终收束为 allow / deny / fallback 三个出口;右侧是 next() 委派与确定性收口两条旁路,底部是仅日志审计链。
安装(四选一):
# git 渠道(最新 main;等价于 git+https://github.com/PerryLink/dsh-auto-review.git)
dsh plugin --profile web add github:PerryLink/dsh-auto-review
# npm 渠道(已发布版本)
dsh plugin --profile web add dsh-auto-review
# 1024 商店渠道:先 npm i -g dsh1024,再
dsh1024 plugin --profile web add dsh-auto-review
# tarball 渠道:本仓库 pnpm pack 后
dsh plugin --profile web add ./dsh-auto-review-<version>.tgz
git 渠道的隔离 prepare 构建需要 dsh CLI 为 dsh-auto-review 打印出的 allowBuilds 键;当 dsh plugin add 因 koffi / node-pty(评估宿主拉入)停在 ERR_PNPM_IGNORED_BUILDS 时,运行 pnpm approve-builds 批准这些构建脚本。
最小配置(开箱即用;随附 patch 默认 AI 审查 bash、write、pwsh、powershell):
- insert:
- id: auto-review
name: dsh-auto-review
config:
toolsPolicy:
overrides: { bash: ai, write: ai, pwsh: ai, powershell: ai }
其他所有工具(包括 edit——原地修改)都委派给人类审批链;接受无人在环的原地编辑时显式加 edit: ai。
验证已生效:
dsh --profile web --dump-config | grep -A4 'id: auto-review'
> /auto-review status
All-time: 1 allows, 0 denies, 1 fallbacks, 1 never rejects (avg 10 ms per verdict).
Recent verdicts: write: fallback(timeout), bash: allow
卸载:dsh plugin --profile web remove dsh-auto-review(或从 profile patch 删掉该行)。
所有 PerryLink 插件均可在 DSH Desktop 内置市场中浏览:市场 → 来源 → 添加来源 → 粘贴 https://perrylink-dsh-catalog.perrylink.workers.dev/catalog-source.json → 选中。安装仍需通过市场的 npm 身份校验与你的确认。
dsh-auto-review 在 approval/request answerer 链上加入第二模型:
ai 策略)的 answerer,其余请求通过 next() 委派;人类审批流程永远不会被短路。read/glob/grep,返回结构化裁决 { decision, reason, riskLevel }。审查器请求靠身份识别并委派;maxDepth + 白名单让审查器无法再委派。fallbackPolicy(默认 rejected)处理;拒绝裁决会把理由反馈给调用模型。ai/human/never)加正则风险规则,全部可在 cordis.yml 中修改。never 策略拒绝也会注入可审计标记([auto-review] / [auto-review-fallback] / [auto-review-never])。autoReview/verdict + autoReview/rejection 会话事件(信封 ignorable: true),外加一个可选的 invariant 配套插件来强制「标记 ⟺ 事件」。/auto-review approve 覆盖,以及会向模型自我解释的 never 策略硬禁用。contextBudget)加 Codex 风格 Markdown 裁决策略(reviewerPolicyText)。每一次决策都能从会话日志重建:approval/asked → autoReview/verdict(或 autoReview/rejection)→ approval/decided。
基于模式的自动审批器在派发前就做决定,没有证据。dsh-auto-review 把决定权交给一个审查子代理:它读取真实工作区(通过只读工具面)、已流式传出的工具调用参数(敏感值已脱敏)、请求理由与你的风险规则——然后返回结构化裁决。拒绝裁决会把理由反馈给调用模型,让代理学会原因,而不是盲目重试。
以下为插件真实入口;安装后调用一个即可。
详细示例 — 命令:
/auto-review status
输出:
All-time: 1 allows, 0 denies, 1 fallbacks, 1 never rejects (avg 10 ms per verdict).
Recent verdicts: write: fallback(timeout), bash: allow
Observed from test/command.spec.ts:123-160 (assertions at :158-159)
失败分支 — 输入:
/auto-review approve 2
输出:
No recent denial #2 in this session (0 recorded).
Observed from plugins/dsh-auto-review/src/messages.ts:53; plugins/dsh-auto-review/src/runtime.ts:1039; plugins/dsh-auto-review/test/command.spec.ts:109-113
简短示例:auto-review · dsh-eval
approval/request waterfall (answerer chain)
│
┌───────────────────────┴──────────────────────┐
│ dsh-auto-review answerer │
│ · session enabled? · policy = ai? │ no ── next() ──▶ human answerer (UI)
│ · risk rules → toolsPolicy → default │
└───────────────────────┬──────────────────────┘
│ yes
▼
┌───────────────────────────────────┐
│ reviewer subagent (fork, one-shot)│
│ · toolFilter: read/glob/grep │
│ · outputSchema: {decision, │
│ reason, riskLevel} │
│ · timeout + req.signal abort │
└───────────────┬───────────────────┘
│ verdict / failure (fail-closed fallback)
▼
allow → allowed-once deny → rejected + reason injected into the
denied tool result (callId-linked)
│ never → rejected + [auto-review-never] feedback
│ (hard disable, no reviewer runs)
▼
audit: approval/asked → autoReview/verdict | autoReview/rejection
→ approval/decided (session events, log-only, invariant-checked)
组合顺序。 answerer 在其注册位置运行于瀑布中:如果人类 UI answerer 被组合在 auto-review 行之前,则人类先应答,审查器只能看到被下游委派的部分。用 dsh --profile <name> --dump-config 验证,并把你希望 ai 策略工具先路由到审查器的 auto-review 行放在人类 answerer 行之前。
| 界面 | 类型 | 说明 |
|---|---|---|
auto-review |
answerer | approval/request 瀑布 answerer —— 认领 ai 策略请求,其余经 next() 委派 |
/auto-review |
命令 | on|off|status|approve [n] —— 持久会话覆盖、预算与累计统计 |
| 拒绝理由注入 | 监听器 | tools/post-execute —— 将裁决 / fallback / never 理由反馈到被拒绝的工具结果 |
autoReview |
会话投影 | 由仅日志的 autoReview/* 事件折叠而成 |
| Web 审查面板 | 客户端 | 会话头部操作:开关、预算、统计、最近裁决、一次性批准 |
dsh-eval |
CLI | YAML 驱动的代理评估引擎(bin/dsh-eval.mjs) |
| invariant 配套插件 | invariant | dsh-auto-review/invariant(可选;需要 invariants 服务) |
/auto-review on|off|status|approve [n]
on/off 追加持久的 autoReview/state 覆盖(折叠在重启/恢复后依然存活——重放即状态),并注入一条模型可见的开关通知(记录为 user/message 事件)。status 报告有效状态、两个每轮预算(AI 裁决与审查器失败)、活跃的熔断器(如有),以及会话的累计统计(允许/拒绝/回退/never 拒绝、平均耗时、最近裁决)。approve [n] 为第 n 条最近的拒绝(1 = 最近)记录一次性 autoReview/override:overrideTtlMs 内下一次对同一工具的审查会携带该授权作为审查上下文——审查器依然做决定,且无论结果如何,该覆盖都会被这次审查消耗掉。
在 Web GUI(web profile)中,该包贡献一个会话头部操作(AI Review),打开面板显示会话的 auto-review 状态:带开/关按钮的开关(执行 /auto-review on|off)、两个每轮预算、累计统计(含硬禁用拒绝与缓存命中)、熔断触发、最近裁决,以及针对最近拒绝的一次性 approve 按钮(执行 /auto-review approve [n])。
接线方式:
autoReview 会话投影(由仅日志的 autoReview/* 事件折叠而成),并通过会话投影通道提供。dsh.client 声明自动发现),注册在 conversation.session.header.actions 席位。面板只读取整个投影值——它从不接收原始会话事件流。
除了审批审查器,dsh-auto-review 还附带 dsh-eval:一个 YAML 驱动的代理评估平台,运行真实的 headless DSH 会话(每个用例一个隔离代理 + 临时工作区,以官方 Minimal persona 作为基线系统提示),从会话事件日志中收集工具调用轨迹,并评估结构化断言以及可选的第二模型审查——与审批 answerer 使用同一条审查接缝。
# eval/cases/demo.yaml (abridged)
suite:
name: my-suite
cases:
- id: math-output
input: