Skip to content
Plugin

dsh-doublecheck

PerryLink580Updated 3d ago

Open on GitHub

Engineering-discipline loop: requirement grilling before edits, red/green test-evidence gates, adversarial delivery review, and a report with per-dimension verification.

Practical score

80 / 100

Setup

Ready to use

License

Apache-2.0

Language

TypeScript

Install

Quick start

Copy the command, or hand the whole task to your harness agent.

git clone https://github.com/PerryLink/dsh-doublecheck.git
DSH versionDSH ≥ 0.1.6-0 <0.2.0
Install with your agent

Please install the DeepSeek Harness plugin "dsh-doublecheck" for me. - GitHub repository: PerryLink/dsh-doublecheck (https://github.com/PerryLink/dsh-doublecheck) - Type: a Cordis plugin (installed into a DSH profile) - The plugin declares a DSH version requir…

From the README

A cleaned excerpt from the project's own documentation.

dsh-doublecheck 把交付从「自称完成」变成有证据的裁决:需求先拷问,测试先红后绿,交接之前由四阶段门禁给出可交付 / 返工。 DeepSeek Harness 的交付质量门禁:两个插件行盯住同一份可重放的会话日志,把 grill → design → red → green → review → verify 的纪律闭环变成命令、工具,和一条会被写进报告的裁决。…

Open on GitHub

Project details

by
PerryLink
License
Apache-2.0
stars
58
Forks
0
Updated
Nov 9, 2026
Created
Aug 14, 2026
Language
TypeScript
Indexed from
awesome-0xsline · topic
Visit homepage

Related entries

Similar tools from the same corner of the ecosystem.

View all
Plugin

dsh-research-report

PerryLink

Verifiable research-report engine for DeepSeek Harness: content-addressed evidence ledger (claim-to-snapshot binding, tamper-evident) and versioned sealed reports with per-claim verification verdicts and a manifest SHA-256 seal.

ai-agentai-agentsaudit
213Ready to use
86/100
Plugin

dsh-auto-review

PerryLink

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

ai-agentai-agentsai-safety
248Needs setup
83/100
Plugin

dsh-github

PerryLink

Official-grade GitHub CI integration: composite action.yml, polling PR review bot with idempotent inline comments and a status-check gate, plus PR/issues tools with every write gated by human approval.

ai-agentai-agentsci
29Needs setup
83/100