dsh-engineering

dsh-engineering is a skill for Codex from qufei1993/skills-hub. It costs 86 tokens per session (1,404 once invoked), scanned A, original, MIT.

An engineering guide for implementing features, fixing bugs, and maintaining a project's AI engineering rules. It uses the project's existing code, callers, checks, documentation, and conventions rather than applying a generic template.

In plain words
What is it for?
Use it for feature work, bug fixes, implementation design, and diagnosing or adopting project engineering instructions, with verification tied to real entry points and required checks.
Why use it?
It reduces mistakes from undocumented assumptions about defaults, input validation, dependencies, extension points, or test coverage. It also helps update project guidance without overwriting stricter local rules.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions AGENTS.md.

Good fit Use it for feature work, bug fixes, implementation design, and diagnosing or adopting project engineering instructions, with verification tied to real entry points and required checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/qufei1993/skills-hub/dsh-engineering
About the project

Skills Hub is a cross-platform desktop application for installing, organizing, updating, and syncing Agent Skills across AI coding tools. Developers use it to maintain one central skill library and distribute selected skills to tools such as Claude Code, Codex, Cursor, OpenCode, and Antigravity. Its catalogue instructions describe how to work with the managed skills.

qufei1993/skills-hub · 1,848 stars · on GitHub · aiskillshub.link

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add qufei1993/skills-hub --skill dsh-engineering
Clone the repo
git clone --depth 1 https://github.com/qufei1993/skills-hub

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for dsh-engineering

README.md
[![agentmods](https://agentmods.dev/badge/skills/qufei1993/skills-hub/dsh-engineering/github.svg)](https://agentmods.dev/skills/qufei1993/skills-hub/dsh-engineering)
Your own site
<a href="https://agentmods.dev/skills/qufei1993/skills-hub/dsh-engineering"><img src="https://agentmods.dev/badge/skills/qufei1993/skills-hub/dsh-engineering/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dsh-engineering

Your own site · 80×15
<a href="https://agentmods.dev/skills/qufei1993/skills-hub/dsh-engineering"><img src="https://agentmods.dev/badge/skills/qufei1993/skills-hub/dsh-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,404 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00086 $0.01404
Opus 5.5 $0.00034 $0.00562
Sonnet 5.5 $0.00017 $0.00281
Haiku 4.5 $0.00009 $0.00140

Measured yesterday against content hash 3899f646960a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dsh-engineering scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/adoption.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/dsh-engineering/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

应用和维护 DSH 工程规范

先读项目上下文和验证证据。按用户任务选择下面的流程。普通开发使用“用于日常开发”;接入或迁移项目规范需要对应的任务要求。

用于日常开发

  1. 阅读受影响的代码、实际调用方和项目必需检查。先明确要实现的行为,再选择抽象或调整约定。
  2. 涉及实现或设计选择时,读编码规范;涉及行为变化时,读测试选择。按当前任务检查默认值、输入校验、依赖方向、扩展点和测试覆盖,不顺带清理无关代码。
  3. 用户要求实现时完成实现;要求设计或审查时给出具体方案或结论。验证相应真实入口和必需检查,区分已执行与建议执行的检查。已安装且与任务有关时,使用专门的审查、错误处理、UI 或性能 Skill;本 Skill 自带所需的基础规则。
  4. 必要时更新现有行为文档。不要仅因开发一个功能或修复一个问题,就创建接入记录、新的 Agent 指令或工程手册。完成时说明行为变化、实际证据和重要限制。

修改规范前先诊断

  1. 明确请求属于诊断、接入、更新还是撤销。诊断保持只读。
  2. 检查适用指令、目录、清单、真实检查命令、CI 和现有文档的维护位置,识别已有优势和具体缺口。
  3. 新项目只记录已知事实和用户选定的技术栈,不虚构测试命令。已有项目复用原有文档,保留更严格的政策。优先解决当前问题,不套用通用目录模板。
  4. 简短列出“缺口 → 涉及的现有文档 → 具体补充”。用户已经要求实现或接入时,在该范围内继续执行。

接入项目

  1. 选择尽量少的文档,通常是现有 Agent 指令入口和开发指南。阅读文档写作;只有确需新建负责维护这些内容的文档时,才使用项目指南模板。不要留下占位内容。
  2. 找到当前安装的 Skill 目录。编辑前运行自带的接入工具: python3 <skill-dir>/scripts/adoption.py snapshot --project <root> --paths AGENTS.md <other-docs> --output <new-temporary-snapshot.json>。 只指定明确的 UTF-8 文档,不采集凭据、无关文档或整个目录。临时快照保持私有,放在版本管理范围之外。
  3. 只修改任务涉及的文档,补足项目导航、职责归属、真实开发和检查命令、证据标准与文档维护规则。保留本地约定,不放宽检查或安装新依赖。阅读编码规范和测试选择,根据项目实际风险选取规则。补充通往已安装 Skill 或现有规范的简短日常入口,不整份复制参考库。
  4. 对照清单和 CI 核实命令,对照真实路径检查链接。项目要求时执行必需检查。新增可执行规则时,必须用真实错误样例证明检查会拒绝违规情况。
  5. 从 UPSTREAM.json 读取版本和固定上游提交 SHA,再运行: python3 <skill-dir>/scripts/adoption.py record --project <root> --snapshot <snapshot.json> --version <version> --upstream <sha>。 检查生成的 .dsh-engineering/adoption.json 和差异。记录包含修改前后的完整文档,提交或发布前检查有无私有信息。
  6. 重复接入应复用已有规则,不增加重复段落;内容未变时,基线文件字节保持不变。说明修改的文件、实际检查和后续使用方式。

更新或撤销项目规范

更新已安装 Skill 包不会自动迁移项目。用户明确要求更新项目规范时,先运行 compare --project <root>。重新阅读项目现状,不假定旧方案仍然合适。

  • 根据新 Skill 和项目事实生成建议。可选的建议 JSON 格式为 {"files":{"AGENTS.md":"完整的 UTF-8 建议内容"}};null 表示文件不存在。运行 compare --project <root> --proposal <proposal.json>,比较基线、当前内容和建议。
  • 检查真实差异,只合并能够确定属于本次规范的内容,保留无关内容和本地修改。重叠修改需要具体段落的解决方案,不能整文件覆盖。意图不清楚时保留该段,针对该段询问,同时继续不受影响的工作。
  • 撤销时,以记录中的 original 为首次接入前的参照。当前内容与 baseline 不同时,只移除能够明确识别的接入规则。只有不会丢失本地或无关内容时,才删除当初创建的文档。
  • 基线缺失或无效意味着归属不明:报告差异,提出人工接入或合并方案。不得凭记忆或哈希重建原文。
  • 迁移前做快照,完成后验证并记录结果。工具保留首次原文和最新基线。完全撤销并验证后,只有没有残留接入规则或未解决修改时,才移除接入记录。

Read the full file on GitHub · 48 lines

Files

What ships with it

11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 48 lines · 86 tokens per session scan A 3899f646960a

Subscribe to this mod's changes

dsh-engineering is a skill published in the GitHub repository qufei1993/skills-hub (1,848 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 1,404 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-31.

Related

Other skills, from other repositories

agentbro-pr-merge

Use when reviewing, fixing CI for, approving workflows for, or merging AgentBro pull requests into dev/main, especially external contributor PRs where contributor attribution matters.

shirenchuang/agentbro · 38 tokens

oculpm-journal

A work-journal format for recording coding-agent tasks, including bugs, features, errors, refactors, and chores. It defines where files go and what information each record must contain.

bunhine0452/Ocul-PM · 55 tokens

redteam

A red-team checker for plans and work journals that tests their verifiable claims against source files, commands, logs, database rows, or Git changes. Red-teaming means deliberately looking for counterexamples rather than assuming a claim is correct.

bunhine0452/Ocul-PM · 58 tokens

cc-port-live-e2e

Run and audit CC Port's opt-in live Windows package E2E and broader native remaining-scope validation. Use when validating that a packaged installer or release candidate can enable AI automation, upload/download a harmless Skill through packaged MCP plus desktop approval, verify Registry v1 and Git blob bytes, or when…

Ling-ye/cc-port · 136 tokens

cc-port

Inspect, compare, plan, transfer, and verify AI agent resources across configured Codex, Claude Code, Cursor, Windows, and WSL profiles through CC Port. Use when an AI must discover or synchronize skills, MCP configurations, rules, prompts, plugins, instructions, or memories; compare local and repository state; upload…

Ling-ye/cc-port · 139 tokens

inception

A project-starting workflow for researching a new idea, agreeing on its requirements, and turning it into a detailed three-level plan.

bunhine0452/Ocul-PM · 53 tokens