personal-dev-guard

personal-dev-guard is a skill for Claude Code, Codex from uvwt/agentdock-skills. It costs 30 tokens per session (6,269 once invoked), scanned A, original, Apache-2.0.

A set of code-writing and code-review rules focused on readable, restrained, maintainable software. It also describes preferences such as keeping Go code simple and using clear data types.

In plain words
What is it for?
Use it while changing or reviewing code to follow existing project conventions, keep the main flow understandable, explain non-obvious decisions in Chinese comments, and test real risks.
Why use it?
It helps prevent temporary fixes, unnecessary layers, clever abstractions, and tests that distort the production design.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it while changing or reviewing code to follow existing project conventions, keep the main flow understandable, explain non-obvious decisions in Chinese comments, and test real risks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/uvwt/agentdock-skills/personal-dev-guard
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 uvwt/agentdock-skills --skill personal-dev-guard
Clone the repo
git clone --depth 1 https://github.com/uvwt/agentdock-skills

Made for: Claude Code, 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 personal-dev-guard

README.md
[![agentmods](https://agentmods.dev/badge/skills/uvwt/agentdock-skills/personal-dev-guard.svg)](https://agentmods.dev/skills/uvwt/agentdock-skills/personal-dev-guard)
Your own site
<a href="https://agentmods.dev/skills/uvwt/agentdock-skills/personal-dev-guard"><img src="https://agentmods.dev/badge/skills/uvwt/agentdock-skills/personal-dev-guard.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,269 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 $0.00030 $0.06269
Opus 5 $0.00015 $0.03134
Sonnet 5 $0.00006 $0.01254
Haiku 4.5 $0.00003 $0.00627

Measured 6d ago against content hash b5e7f6bcd45b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

personal-dev-guard 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 6d ago.

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/personal-dev-guard/SKILL.md · 486 lines

How it starts

The opening of the file, as written. The whole thing — 486 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Personal Dev Guard / 个人开发守门规范

这是一个中文指令型 Skill。它的本体是这份 Markdown 文档,而不是自动评分脚本。

使用者读取本规范后,应按用户的个人高级开发标准进行代码开发和代码审查。这里的重点不是部署、排障、工具调用礼仪,也不是形式化流程检查,而是判断一份代码是否清晰、可读、克制、可维护,是否像高级开发者写出来的代码。

1. 短版核心规范

开发和审查代码时,优先遵守以下原则:

  1. 长期工程质量优先。不能只追求暂时能跑、暂时能实现、最小改动;方案必须符合项目既有规范,能长期维护、长期演进。
  2. 可读性优先。代码首先要能顺着读懂,主流程要连贯,不要让读者在一堆小函数之间来回跳转。
  3. 反对补丁味。不要为了修一个点硬塞特殊判断、flag、临时分支,让代码长期补丁化。
  4. 反对炫技抽象。抽象必须来自真实需求,不为了设计感、层级感、模式感而抽象。
  5. 项目规范优先。开发前要尊重现有目录结构、接口边界、命名风格、数据模型、错误处理、测试方式和发布约定;不要做一处可用、全局不一致的改动。
  6. 复杂度应该来自业务本身,而不是框架、helper、接口、目录层级或设计模式额外放大出来的复杂度。
  7. 核心流程需要中文注释。注释重点解释为什么、业务原因、设计取舍、坑点和非显然约束。
  8. 测试应该覆盖真实风险,并且测试代码本身也要可读,像业务行为文档,而不是复杂 mock 工程。
  9. Go 项目优先简单直接:少做 Java 式机械分层,不提前定义 interface,不为了 mock 污染业务结构。
  10. 泛型默认克制使用:能用普通函数、明确类型或具体结构表达清楚的,就不要上泛型;只有真实多类型复用能明显减少重复并保持可读时才使用。
  11. any 不算泛型,但也要克制:边界层解析动态 JSON 可以用,业务内部优先转成明确 struct、具体类型或小结构,避免把字段契约藏进运行时。
  12. Review 时优先看:是否符合长期规范性和项目规范,主流程是否连贯,有没有补丁味和炫技抽象,测试/验证是否覆盖风险,改动范围是否形成完整闭环。
  13. 包和目录按稳定职责与共同变更原因组织;既不要为了架构感机械拆包,也不要把多个独立能力长期堆进一个大包或 God Object。
  14. 测试不能反向污染生产设计。不得仅为了测试方便,在生产代码中新增职责不合理的方法、接口、导出符号、setter/getter、hook,或放宽字段和方法可见性;生产 API 和模块边界必须在没有测试需求时也成立。

如果因为现实约束违反核心偏好,必须在 Review 或交付说明中说清楚:为什么违反、替代方案是什么、风险是什么、后续是否需要修正。

2. 规范定位

本规范约束的是代码开发质量,不是 AgentDock 运维流程。

它应该用于:

  • 新增功能、修复 bug、重构、清理代码。
  • Go 项目开发,尤其是服务端、CLI、工具类项目。
  • 其他语言项目中的通用可读性、可维护性和测试判断。
  • 开发后的代码 Review 和 debrief。

它不重点覆盖:

  • Docker 部署、反代、证书、服务排障。
  • iOS/watchOS 安装签名流程。
  • 工具调用前后如何汇报的细节。
  • 自动化评分、静态分析或代替测试工具。

这份规范不是要求所有代码都写成一种形状,而是帮助开发者始终回答一个问题:未来接手这段代码的人,能不能顺着读懂、放心修改、快速定位问题?

当“最小改动”和“长期正确”冲突时,不能默认选择最小改动。应该优先选择符合项目规范、能形成完整闭环、未来维护成本更低的方案;如果只能先临时处理,必须说明临时性、风险和后续正式方案。

3. 高级开发者判断标准

高级开发者不是把代码写得复杂,而是把真实复杂度控制在可读、可定位、可维护的范围里。

优先级如下:

  1. 主流程可读,读者能顺着理解业务链路。
  2. 方案符合项目既有规范和长期演进方向,不为了暂时可用破坏一致性。
  3. 代码没有明显补丁味、临时味和硬塞特例。
  4. 抽象克制,不为了看起来高级而制造层级。
  5. 错误路径、边界条件和状态变化清楚可见。
  6. 测试或验证覆盖本次改动真正的风险。
  7. 改动范围服务当前目标,同时足以把功能、数据、接口、前端、测试和文档等相关闭环补齐。

不高级的代码通常有这些味道:

  • 为了短函数把主流程拆散,读代码需要频繁跳转。
  • 为了一个小需求引入过多 interface、manager、processor、adapter、factory。
  • 为了快速修复硬塞特殊 case,没有说明原因、影响和退出条件。
  • 错误被吞掉、被模糊包装,或者只打印日志后继续。
  • 业务对象含义不清,充斥 map、any、万能 DTO、泛名 helper。
  • 测试比业务代码还难读,mock 和 fixture 成为新的复杂度来源。
  • 为了快或“少改点”,只修表面现象,不处理同一业务链路里的规范、一致性和闭环问题。

Read the full file on GitHub · 486 lines

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. 6d ago First seen · 486 lines · 30 tokens per session scan A b5e7f6bcd45b

Subscribe to this mod's changes

personal-dev-guard is a skill published in the GitHub repository uvwt/agentdock-skills (3 stars, last pushed 5d ago), licensed Apache-2.0. It adds 30 tokens to every session and 6,269 once invoked, about $0.0002 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

agent-watchdog

Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Codex session ID, Claude Code session/transcript, chat/thread link, PR, branch, log, or pasted run summary. Monitor until the other agent is done or blocked, reconstruct what the user asked, independently investigate the same…

BuilderIO/skills · 115 tokens

comet-verify

Comet Phase 4: Verify and Close. Invoke with /comet-verify. Verify implementation matches design, handle development branch.

rpamis/comet · 32 tokens

agent-design-best-practices

Best practices for designing Claude Code agent files (.claude/agents/.md). This skill should be used when writing or reviewing agent markdown files to ensure proper design with focused domains, correct tool access, reusable definitions, and separation of capabilities from lifecycle. Combines Anthropic's official…

majiayu000/claude-skill-registry · 73 tokens

graphify-dotnet

Use graphify-dotnet to generate codebase knowledge graphs, architecture snapshots, and exportable repository maps from .NET or polyglot source trees, with optional AI-enriched semantic relationships. USE FOR: graphify commands; graph JSON, HTML, SVG, Cypher, Markdown, and Obsidian exports; repository map and…

managedcode/dotnet-skills · 125 tokens

map-codebase

Deep architecture report that fans out parallel inspections across different aspects of the codebase (structure, tech stack, APIs, patterns, data flow, dependencies, testing) and synthesizes findings into a comprehensive document at .turbo/codebase-map.md and .turbo/codebase-map.html. Use when the user asks to "map…

tobihagemann/turbo · 106 tokens

reply-to-pr-threads

Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".

tobihagemann/turbo · 71 tokens