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.
npx skills add uvwt/agentdock-skills --skill personal-dev-guardgit clone --depth 1 https://github.com/uvwt/agentdock-skillsWrote 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.
[](https://agentmods.dev/skills/uvwt/agentdock-skills/personal-dev-guard)<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/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.
<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="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00030 | $0.06260 |
| Opus 5.5 | $0.00012 | $0.02504 |
| Sonnet 5.5 | $0.00006 | $0.01252 |
| Haiku 4.5 | $0.00003 | $0.00626 |
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 29d 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.
How it starts
The opening of the file, as written. The whole thing — 485 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:
- 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。
- 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。
- 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。
- 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。
- 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。
- 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。
- 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。
- 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。
- 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。
- 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。
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。- 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。
- 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。
- 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:
- 主流程可读,读者能顺着理解业务链路。
- 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。
- 代码没有明显补丁味、临时味和硬塞特例。
- 抽象克制,不为了看起来高级而制造层级。
- 错误路径、边界条件和状态变化清楚可见。
- 测试或验证覆盖本次改动真正的风险。
- 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。
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.
- 29d ago Changed · -1 lines 286c6a57cb9f
- 1mo ago First seen · 486 lines · 30 tokens per session scan A b5e7f6bcd45b
personal-dev-guard is a skill published in the GitHub repository uvwt/agentdock-skills (6 stars, last pushed 8d ago), licensed Apache-2.0. It adds 30 tokens to every session and 6,260 once invoked, about $0.0001 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 2026-08-31.
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…
comet-verify
Comet Phase 4: Verify and Close. Invoke with /comet-verify. Verify implementation matches design, handle development branch.
find-simplifications
Use when asked to find or plan Cherry Studio cleanup, simplification, refactoring, dead-code removal, duplicated state removal, unnecessary APIs, speculative generality, or library replacements, especially when the result should become evidence-backed proposed Agent Notes.
no-comments
Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
pr-description-writer
Redacta una descripción de pull request clara y estructurada a partir de un diff de git, resumen de rama o lista de commits. Úsalo cuando te pidan escribir una descripción de PR, redactar una solicitud de cambios o documentar cambios de código. Produce una descripción con resumen, motivación, cambios realizados, pasos…
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…