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 devcxl/mattpocock-skills-zh --skill retrogit clone --depth 1 https://github.com/devcxl/mattpocock-skills-zhWrote 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/devcxl/mattpocock-skills-zh/retro)<a href="https://agentmods.dev/skills/devcxl/mattpocock-skills-zh/retro"><img src="https://agentmods.dev/badge/skills/devcxl/mattpocock-skills-zh/retro/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/devcxl/mattpocock-skills-zh/retro"><img src="https://agentmods.dev/badge/skills/devcxl/mattpocock-skills-zh/retro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00011 | $0.00789 |
| Opus 5 | $0.00005 | $0.00394 |
| Sonnet 5 | $0.00002 | $0.00158 |
| Haiku 4.5 | $0.00001 | $0.00079 |
Grade A, and why
retro 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 10d 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.
What it actually says
用户请求了回顾。你正在为编码 agent 的环境提出改进建议，以提升后续运行的体验。
步骤
-
调用 Skill 工具并传入
writing-for-agents，获取写作风格指南。 -
读取用户指定的会话的主源资料。这可能意味着在本机上的会话日志中检索。如果用户没有指定会话，则默认为当前这个。
-
在以下类别中寻找可改进的候选：
- 导航：agent 找到正确文件的难易程度如何？文件之间是否存在隐藏依赖？一个导航指针会让事情更简单吗？当会话花很长时间才找到某条信息时使用。
- 自动化检查：是否存在能捕捉 agent 所犯错误的自动化检查？linting、类型检查、测试、文件系统 linter？当 agent 犯了一个本可被自动化检查捕获的错误时使用。
- 编码规范：是否应给评审 agent 一条新规则去执行？是否应删除或澄清已有规则？当评审 agent 没抓住错误时使用。
- 全局 AGENTS.md：是否有些引导指令应当改为编码规范（或自动化检查）？当 AGENTS.md 文件特别庞大时：无论是在仓库还是用户的全局作用域：使用。
- 工具经济性：agent 是否做了昂贵且可以精简的工具调用？是否存在特别消耗 token 的自定义工具（CLI、MCP）？当 agent 做了昂贵的工具调用时使用。
- 空操作（No-ops）：在引导文件里寻找那些并不修改 agent 行为的指令。当引导文件庞大且难以驾驭时使用。
- 信息访问：寻找可以提升 agent 信息访问能力的机会。Tee 出开发服务器的日志、对第三方服务的只读访问等。当 agent 缺少某条关键信息时使用。
- 按严重程度顺序向用户呈现这些候选。
参考
实现 vs 评审
记住所有工作都会经过两个阶段：实现和评审。实现 agent 承受最大的上下文压力。他们负责探索、写代码和调试失败。
评审 agent 的上下文压力最小：它接收的是 diff，不需要探索。它通常既不需要写代码也不需要调试。
这意味着评审 agent 应该负责落实编码规范，而不是实现 agent。
文件
你可以访问仓库里的几个文件：
CLAUDE.md/AGENTS.md：这些文件会被推送到任何在该仓库中工作的 agent 的上下文窗口里。它们应当被极其克制地使用，通常仅用于指向其他文件的导航指针。CODING_STANDARDS.md：这个文件在评审时被读取，而不是在实现时。当标准文件超过 1,000 行时，新增指向 docs 文件夹的导航指针。- Docs：把文档当作引用文件使用，由其他文件指向。在写新文档之前先看看是否已有现成的。
- Skills：把 skills 当作文档使用（因为它们的 description 会进入 agent 的上下文窗口），或者当作用户调用命令使用。遵循
writing-for-agents技能中的建议。
What ships with it
1 file 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.
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.
- 10d ago First seen · 45 lines · 11 tokens per session scan A 8fb52a7fae2f
retro is a skill published in the GitHub repository devcxl/mattpocock-skills-zh (331 stars, last pushed 5d ago), licensed MIT. It adds 11 tokens to every session and 789 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
chinese-code-review
A Chinese-language code-review communication guide with templates and severity levels for review comments.
chinese-commit-conventions
A Chinese-language guide to Conventional Commits, a format for writing consistent Git commit messages, plus related changelog, commit-checking, and commit-helper configuration.
systematic-debugging
A step-by-step method for finding the underlying cause of technical problems before changing code. It covers reading errors, reproducing failures, checking recent changes, and tracing data across system components.
dispatching-parallel-agents
A workflow for assigning separate coding agents to independent tasks that do not share state or depend on one another. Each agent receives a focused scope, constraints, and an expected result.
executing-plans
A procedure for carrying out a written software implementation plan in a separate session, including reviewing the plan, completing its tasks, and checking the results at defined review points.