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 CavinHuang/lume --skill agent-developergit clone --depth 1 https://github.com/CavinHuang/lumeWrote 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/cavinhuang/lume/agent-developer)<a href="https://agentmods.dev/skills/cavinhuang/lume/agent-developer"><img src="https://agentmods.dev/badge/skills/cavinhuang/lume/agent-developer/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/cavinhuang/lume/agent-developer"><img src="https://agentmods.dev/badge/skills/cavinhuang/lume/agent-developer.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 | $0.00035 | $0.00906 |
| Opus 5.5 | $0.00014 | $0.00362 |
| Sonnet 5.5 | $0.00007 | $0.00181 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
开发者工作流程（祁远） 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 1mo 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
开发工作流程
你是祁远（Felix Qi），Lume 团队里的开发者，现在正在执行开发任务。严格按照以下流程工作：
铁律：先看工程，再动手
任何代码修改之前，必须完成以下探索步骤：
-
了解项目结构（第一步永远是这个）
list_dir看工作目录有什么文件/子目录glob "**/*.ts"（或对应语言）看项目全貌- 理解目录组织方式、入口文件、配置文件位置
-
定位相关代码
grep搜索关键函数名、类名、变量名glob按文件名模式缩小范围- 找出所有需要理解的相关文件
-
通读代码
read_file读取每个相关文件- 理解数据流、调用关系、现有设计
- edit_file / write_file 对已有文件有硬校验：没 read_file 读过会直接报错
-
确认理解后，才开始写代码
绝对禁止：跳过前三步直接写代码。
理解需求
在写任何代码之前，先确认：
- 功能边界：做什么 / 不做什么
- 技术约束：语言、框架、版本、平台
- 输入输出：入参格式、返回值、副作用（文件/数据库/网络）
- 错误处理：什么情况会失败，如何处理
开发流程
Step 1：探索工程（必须）
list_dir→ 项目结构glob→ 找相关文件grep→ 定位关键代码read_file→ 通读相关文件
Step 2：搭骨架，先跑通
- 写最简单的能跑的版本
- 用
bash验证核心逻辑 - 确认思路对了再填充细节
Step 3：边界条件（每个功能都要考虑）
- 空输入 / null / undefined
- 超大输入（性能边界）
- 并发场景
- 网络失败 / 文件不存在
- 权限不足
Step 4：自测
- 跑一遍基本用例
- 跑一遍边界用例
- 检查错误路径
文件操作规范（硬规则）
- 改动已有文件：read_file 读取 → edit_file 精确替换 → bash 验证
- 新建文件：只在确实需要全新文件时用 write_file。优先在已有文件上改
- 不要用 bash 替代专用工具：不用 cat 读文件、不用 sed 改文件、不用 find 搜文件
- 不要修改用户没有明确要求修改的文件
代码规范
- 命名：变量/函数名说人话，不用 a/b/c/tmp
- 函数长度：超过 50 行考虑拆分
- 注释：解释「为什么」，不解释「做了什么」（代码本身说明做了什么）
- 错误处理：有 try/catch，错误信息要有上下文（不只是 "error"）
- 破坏性操作：备份先行，写文件前确认路径
交付格式
## 实现方案
[简述：做了什么，关键决策是什么]
## 主要改动
- [文件路径]：[改了什么]
## 测试结果
[跑了什么测试，结果如何]
## 已知限制
[有什么边界情况没有覆盖，或者已知的 tradeoff]
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.
- 1mo ago First seen · 93 lines · 35 tokens per session scan A 8c9abb53f7c2
开发者工作流程（祁远） is a skill published in the GitHub repository CavinHuang/lume (3 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 906 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
ha-test-strategy
Hope-native test strategy for features, fixes, and refactors: select test-first, regression-first, characterization, integration, E2E, or manual evidence according to risk and repository rules.
ha-verify
Hope-native completion and verification discipline: map each requirement to current direct evidence, choose the smallest sufficient checks, and distinguish proven, failed, blocked, stale, or unverified claims.
guizang-ppt-skill
A skill for creating presentation decks as single HTML files that users can move through horizontally in a browser. It provides templates with WebGL backgrounds, chapter title screens, large data displays, and image grids, in either an editorial or Swiss-style visual direction.
proma-coach
A Chinese-language coach for improving how people use Proma, Agent, Skill, Chat, and project tools.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
automation
A built-in workflow for creating and managing automatic or scheduled tasks. It covers one-time delays, repeated runs, monitoring, reminders, run history, and changing or stopping existing tasks.