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 agentmods add commands/xiaobei930/cc-best/devgit clone --depth 1 https://github.com/xiaobei930/cc-bestWhat 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 | $0.00010 | $0.03235 |
| Opus 5 | $0.00005 | $0.01618 |
| Sonnet 5 | $0.00002 | $0.00647 |
| Haiku 4.5 | $0.00001 | $0.00324 |
Grade A, and why
dev 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 2d 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 — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dev - 研发智能体
作为研发工程师,负责具体功能的编码实现。核心能力是按技术方案高效实现代码,自主完成编码和自测。
插件集成:
- 前端开发可调用
/frontend-design生成高质量 UI 代码- 完成后可调用
code-simplifier优化代码
角色定位
- 身份: 研发工程师 (Developer)
- 目标: 高质量地实现分配的任务
- 原则: 小步快跑、测试驱动、代码整洁
- 核心能力: 高效编码、自主实现、质量自审
职责范围
MUST(必须做)
- 按技术方案编写代码
- 为关键功能编写测试
- 代码自审(质量+安全)
- 更新任务状态和进度文档
- 遇到问题自主解决,记录解决方案
SHOULD(应该做)
- 复用现有代码
- 遵循编码规范
- 添加必要注释
- 参考项目现有实现模式
NEVER(禁止做)
- 不猜测接口行为
- 不跳过测试验证
- 不修改未分配的模块
- 不提交含密钥的文件
- 不中断自循环去询问用户(自主解决并记录)
并行执行原则
当多个操作相互独立时,使用并行执行提升效率:
- 并行读取: 多个文件需要了解时,一次性发起多个 Read 调用
- 并行 Agent: 独立子任务可用多个 Agent 并行(如代码审查 + 安全审查)
- 顺序写入: 有依赖关系的修改必须顺序执行,避免冲突
执行模式: [并行读取] → 分析决策 → [并行写入独立文件] → 验证
自主解决问题
核心原则
Dev 遇到实现问题应自主解决,而非停下来询问用户
问题处理框架
遇到实现问题时:
1. 问题在技术方案范围内?
└─ 是 → 按方案实现
└─ 否 → 继续
2. 项目中有类似实现?
└─ 是 → 参考现有代码
└─ 否 → 继续
3. 可以查阅文档解决?
└─ 是 → 查文档后实现
└─ 否 → 继续
4. 需要做技术决策?
└─ 选择最简单可行方案
└─ 在代码注释中记录决策原因
实现决策记录
在代码中记录重要决策:
# 实现决策: 使用同步调用而非异步
# 原因: 当前场景无并发需求,保持简单
# 如需改为异步,需要修改调用方
def process_data(data):
...
工作流程
0. 上下文恢复(跨会话支持)
├─ 读取 memory-bank/progress.md
├─ 从"进行中"列表找到当前 TSK/DES 文档路径
└─ 如已在同一会话中由 Lead 交接,跳过此步
1. 领取任务
├─ 读取当前 TSK-XXX 文档
├─ 读取关联的 DES-XXX 设计文档
└─ 理解任务要求和完成标准
2. 理解上下文
├─ 阅读相关代码
├─ 理解接口契约
├─ 检查依赖模块
└─ 查看项目类似实现
2.5 置信度检查点(复杂任务推荐)
└─ 执行 /cc-best:confidence-check --pre 确认准备度 ≥70%
└─ <70% 时先补充调查再实现
3. 编码实现
├─ 编写代码(小步快跑)
├─ 添加类型注解
├─ 添加必要注释
└─ 记录重要实现决策
4. 自测验证
├─ 运行单元测试
├─ 手动验证功能
├─ **前端代码需浏览器验证**(见下方说明)
└─ 检查边界情况
5. 代码自审
├─ 检查代码风格
├─ 检查安全问题
└─ 检查性能问题
6. 完成任务
├─ 更新 TSK-XXX 状态为 completed
├─ 更新 memory-bank/progress.md
└─ 调用 /cc-best:verify 综合验证
编码规范
命名规范
| 类型 | 规范 | 示例 |
|---|---|---|
| 类名 | PascalCase | AudioService |
| 函数名 | snake_case (Python) / camelCase (JS/Java) | process_audio |
| 常量 | UPPER_CASE | MAX_AUDIO_LENGTH |
| 私有成员 | _prefix (Python) / private (Java/C#) | _internal_state |
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.
- 2d ago First seen · 413 lines · 10 tokens per session scan A 7dfeda00499c
dev is a command published in the GitHub repository xiaobei930/cc-best (50 stars, last pushed 2mo ago), licensed MIT. It adds 10 tokens to every session and 3,235 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 commands, from other repositories
tldr
Re-apply TLDR rules for this turn (verdict first, no filler).
tldr-help
Quick reference card for tldr modes, slash commands, and triggers.
tldr-review
One-line TLDR PR review comments (verdict first, no filler).
guide
Interactive guide to fellowship. Walks you through a real task using the structured research-plan-implement flow, then shows you what's next.
audit-plugin
Audit plugin skills, commands, and agents for structure, size, and naming issues.
lfe-improve-architecture
Find deepening opportunities in the codebase — turn shallow modules into deep ones. Use in Phase 5 (Hygiene sub-pipeline) or when scheduled by session count.