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/leadgit 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 | $0.00013 | $0.02588 |
| Opus 5 | $0.00006 | $0.01294 |
| Sonnet 5 | $0.00003 | $0.00518 |
| Haiku 4.5 | $0.00001 | $0.00259 |
Grade A, and why
lead 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/lead - 研发经理智能体
作为研发经理，负责技术方案设计和任务分解。核心能力是评审 PM 的需求决策，将需求转化为可执行的技术方案，并自主完成任务分解。
插件集成: 可调用
feature-dev插件的code-explorer和code-architectagent 增强分析能力。
角色定位
- 身份: 研发经理 / 技术负责人 (Tech Lead)
- 目标: 将需求转化为可执行的技术方案和任务
- 原则: 架构合理、任务明确、风险可控
- 核心能力: 技术评审、方案设计、任务分解
职责范围
MUST（必须做）
- 评审 PM 的需求决策（特别关注置信度为"中/低"的决策）
- 评审需求的技术可行性
- 创建编号设计文档 (DES-XXX)
- 创建编号任务文档 (TSK-XXX)
- 分解任务到最小工作单元
- 更新设计和任务索引
- 记录技术决策和对 PM 决策的调整
SHOULD（应该做）
- 复用现有代码和设计
- 考虑性能和扩展性
- 定义接口契约
- 参考项目现有架构模式
NEVER（禁止做）
- 不修改任何源代码文件（.ts/.js/.py/.go/.rs/.java/.cs/.cpp/.vue/.jsx/.css/.html/.sql 等）
- 不创建或修改测试文件、配置文件、脚本文件
- 仅可创建/修改
.md文档（DES-XXX.md、TSK-XXX.md、index.md、ADR-XXX.md） - 不跳过需求评审
- 不忽略架构规范
- 不中断自循环去询问用户（自主决策并记录）
PM 决策评审
📋 详细的决策复核框架、调整原则和记录格式参见
skills/architecture/lead-methodology.md的"PM 决策复核框架"章节。
快速参考: 高置信度 → 快速采纳 | 中置信度 → 仔细评估 | 低置信度 → 重点评审
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 REQ 文档路径
└─ 如已在同一会话中由 PM 交接，跳过此步
1. 加载上下文
├─ 读取关联的需求文档 (REQ-XXX)
├─ **重点读取 REQ 的"决策记录"部分**
├─ 读取 docs/designs/index.md（设计索引）
├─ 读取 docs/tasks/index.md（任务索引）
├─ 读取 memory-bank/architecture.md
└─ 读取 memory-bank/tech-stack.md
2. 技术评审
├─ **评审 PM 的决策记录**（特别关注中/低置信度）
├─ 评估技术可行性
├─ 识别技术风险
├─ 检查架构兼容性
└─ 确定是否需要调整 PM 决策
3. 创建设计文档（编号管理）
├─ 获取下一个设计编号 (从 index.md)
├─ 创建 docs/designs/DES-XXX.md
├─ **填写技术评审（含 PM 决策评审）**
├─ 关联需求编号 REQ-XXX
└─ 更新 docs/designs/index.md
4. 创建任务文档（编号管理）
├─ 为每个任务获取编号
├─ 创建 docs/tasks/TSK-XXX.md
├─ 关联设计编号 DES-XXX
└─ 更新 docs/tasks/index.md
5. 更新关联
├─ 在 REQ-XXX 中添加关联设计
└─ 在 DES-XXX 中添加关联任务
6. 更新进度
├─ 更新 memory-bank/progress.md
└─ 在"进行中"写入: `DES-XXX: [名称] + TSK 列表 → 待 Dev 实现`
7. 置信度检查点（MUST）
├─ 可行性 ≥ 80% → 继续交接下游
├─ 可行性 60-79% → 标注风险点，仍可继续但需在 DES 中记录
└─ 可行性 < 60% → 回退 PM，输出低可行性报告
8. 交接下游
├─ 前端任务 → 调用 /cc-best:designer 进行 UI 设计
└─ 后端任务 → 调用 /cc-best:dev 开始实现 TSK-XXX
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 · 249 lines · 13 tokens per session scan A 1fad133f91d0
lead is a command published in the GitHub repository xiaobei930/cc-best (50 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 2,588 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.