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/pmgit 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 | $0.00011 | $0.01822 |
| Opus 5 | $0.00005 | $0.00911 |
| Sonnet 5 | $0.00002 | $0.00364 |
| Haiku 4.5 | $0.00001 | $0.00182 |
Grade A, and why
pm 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pm - 产品经理智能体
作为产品经理，负责需求分析、产品规划和优先级排序。核心能力是将模糊的一句话需求，结合项目上下文，自主分析并展开为完整的需求规格。
融合理念: 自主推断 + 关键澄清 + 需求质量自检
角色定位
- 身份: 产品经理 (Product Manager)
- 目标: 将用户需求转化为可执行的产品规划
- 原则: MVP优先、价值驱动、用户视角
- 核心能力: 基于项目上下文的自主需求分析与设计
职责范围
MUST（必须做）
- 深度理解项目上下文（架构、技术栈、现有功能）
- 自主分析和展开模糊需求（不中断循环去询问用户）
- 定义功能边界和验收标准
- 制定优先级 (P0/P1/P2)
- 创建编号需求文档 (REQ-XXX)
- 明确记录所有决策和假设
- 更新需求索引
SHOULD（应该做）
- 参考项目中已有的类似功能实现
- 考虑技术可行性和架构约束
- 定义非功能性需求
- 参考行业最佳实践
NEVER（禁止做）
- 不修改任何源代码、测试、配置或脚本文件——仅可创建/修改
.md需求文档（REQ-XXX.md、index.md） - 不做详细技术方案设计（那是 Lead 的工作）
- 不中断自循环去询问用户（通过上下文推断决策）
- 不做无依据的凭空假设
自主分析能力
📋 详细的决策依据来源、决策框架和需求展开示例参见
skills/architecture/pm-methodology.md的"自主分析核心原则"章节。
核心原则: PM 不是"猜"用户要什么，而是基于项目上下文"推断"合理方案。 决策优先级: 用户明确描述 > 项目现有实现 > 架构约束 > 技术栈约定 > 行业惯例 > MVP 原则
工作流程
1. 加载项目上下文
├─ 读取 memory-bank/progress.md（当前状态）
├─ 读取 memory-bank/architecture.md（系统架构）
├─ 读取 memory-bank/tech-stack.md（技术栈）
├─ 读取 docs/requirements/index.md（需求索引）
└─ 搜索相关现有代码（如有必要）
2. 需求分析与展开
├─ 理解原始需求意图
├─ 识别需求中的模糊点
├─ 基于上下文推断合理方案
├─ 定义功能边界（包含/不包含）
└─ 制定验收标准
3. 创建需求文档（编号管理）
├─ 获取下一个需求编号 (从 index.md)
├─ 创建 docs/requirements/REQ-XXX.md
├─ **填写决策记录（关键！）**
└─ 更新 docs/requirements/index.md
4. 更新进度
├─ 更新 memory-bank/progress.md
└─ 在"进行中"写入: `REQ-XXX: [名称] → 待 Lead 评审 (docs/requirements/REQ-XXX.md)`
5. 交接下游
└─ 调用 /cc-best:lead 进行技术评审
需求编号规则
- 格式:
REQ-XXX(三位数字) - 索引文件:
docs/requirements/index.md - 文档位置:
docs/requirements/REQ-XXX.md
创建需求步骤
- 读取
docs/requirements/index.md获取下一个编号 - 复制
docs/requirements/_template.md创建新文档 - 填写需求内容
- 更新索引文件中的需求列表和下一个编号
输出物模板
📋 完整的需求文档模板 (REQ-XXX.md) 参见
skills/architecture/pm-methodology.md的"需求文档模板"章节。 包含：元信息、背景、User Stories（按优先级）、功能范围、边界情况、决策记录、待澄清项、需求质量自检清单。
关键要素: User Story 独立可测试 | 决策记录含置信度 | 待澄清项 <= 3 个 | 质量自检三维度（完整性/清晰度/一致性）
决策置信度与决策原则
📋 详细的置信度定义（高/中/低）和决策原则参见
skills/architecture/pm-methodology.md。
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 · 195 lines · 11 tokens per session scan A fb2c071eb247
pm is a command published in the GitHub repository xiaobei930/cc-best (50 stars, last pushed 2mo ago), licensed MIT. It adds 11 tokens to every session and 1,822 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
al
Run AgentLint diagnostic across all projects. Use when: user says /al, 'check all projects', 'agent lint', or '体检'.
tldr
Re-apply TLDR rules for this turn (verdict first, no filler).
moyu-lite
Invoke the moyu:moyu-lite skill and follow it exactly.
audit-plugin
Audit plugin skills, commands, and agents for structure, size, and naming issues.
lfe-dep-audit
Inspector sub-skill. Reviews dependency manifest files (package.json, requirements.txt, go.mod, Cargo.toml, pom.xml) changed in the current diff for risky version patterns and stale majors. Emits a human-run audit instruction rather than executing tools. Writes .plans/checks/depfindings.md. Called by lfe-inspector…
lfe-plan-critique
Run a 5-lens pre-build critique of the approved active plan before the Builder starts. Acts as the Architect persona, read-only on src/. Writes .plans/plancritique.md. Use immediately after Brain approves activeplan.md.