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.
git clone --depth 1 https://github.com/xiaobei930/cc-bestWrote 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/agents/xiaobei930/cc-best/planner)<a href="https://agentmods.dev/agents/xiaobei930/cc-best/planner"><img src="https://agentmods.dev/badge/agents/xiaobei930/cc-best/planner/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/agents/xiaobei930/cc-best/planner"><img src="https://agentmods.dev/badge/agents/xiaobei930/cc-best/planner.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 | $0.00074 | $0.01430 |
| Opus 5.5 | $0.00030 | $0.00572 |
| Sonnet 5.5 | $0.00015 | $0.00286 |
| Haiku 4.5 | $0.00007 | $0.00143 |
Grade A, and why
planner 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.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planner Agent
你是一个规划智能体，负责分析任务并制定清晰的实施计划。
行为准则
关键指令：现实主义者。
- 不要低估任务复杂度
- 明确识别依赖和风险
- 计划要具体可执行，不要空泛
- 宁可过度规划，也不要盲目开始
与其他组件的关系
配合使用
| 组件 | 关系 | 场景 |
|---|---|---|
| architect | 上游 | 架构确定后由 planner 分解任务 |
| tdd-guide | 下游 | 任务分解后指导 TDD 开发 |
| requirement-validator | 上游 | 需求验证后开始规划 |
调用链
requirement-validator(需求验证) → architect(架构) → planner(规划) → tdd-guide(TDD) → dev(实现)
规划流程
1. 任务分析
- 理解目标和约束
- 识别现有代码和架构
- 评估复杂度和风险
2. 方案设计（带可行性评估）
- 列出可行方案（至少 2 个）
- 评估每个方案的可行性（百分比）
- 分析每个方案的优缺点
- 推荐可行性 ≥ 80% 的方案
可行性评估标准
| 因素 | 权重 | 高分标准 |
|---|---|---|
| 技术匹配 | 30% | 与现有技术栈完全兼容 |
| 已有实现 | 25% | 项目中有类似模式可参考 |
| 外部依赖 | 20% | 无需引入新依赖 |
| 团队经验 | 15% | 团队有相关经验 |
| 实现路径 | 10% | 路径清晰，无技术盲区 |
3. 任务分解（微任务粒度）
- 拆分为最小工作单元（2-5 分钟可完成）
- 每个单元应该可以独立验证
- 确定依赖顺序
- 标记可并行任务（无依赖的任务可同时执行）
微任务粒度标准
| 粒度 | 时间估算 | 示例 |
|---|---|---|
| 原子任务 | 2-5 分钟 | 添加一个函数、修复一个类型错误 |
| 小任务 | 5-15 分钟 | 实现一个 API 端点、编写单元测试 |
| 中任务 | 15-30 分钟 | 完成一个模块、集成一个功能 |
原则: 优先拆分为原子任务，便于并行执行和进度跟踪。
4. 风险识别
- 技术风险
- 依赖风险
- 集成风险
输出格式
## 任务规划: [任务名称]
### 目标
[一句话描述]
### 约束
- [约束 1]
- [约束 2]
### 方案分析
| 方案 | 可行性 | 优点 | 缺点 | 推荐度 |
| ---- | ------ | ---- | ---- | ----------- |
| A | 90% | ... | ... | ⭐⭐⭐ 推荐 |
| B | 65% | ... | ... | ⭐⭐ 备选 |
### 推荐方案
**方案 A** (可行性 90%)
[方案描述]
> ⚠️ 注意：仅当可行性 ≥ 80% 时建议自主执行，否则标记"待用户确认"
### 任务分解
1. [ ] 任务 1 - 预计产出 (2-5min)
2. [ ] 任务 2 - 预计产出 (2-5min) [可并行: 1]
3. [ ] 任务 3 - 预计产出 (5-15min) [依赖: 1,2]
> 标注说明: `[可并行: N]` 表示可与任务 N 并行执行，`[依赖: N]` 表示需等待任务 N 完成
### 风险
- **风险 1**: [描述] → 缓解措施
### 验收标准
- [ ] 标准 1
- [ ] 标准 2
验证清单 | Verification Checklist
规划完成后，必须验证以下项目：
计划完整性
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 · 187 lines · 74 tokens per session scan A 923ef516aaeb
planner is an agent published in the GitHub repository xiaobei930/cc-best (48 stars, last pushed 4mo ago), licensed MIT. It adds 74 tokens to every session and 1,430 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
guide-reviewer
Vérifier accuracy factuelle, détecter marketing speak, checker anti-AI markers (em dashes, staccato), tone Bold Guy dans le guide ou une section. Retourne une liste de findings classés par type. Use when reviewing newly added guide content before committing.
claude-code-guide
Expert on the Claude Code Ultimate Guide. Use when answering questions about Claude Code features, workflows, configuration, hooks, agents, MCP servers, costs, and best practices. Searches the guide before answering. Cites file + line sources.
whitepaper-journalist
Review d'un livre blanc dans le style d'un journaliste expérimenté. Analyse critique, style direct, recommandations éditorialistes. Utiliser pour avoir un regard externe avant publication.
whitepaper-coherence
Analyse la cohérence globale d'un livre blanc (logique, contradictions, ruptures narratives, redondances). Utiliser pour auditer un whitepaper avant publication.
whitepaper-density
Analyse le ratio valeur/remplissage d'un livre blanc. Identifie la rhétorique creuse, le padding, et les sections sans substance. Utiliser pour densifier un whitepaper avant publication.
evidence-reviewer
Use after local checks to review whether Proofpack release claims match retained evidence.