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/commands/xiaobei930/cc-best/catchup)<a href="https://agentmods.dev/commands/xiaobei930/cc-best/catchup"><img src="https://agentmods.dev/badge/commands/xiaobei930/cc-best/catchup.svg" alt="Measured on agentmods" 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 | $0.00009 | $0.01297 |
| Opus 5 | $0.00005 | $0.00648 |
| Sonnet 5 | $0.00002 | $0.00259 |
| Haiku 4.5 | $0.00001 | $0.00130 |
Grade A, and why
catchup 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 7d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/catchup - 快速恢复上下文
在 /clear 后快速恢复项目上下文。核心原则:快速加载,精准定位,无缝继续。
核心理念
每次 /clear 后,Claude 需要重新了解项目状态。此命令自动读取关键文档和最近变更,快速恢复工作上下文。
执行流程
1. 读取核心文档
├─ CLAUDE.md(项目宪法)
├─ memory-bank/progress.md(当前进度)
├─ memory-bank/architecture.md(系统架构)
└─ memory-bank/tech-stack.md(技术选型)
2. 查看最近 Git 变更
├─ git status(当前状态)
├─ git log --oneline -10(最近提交)
└─ git diff HEAD~3 --stat(最近文件变更)
3. 检查会话历史(如有)
└─ ~/.claude/sessions/ 目录下的最近会话文件
4. 识别当前状态
├─ 正在进行的任务
├─ 下一步工作
└─ 待解决的问题
5. 输出摘要
├─ 项目当前阶段
├─ 最近完成的工作
└─ 下一个任务建议
输出格式
## 上下文恢复完成
### 项目信息
- **项目**: [项目名称]
- **技术栈**: [主要技术]
### 当前状态
- **阶段**: [当前阶段]
- **上次检查点**: [时间]
- **进度**: [完成百分比或描述]
### 最近活动(Git)
[最近 5 条 commit]
### 最近完成
- [x] [最近完成的任务 1]
- [x] [最近完成的任务 2]
### 当前任务
- [ ] [正在进行的任务]
### 下一步
[建议的下一个动作]
### 需要关注
- [待解决的问题或注意事项]
***
已准备就绪,可以继续工作。
使用场景
| 场景 | 命令组合 |
|---|---|
| 新会话开始 | /cc-best:catchup → 了解状态 → 继续工作 |
| 切换任务后 | /clear → /cc-best:catchup → 开始新任务 |
| 长时间中断后 | /cc-best:catchup → 回顾进度 → 继续 |
| 上下文压缩后 | /cc-best:catchup → 恢复关键信息 |
深度恢复模式
/cc-best:catchup deep
当需要更深入的上下文恢复时:
1. 执行标准 catchup 流程
2. 额外读取
├─ 最近修改的源代码文件
├─ 相关的测试文件
└─ 配置文件变更
3. 分析代码状态
├─ 未完成的 TODO 注释
├─ 临时代码标记
└─ 调试代码残留
4. 生成详细报告
快速恢复模式
/cc-best:catchup quick
只读取最关键的信息:
1. 仅读取 memory-bank/progress.md
2. 获取"下一步"内容
3. 输出简短摘要
适用于:
- 已经熟悉项目
- 只是短暂中断
- 需要快速继续
与 Memory Persistence 配合
如果启用了 Memory Persistence hooks,/cc-best:catchup 会自动检查:
# 检查最近的会话文件
~/.claude/sessions/YYYY-MM-DD-session.tmp
# 如果存在,读取并显示
- 上次会话完成的内容
- 上次会话的注意事项
- 建议加载的上下文文件
Hooks 配置(可选)
在 settings.local.json 中配置自动 catchup 提示:
{
"hooks": {
"SessionStart": [
{
"matcher": "*",
"hooks": [
{
"type": "command",
"command": "echo '[Session] 建议执行 /cc-best:catchup 恢复上下文' && ls -la ~/.claude/sessions/*.tmp 2>/dev/null | tail -3"
}
]
}
]
}
}
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.
- 7d ago First seen · 222 lines · 9 tokens per session scan A 9fe8b059e658
catchup is a command published in the GitHub repository xiaobei930/cc-best (50 stars, last pushed 2mo ago), licensed MIT. It adds 9 tokens to every session and 1,297 once invoked, about $0.0000 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
retex
Retex - Capture lesson learned dans memory après fix, rollback, erreur.
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
audit-whitepapers
Audit version freshness, FR/EN parity, and metadata quality of all whitepapers and recap cards.
boldguy-linkedin-answer
Draft a LinkedIn comment on a post, referencing the guide's relevant section, in Flow style with AI markers removed.
methodology-advisor
Analyzes your codebase and asks 3 targeted questions to recommend the right AI-assisted development methodology stack.
release
Release guide version (CHANGELOG + VERSION + README + landing sync + commit + push).