catchup

catchup is a command for Claude Code from xiaobei930/cc-best. It costs 9 tokens per session (1,297 once invoked), scanned A, original, MIT.

A command for quickly rebuilding project context after the conversation has been cleared. It reads key project documents, recent Git changes, and available session history, then summarizes the current state.

In plain words
What is it for?
Use it at the start of a new session or after clearing context to find the current phase, recent work, open tasks, next step, and potential issues.
Why use it?
It reduces the time needed to understand the project and resume unfinished work after an interruption or context reset.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Part of the cc-best plugin — 19 skills, 44 commands, 8 agents, 20 hooks shipped together

Good fit Use it at the start of a new session or after clearing…

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/xiaobei930/cc-best/catchup
Install

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.

Clone the repo
git clone --depth 1 https://github.com/xiaobei930/cc-best

Made for: Claude Code.

Or install cc-best, the plugin that ships this one along with the rest of its 19 skills, 44 commands, 8 agents, 20 hooks.

Wrote 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.

agentmods badge for catchup

README.md
[![agentmods](https://agentmods.dev/badge/commands/xiaobei930/cc-best/catchup.svg)](https://agentmods.dev/commands/xiaobei930/cc-best/catchup)
Your own site
<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>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,297 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 7d ago against content hash 9fe8b059e658, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

commands/catchup.md · 222 lines

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

/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)

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"
          }
        ]
      }
    ]
  }
}

Read the full file on GitHub · 222 lines

Changes

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.

  1. 7d ago First seen · 222 lines · 9 tokens per session scan A 9fe8b059e658

Subscribe to this mod's changes

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.