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/checkpointgit 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 | $0.00009 | $0.01827 |
| Opus 5 | $0.00005 | $0.00914 |
| Sonnet 5 | $0.00002 | $0.00365 |
| Haiku 4.5 | $0.00001 | $0.00183 |
Grade A, and why
checkpoint 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 — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/checkpoint - 检查点管理
任务完成时执行检查点，确保状态持久化到文档。核心原则：文档是上下文的持久化存储。
核心理念
/clear 后 Claude 只能从文档了解项目状态，检查点是跨会话记忆的关键
检查点流程
验证 → 提交 → 更新文档 → 保存会话状态 → 建议 /clear
1. 验证
# 代码验证（根据项目类型选择）
# Python
python -m py_compile <file.py>
pytest <test_file.py> -v
# TypeScript/Node
npm run build
npm test
# 通用
git diff --check # 检查空白错误
2. 提交
# 检查变更
git status
git diff
# 提交（Conventional Commits）
git add <files>
git commit -m "type(scope): description"
提交类型：
feat: 新功能fix: 修复 bugdocs: 文档更新refactor: 重构test: 测试相关chore: 构建/工具
3. 更新文档（最重要！）
必须更新 memory-bank/progress.md：
# 项目进度
## 当前状态
- **阶段**: [阶段名称]
- **最后更新**: [YYYY-MM-DD HH:MM]
- **last_checkpoint**: [YYYY-MM-DD HH:MM]
## 已完成
- [x] 完成的任务1
- [x] 完成的任务2
## 进行中
- [ ] 当前任务（如有）
## 待办
- [ ] 下一个任务
- [ ] 后续任务
## 下一步
[明确说明下一个要做什么]
## 决策记录
| 日期 | 角色 | 决策 | 依据 | 置信度 |
| ---- | ---- | ---- | ---- | ------ |
## 检查点历史
| 时间 | 完成内容 | Git Commit |
| ---- | -------- | ---------- |
文档更新原则：
- 写给 /clear 后的下一个 Claude 实例看
- 包含足够的上下文让它能继续工作
- 明确说明下一步是什么
4. 保存会话状态（可选）
如果启用了 Memory Persistence hooks，会话状态会自动保存到 ~/.claude/sessions/。
手动保存会话笔记：
# 会话笔记 - YYYY-MM-DD
## 本次会话完成
- [完成的内容]
## 遇到的问题
- [问题及解决方案]
## 下次会话注意
- [需要注意的事项]
## 需要加载的上下文
- memory-bank/progress.md
- [其他相关文件]
5. 建议 /clear
任务完成后，告知用户：
检查点完成。文档已更新。
建议执行 /clear 清除上下文，然后 /cc-best:iterate 继续下一个任务。
下一个任务: [具体任务名称]
检查清单
代码检查点
- 无语法错误
- 可以正常导入/构建
- 相关测试通过
前端检查点（如涉及）
- 页面正常渲染
- Console 无 Error 级别日志
- 关键交互功能正常
Git 检查点
- 变更已提交
- commit message 符合规范
- 无敏感信息
文档检查点（最重要！）
- progress.md 已更新
- 记录了完成的内容
- 明确了下一步任务
- 重要决策已记录
使用方式
/cc-best:checkpoint # 执行完整检查点流程
/cc-best:checkpoint verify # 只验证，不提交
/cc-best:checkpoint docs # 只更新文档
/cc-best:checkpoint restore # 从上一个检查点恢复状态
/cc-best:checkpoint --archive # 归档旧记录（当 progress.md 过大时）
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 · 311 lines · 9 tokens per session scan A 0f32cb21f80b
checkpoint 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 1,827 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
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.