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/self-checkgit 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/self-check)<a href="https://agentmods.dev/commands/xiaobei930/cc-best/self-check"><img src="https://agentmods.dev/badge/commands/xiaobei930/cc-best/self-check.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 | $0.00007 | $0.01321 |
| Opus 5 | $0.00003 | $0.00660 |
| Sonnet 5 | $0.00001 | $0.00264 |
| Haiku 4.5 | $0.00001 | $0.00132 |
Grade A, and why
self-check 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 4d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/self-check - 自我检查
定期进行自我检查，确保工作质量和方向正确。
检查时机
定时检查
| 频率 | 检查内容 |
|---|---|
| 每个任务完成后 | 任务验证 |
| 每 5 个任务后 | 方向检查 |
| 每个 Phase 完成后 | 阶段审查 |
| 每天结束前 | 日总结 |
触发检查
| 触发条件 | 检查内容 |
|---|---|
| 遇到阻塞 | 问题分析 |
| 不确定时 | 方向确认 |
| 用户反馈后 | 调整确认 |
检查清单
任务级检查
[ ] 任务目标是否达成？
[ ] 代码是否可运行？
[ ] 是否有未处理的错误？
[ ] 是否需要更新文档？
[ ] 是否需要提交 Git？
阶段级检查
[ ] Phase 目标是否达成？
[ ] 所有验收标准是否满足？
[ ] 文档是否同步更新？
[ ] 是否有遗留问题？
[ ] 下一阶段依赖是否就绪？
方向检查
[ ] 是否偏离了项目目标？
[ ] 是否过度设计？
[ ] 是否遗漏了用户需求？
[ ] 是否有更简单的方案？
[ ] 当前优先级是否正确？
问题发现后的处理
小问题（可立即修复）
- 记录问题
- 立即修复
- 验证修复
- 继续原任务
中等问题（需要规划）
- 记录问题到 progress.md
- 评估影响范围
- 创建修复任务
- 安排到合适时机
大问题（需要决策）
- 停止当前工作
- 详细记录问题
- 分析可选方案
- 请求用户决策
自检报告格式
## Self-Check Report [时间戳]
### 当前状态
- Phase: X / Step: Y
- 进度: XX%
- 状态: 正常/需关注/阻塞
### 完成检查
- [x/] 任务验证
- [x/] 代码质量
- [x/] 文档同步
- [x/] Git 状态
### 发现问题
1. [问题描述] - [严重程度] - [处理方式]
### 下一步
- [下一个任务]
- [预期产出]
红旗检测 | Red Flag Detection
以下信号表明可能存在问题，需要立即关注：
7 个红旗信号
| # | 红旗 | 检测方式 | 行动 |
|---|---|---|---|
| 1 | 引用不存在的 API/函数 | Grep 搜索确认 | 停止，查文档 |
| 2 | 假设未验证的业务规则 | 检查需求文档 | 标记 TBD |
| 3 | 引用的版本号/语法可能过时 | WebSearch 验证 | 更新引用 |
| 4 | 多次失败后仍用相同方法 | 检查会话历史 | 换方案 |
| 5 | 修改了不理解的代码 | 检查是否先 Read | 先阅读再修改 |
| 6 | 跳过了测试直接提交 | 检查 verify 记录 | 补测试 |
| 7 | 长时间无进展（>10次工具调用无产出） | 计数器检测 | 暂停反思 |
检测集成
红旗检测自动集成到现有检查流程中：
- 任务级检查：检查红旗 #1, #5, #6（API 存在性、代码理解、测试覆盖）
- 阶段级检查：检查红旗 #2, #3（业务假设、技术时效）
- 方向检查：检查红旗 #4, #7（方法有效性、进展停滞）
自动化检测 (v0.8.2+)
红旗 #4（多次失败后仍用相同方法）已通过 observe-patterns.js PostToolUse hook 自动检测：
- 同文件 Edit 3+ 次 + 最近 5 步内 Bash 错误 2+ 次 → 自动输出
[RedFlag]警告 - 其他红旗仍需手动检查
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.
- 4d ago First seen · 175 lines · 7 tokens per session scan A f6c542fd7c23
self-check is a command published in the GitHub repository xiaobei930/cc-best (50 stars, last pushed 2mo ago), licensed MIT. It adds 7 tokens to every session and 1,321 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
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.
audit-repo-docs
Audit repository documentation against 85+ best practices from claude-code-ultimate-guide.
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).