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 skills add xiaobei930/cc-best --skill sessiongit 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/skills/xiaobei930/cc-best/session)<a href="https://agentmods.dev/skills/xiaobei930/cc-best/session"><img src="https://agentmods.dev/badge/skills/xiaobei930/cc-best/session/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/skills/xiaobei930/cc-best/session"><img src="https://agentmods.dev/badge/skills/xiaobei930/cc-best/session.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 | $0.00024 | $0.01091 |
| Opus 5.5 | $0.00010 | $0.00436 |
| Sonnet 5.5 | $0.00005 | $0.00218 |
| Haiku 4.5 | $0.00002 | $0.00109 |
Grade A, and why
session 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
会话生命周期管理
本技能提供 Claude Code 会话的生命周期管理策略，整合持续学习和上下文压缩。
会话生命周期
会话开始 ──→ 工作阶段 ──→ 检查点 ──→ 会话结束
│ │ │ │
│ │ │ └─→ 提取模式 (/learning)
│ │ └─→ 上下文压缩 (/cc-best:compact-context)
│ └─→ 持续工作
└─→ 加载上次上下文
策略选择
| 场景 | 推荐策略 | 子技能 |
|---|---|---|
| 上下文接近限制 | 策略性压缩 | /cc-best:compact-context |
| 完成重要任务节点 | 主动压缩 | /cc-best:compact-context |
| 会话结束时 | 提取可复用模式 | /learning |
| 解决了复杂问题 | 记录解决方案 | /learning |
| 发现项目特定知识 | 记录到知识库 | /learning |
子技能
1. learning（持续学习）
适用场景：
- 会话结束时提取模式
- 记录调试技巧
- 保存项目特定知识
- 积累可复用解决方案
使用方式：/learning 或参阅 skills/learning/SKILL.md
2. compact（上下文压缩）
适用场景：
- 上下文接近限制时
- 完成阶段性任务后
- 切换工作主题前
- 需要释放上下文空间
使用方式：/cc-best:compact-context 或参阅 skills/compact/SKILL.md
最佳实践
何时压缩
- 主动压缩 - 完成一个功能模块后
- 被动压缩 - 系统提示上下文接近限制
- 切换压缩 - 准备切换到不同任务前
何时记录
- 立即记录 - 解决问题后立即记录
- 定期回顾 - 会话结束前检查值得记录的内容
- 增量更新 - 发现新知识时更新已有记录
会话别名 | Session Aliases
为会话设置语义化标签，便于快速查找和恢复。
别名管理
在会话元数据中记录语义化标签：
{
"name": "feature-login-page",
"sessionPath": "memory-bank/progress.md",
"tags": ["feature", "frontend"],
"created": "2026-02-24 14:30:00",
"summary": "实现登录页面 - PM/Lead/Dev 已完成"
}
存储位置: ~/.claude/session-aliases.json（全局，跨项目共享）
标签分类系统：
| 前缀 | 含义 | 示例 |
|---|---|---|
feature-* |
功能开发 | feature-login-page |
bugfix-* |
缺陷修复 | bugfix-auth-timeout |
refactor-* |
重构改进 | refactor-api-layer |
explore-* |
技术探索 | explore-new-framework |
跨会话恢复
当使用 /cc-best:catchup 恢复时：
- 读取上次会话的 alias 信息
- 加载对应的 progress.md 状态
- 显示上次会话的关键决策摘要
别名操作
- 保存: 会话结束时自动提示或通过
/cc-best:checkpoint手动触发 - 查找: 通过
/cc-best:catchup --alias <name>快速恢复指定会话 - 清理: 超过 30 天未使用的别名自动标记为过期
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 125 lines · 24 tokens per session scan A 83aa92eef14d
session is a skill published in the GitHub repository xiaobei930/cc-best (48 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 1,091 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
rtk-optimizer
Wrap high-verbosity shell commands with RTK to reduce token consumption. Use when running git log, git diff, cargo test, pytest, or other verbose CLI output that wastes context window tokens.
session-save
Save the current session state (decisions, modified files, current status, and next steps) to a handoff file for later resume.
catchup
Restore context after /clear by summarizing recent work and project state.
handoff-create
Generate a structured handoff document from the current session. Captures scope, relevant files with line numbers, key discoveries, work completed, current status, next steps, and code snippets. Use before ending a session or handing work to another agent.
handoff-update
Update an existing handoff document with current session progress. Applies section-specific merge rules: append-only for Work Done (never deletes history), replace for Status and Next Steps, merge for Files and Discoveries. Falls back to creating a new handoff if no source file is found.
handoff-resume
Load a handoff document and resume work from where a previous session left off. Parses scope, file references, completed work, and next steps, then checks live state and existing authorization before proceeding.