232b045e03
Updated ECC notes to match the current state of affaan-m/everything-claude-code docs/token-optimization.md and docs/SKILL-PLACEMENT-POLICY.md: - Drop CLAUDE_AUTOCOMPACT_PCT_OVERRIDE recommendations (now warned against upstream — variable can only lower threshold, opposite of intent) - Add CLAUDE_CODE_SUBAGENT_MODEL=haiku as the new core token-saving setting - Flag the default `memory` MCP for disablement (no skill/agent/hook references) - Add Skill Placement Policy section (curated/learned/imported/evolved + provenance) - Cover missing commands: /checkpoint, /sessions, /security-scan, /claw, /projects Add new resource: ECC 编排实战手册.md (721 lines). Six orchestration patterns (dmux+worktree, sequential claude -p, continuous-claude, Ralphinho RFC-DAG, santa-loop, Task in-process) with real commands, real plan.json structures, real CLI flags, and explicit "could not verify online" markers for /multi-* and /feature-dev. All sourced to specific commands/*.md or skills/*.md files. Cross-link the new manual from 完整指南 and 用法速查.
54 lines
2.1 KiB
Markdown
54 lines
2.1 KiB
Markdown
---
|
||
created: "2026-03-08 21:30"
|
||
type: zettel
|
||
tags: [zettel, claude-code, best-practices, AI-tools]
|
||
source: "https://github.com/affaan-m/everything-claude-code"
|
||
---
|
||
|
||
# Everything Claude Code 最佳实践
|
||
|
||
## 上下文窗口是最稀缺资源
|
||
|
||
200k 上下文窗口在启用太多 MCP 后可能只剩 70k。三条铁律：
|
||
|
||
1. **MCP < 10 个启用，< 80 个工具活跃** — 用 CLI + skill 替代 MCP（如 `gh` CLI 替代 GitHub MCP）
|
||
2. **关闭 auto compact** — 在逻辑断点手动 `/compact`，避免在关键推理中被截断
|
||
3. **CLAUDE.md < 200 行** — 详细规则放 `rules/`，利用 skill 的渐进式加载
|
||
|
||
## Token 成本路由
|
||
|
||
90% 任务用 Sonnet，只在架构决策和安全分析时用 Opus，搜索探索用 Haiku。设置：
|
||
|
||
```json
|
||
{ "model": "sonnet", "env": { "MAX_THINKING_TOKENS": "10000", "CLAUDE_CODE_SUBAGENT_MODEL": "haiku" } }
|
||
```
|
||
|
||
`CLAUDE_CODE_SUBAGENT_MODEL=haiku` 是省钱新核心 —— 子 agent(通过 Task 工具派发的)跑 Haiku，比默认便宜约 80%，文件读取/探索质量基本无损。
|
||
|
||
> ⚠️ **不要再设 `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE`**。仓库 `docs/token-optimization.md` 已警告：该变量在新版 Claude Code 上只能"降低阈值"(让压缩更早触发)，与延后压缩的目的相反。改用手动 `/compact` + `strategic-compact` skill。
|
||
|
||
用 mgrep 替代 grep 可减少约 50% token 使用。
|
||
|
||
## 记忆持久化
|
||
|
||
- 每个 session 结束保存摘要到 `.tmp` 文件（记录：有效方法、无效尝试、待办事项）
|
||
- 下次 session 提供文件路径作为上下文
|
||
- 动态注入：`claude --system-prompt "$(cat ~/.claude/contexts/dev.md)"`
|
||
|
||
## 并行但有纪律
|
||
|
||
- 最小可行并行度 — 不盲目开多终端
|
||
- Git worktree 隔离并行实例
|
||
- `/rename` 命名每个 chat，`/fork` 分叉非重叠工作
|
||
- 级联方法：新任务右开，从左到右扫描，同时不超过 3-4 个
|
||
|
||
---
|
||
|
||
## Related
|
||
|
||
- [[Everything Claude Code 完整指南]]
|
||
- [[Everything Claude Code 方法论与最佳实践]]
|
||
- [[Everything Claude Code 用法速查]]
|
||
- [[Everything Claude Code Agent 编排模式]]
|
||
- [[Everything Claude Code Token 优化]]
|