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.
55 lines
2.0 KiB
Markdown
55 lines
2.0 KiB
Markdown
---
|
||
created: "2026-03-08 21:32"
|
||
type: zettel
|
||
tags: [zettel, claude-code, token-optimization, cost]
|
||
source: "https://github.com/affaan-m/everything-claude-code"
|
||
---
|
||
|
||
# Everything Claude Code Token 优化
|
||
|
||
## 节省 60%+ 成本的四个策略
|
||
|
||
### 1. 模型路由
|
||
90% 任务用 Sonnet，Haiku 做搜索/文档，Opus 只用于架构和安全。用 `/model-route` 自动路由。
|
||
|
||
**子 agent 强制用 Haiku** —— 设置 `CLAUDE_CODE_SUBAGENT_MODEL=haiku`，所有通过 Task 工具派发的子 agent 都跑 Haiku，比默认便宜约 80%，文件读取/探索质量基本无损。这是新版的省钱大头。
|
||
|
||
### 2. MCP 精简
|
||
- 保持 < 10 个 MCP 启用
|
||
- 用 CLI + skill 替代 MCP wrapper（如 `gh` 替代 GitHub MCP、`aws` 替代 AWS MCP）
|
||
- 默认安装的 `memory` MCP 没有任何 skill/agent/hook 引用 → 优先关掉
|
||
- 每个 MCP 消耗上下文窗口，多到一定程度 200k 变 70k
|
||
|
||
### 3. 工具替换
|
||
mgrep 替代 grep/ripgrep，在 50 任务 benchmark 中减少约 2x token 使用。
|
||
|
||
### 4. 代码模块化
|
||
文件保持 200-400 行（最大 800）。模块化代码库让 agent 不需要读取大文件，减少上下文消耗，且首次成功率更高。
|
||
|
||
## 配置
|
||
|
||
```json
|
||
{
|
||
"model": "sonnet",
|
||
"env": {
|
||
"MAX_THINKING_TOKENS": "10000",
|
||
"CLAUDE_CODE_SUBAGENT_MODEL": "haiku"
|
||
}
|
||
}
|
||
```
|
||
|
||
> ⚠️ **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 控制压缩时机。
|
||
|
||
## Skill 的渐进式加载
|
||
|
||
Skill 启动时只读描述（约 100 tokens），只在相关时才加载完整内容。这比把所有内容放在 CLAUDE.md 系统提示中高效得多。
|
||
|
||
---
|
||
|
||
## Related
|
||
|
||
- [[Everything Claude Code 完整指南]]
|
||
- [[Everything Claude Code 用法速查]]
|
||
- [[Everything Claude Code 最佳实践]]
|
||
- [[Everything Claude Code Agent 编排模式]]
|