vault: align ECC docs with current repo and add orchestration manual

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.
This commit is contained in:
Yaojia Wang
2026-04-26 12:17:47 +02:00
parent ab3263c474
commit 232b045e03
7 changed files with 820 additions and 20 deletions

View File

@@ -12,9 +12,12 @@ source: "https://github.com/affaan-m/everything-claude-code"
### 1. 模型路由
90% 任务用 SonnetHaiku 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 MCP 启用
- CLI + skill 替代 MCP wrapper gh CLI 替代 GitHub MCP
- CLI + skill 替代 MCP wrapper `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 70k
### 3. 工具替换
@@ -30,11 +33,13 @@ mgrep 替代 grep/ripgrep在 50 任务 benchmark 中减少约 2x token 使用
"model": "sonnet",
"env": {
"MAX_THINKING_TOKENS": "10000",
"CLAUDE_AUTOCOMPACT_PCT_OVERRIDE": "50"
"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 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