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

@@ -242,15 +242,7 @@ ECC 最独特的创新 — **本能学习系统**。
# Feature development: start new feature (清除调试噪音)
```
禁用自动压缩的配置:
```json
{
"env": {
"CLAUDE_AUTOCOMPACT_PCT_OVERRIDE": "50"
}
}
```
> ⚠️ **不要再设 `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE`**。仓库 `docs/token-optimization.md` 现已警告:该变量在新版 Claude Code 上只能"降低阈值"(让压缩**更早**触发),与延后压缩的目的完全相反。完全靠手动 `/compact` + `strategic-compact` skill 控制压缩时机。
### 6. Verification Loop验证循环
@@ -316,13 +308,16 @@ ECC 最独特的创新 — **本能学习系统**。
"model": "sonnet",
"env": {
"MAX_THINKING_TOKENS": "10000",
"CLAUDE_AUTOCOMPACT_PCT_OVERRIDE": "50"
"CLAUDE_CODE_SUBAGENT_MODEL": "haiku"
}
}
// → ~60% 成本降低 (Sonnet vs Opus)
// → ~70% thinking 成本降低
// → ~80% 子 agent 成本降低 (Haiku 跑 Task 工具派发的子 agent)
```
⚠️ **不要再设 `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE`** —— 仓库现已警告该变量在新版只会让压缩更早触发,改用手动 `/compact`
**模型选择策略**:
| 模型 | 场景 | 能力/成本比 |
@@ -336,7 +331,8 @@ ECC 最独特的创新 — **本能学习系统**。
- 启用的 MCP <= 10 个,活跃工具总数 <= 80 个
- 10+ MCP 时,有效上下文从 200K 降至 ~70K tokens
-`disabledMcpServers` 禁用不用的
- 重操作优先用 CLI`gh`)而不是 MCP
- **默认安装的 `memory` MCP 没有任何 skill/agent/hook 引用 → 优先关掉**(仓库 `docs/token-optimization.md` 明确建议)
- 重操作优先用 CLI`gh``aws`)而不是 MCP wrapper
- 使用 `llms.txt` 模式(如 `vercel.com/docs/llms.txt`)代替 MCP 获取文档
### 会话管理