Files

Yaojia Wang 232b045e03 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.

2026-04-26 12:17:47 +02:00

1.1 KiB

Raw Blame History

created, type, tags, source

created

type

MCP 数量与上下文窗口的反比关系

每个启用的 MCP Server 都会占用上下文窗口空间（工具定义、schema 描述等）。实测数据：

0-5 个 MCP: 有效上下文接近 200K tokens
10+ 个 MCP: 有效上下文降至 ~70K tokens（降幅 65%）

最佳实践:

活跃 MCP <= 10 个，活跃工具总数 <= 80 个
用 disabledMcpServers 动态禁用不用的
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（如 gh、aws）而不是 MCP wrapper
使用 llms.txt 模式获取文档，避免 MCP 常驻开销

这是 Claude Code 性能优化中最重要的单一因素 — 比任何 Agent 或 Skill 都重要。

1.1 KiB Raw Blame History Unescape Escape

MCP 数量与上下文窗口的反比关系

Related

1.1 KiB

Raw Blame History