CLAUDE.md Progressive Disclosurer
Slim down and restructure a bloated CLAUDE.md (or AGENTS.md) using progressive disclosure — move low-frequency detail to Level 2 references while keeping Level 1 lean, with zero information loss.
A CLAUDE.md that's grown too long stops being followed — the model drowns in detail. This playbook restructures it into a lean core with offloaded references, losing nothing.
Who it's for: Claude Code users, developers, prompt engineers
Example
"My CLAUDE.md is too long and the model ignores rules" → A restructured file with a lean Level 1 and detail moved to grep-verified Level 2 references
CLAUDE.md Template
New here? 3-minute setup guide → | Already set up? Copy the template below.
npx ccplaybooks add claude-md-progressive-disclosurer# CLAUDE.md 渐进式披露优化器
## 核心理念
> "找到最小的高信号 token 集合，最大化期望结果的可能性。" — Anthropic
**目标是最大化信息效率、可读性、可维护性。**
> 本 skill 自身遵守渐进式披露：新方法论以"精炼规则 + 触发条件"留在 SKILL.md，深度战例 / 引文沉到 references/。SKILL.md 行数由信息密度决定、**不设为硬目标**（约 500 行量级；新增高价值规则可略超，但深度永远沉 references）——skill 自己示范它教别人的事：**行数不是 KPI**，自洽地不拿"≤N 行"约束自己。
### 铁律：行数禁作 KPI，可作诊断症状
Get new playbooks like this one
One email a week with new Claude Code workflows. Free, like everything here.
No spam. Unsubscribe anytime.
What This Does
Slim down and restructure a bloated CLAUDE.md (or AGENTS.md) using progressive disclosure — move low-frequency detail to Level 2 references while keeping Level 1 lean, with zero information loss.
What's Inside
The template covers:
- 核心理念
- 优化工作流
- Level 1 内容分类
- 引用格式（四种）
- 核心原则
- 反模式警告
Quick Start
Step 1: Create a Project Folder
Make a dedicated folder for this workflow and open it in Claude Code.
Step 2: Download the Template
Click Download above to save the template, then drop it into your project as CLAUDE.md (or paste it into your existing one).
Step 3: Start Working
Tell Claude what you need in plain language — it will follow the template's workflow automatically. For example:
My CLAUDE.md is too long and the model ignores rules
Claude reads the template and runs the steps for you.