CLAUDE.md jako orchestrace workflow [Wiki]

Tato stránka je pouze pro čtení. Můžete si pouze prohlédnout zdrojový kód, ale ne ho měnit. Zeptejte se správce, pokud si myslíte, že něco není v pořádku.
====== CLAUDE.md jako orchestrace workflow ======

[[ai:platformy:claude-code:anatomie-projektu|Anatomie Claude Code projektu]] popisuje ''CLAUDE.md'' hlavně jako paměť repozitáře. Tady jde o druhou roli: ''CLAUDE.md'' jako provozní vrstva pro workflow, task management a rozhodovací principy agenta.
===== Přepis screenshotu =====

<code>
Boris Cherny's CLAUDE.md File

## Workflow Orchestration

### 1. Plan Mode Default
- Enter plan mode for ANY non-trivial task (3+ steps or architectural decisions)
- If something goes sideways, STOP and re-plan immediately
- Use plan mode for verification steps, not just building
- Write detailed specs upfront to reduce ambiguity

### 2. Subagent Strategy
- Use subagents liberally to keep main context window clean
- Offload research, exploration, and parallel analysis to subagents
- For complex problems, throw more compute at it via subagents
- One task per subagent for focused execution

### 3. Self-Improvement Loop
- After ANY correction from the user: update tasks/lessons.md with the pattern
- Write rules for yourself that prevent the same mistake
- Ruthlessly iterate on these lessons until mistake rate drops
- Review lessons at session start for relevant project

### 4. Verification Before Done
- Never mark a task complete without proving it works
- Diff behavior between main and your changes when relevant
- Ask yourself: "Would a staff engineer approve this?"
- Run tests, check logs, demonstrate correctness

### 5. Demand Elegance (Balanced)
- For non-trivial changes: pause and ask "is there a more elegant way?"
- If a fix feels hacky: "Knowing everything I know now, implement the elegant solution"
- Skip this for simple, obvious fixes -- don't over-engineer
- Challenge your own work before presenting it

### 6. Autonomous Bug Fixing
- When given a bug report: just fix it. Don't ask for hand-holding
- Point at logs, errors, failing tests -- then resolve them
- Zero context switching required from the user
- Go fix failing CI tests without being told how

Workflow

## Task Management

1. Plan First: Write plan to tasks/todo.md with checkable items
2. Verify Plan: Check in before starting implementation
3. Track Progress: Mark items complete as you go
4. Explain Changes: High-level summary at each step
5. Document Results: Add review section to tasks/todo.md
6. Capture Lessons: Update tasks/lessons.md after corrections

Tasks

## Core Principles

- Simplicity First: Make every change as simple as possible. Impact minimal code.
- No Laziness: Find root causes. No temporary fixes. Senior developer standards.
- Minimal Impact: Only touch what's necessary. No side effects with new bugs.

Principles
</code>

{{.:pasted:20260319-165344.png}}

===== Poznámka =====

Tenhle typ ''CLAUDE.md'' už není jen statický souhrn kontextu. Je to lehká provozní vrstva, která říká, jak má agent pracovat, kdy plánovat, jak delegovat práci a jak si průběžně ukládat lessons learned.