Work like Manus — the AI agent company Meta just acquired for $2 billion.
A Claude Code skill that transforms your workflow to use persistent markdown files for planning, progress tracking, and knowledge storage — the exact pattern that made Manus worth billions.
On December 29, 2025, Meta acquired Manus for $2 billion. In just 8 months, Manus went from launch to $100M+ revenue. Their secret? Context engineering.
This skill implements Manus's core workflow pattern:
"Markdown is my 'working memory' on disk. Since I process information iteratively and my active context has limits, Markdown files serve as scratch pads for notes, checkpoints for progress, building blocks for final deliverables." — Manus AI
Claude Code (and most AI agents) suffer from:
- Volatile memory — TodoWrite tool disappears on context reset
- Goal drift — After 50+ tool calls, original goals get forgotten
- Hidden errors — Failures aren't tracked, so the same mistakes repeat
- Context stuffing — Everything crammed into context instead of stored
For every complex task, create THREE files:
task_plan.md → Track phases and progress
notes.md → Store research and findings
[deliverable].md → Final output
1. Create task_plan.md with goal and phases
2. Research → save to notes.md → update task_plan.md
3. Read notes.md → create deliverable → update task_plan.md
4. Deliver final output
Key insight: By reading task_plan.md before each decision, goals stay in the attention window. This is how Manus handles ~50 tool calls without losing track.
# Navigate to your Claude Code skills directory
cd ~/.claude/skills # or your custom skills path
# Clone this skill
git clone https://github.com/OthmanAdi/planning-with-files.git- Download or copy the
planning-with-filesfolder - Place it in your Claude Code skills directory:
- macOS/Linux:
~/.claude/skills/ - Windows:
%USERPROFILE%\.claude\skills\
- macOS/Linux:
In Claude Code, the skill will automatically activate when you:
- Start complex tasks
- Mention "planning", "organize", or "track progress"
- Ask for structured work
Once installed, Claude will automatically:
- Create
task_plan.mdbefore starting complex tasks - Update progress with checkboxes after each phase
- Store findings in
notes.mdinstead of stuffing context - Log errors for future reference
- Re-read plan before major decisions
You: "Research the benefits of TypeScript and write a summary"
Claude creates:
# Task Plan: TypeScript Benefits Research
## Goal
Create a research summary on TypeScript benefits.
## Phases
- [x] Phase 1: Create plan ✓
- [ ] Phase 2: Research and gather sources (CURRENT)
- [ ] Phase 3: Synthesize findings
- [ ] Phase 4: Deliver summary
## Status
**Currently in Phase 2** - Searching for sourcesThen continues through each phase, updating the file as it goes.
This skill implements these key context engineering principles:
| Principle | Implementation |
|---|---|
| Filesystem as memory | Store in files, not context |
| Attention manipulation | Re-read plan before decisions |
| Error persistence | Log failures in plan file |
| Goal tracking | Checkboxes show progress |
| Append-only context | Never modify history |
planning-with-files/
├── SKILL.md # Core instructions (what Claude reads)
├── reference.md # Manus principles deep dive
├── examples.md # Real usage examples
└── README.md # This file
Use this pattern for:
- Multi-step tasks (3+ steps)
- Research tasks
- Building/creating projects
- Tasks spanning many tool calls
- Anything requiring organization
Skip for:
- Simple questions
- Single-file edits
- Quick lookups
- Manus AI — For pioneering context engineering patterns that made this possible
- Anthropic — For Claude Code and the Agent Skills framework
- Based on Context Engineering for AI Agents
Contributions welcome! Please:
- Fork the repository
- Create a feature branch
- Submit a pull request
MIT License — feel free to use, modify, and distribute.
Author: Ahmad Othman Ammar Adi