home / skills / benchflow-ai / skillsbench / planning-with-files
/tasks/organize-messy-files/environment/skills/planning-with-files
This skill enables persistent, on-disk planning for complex tasks by creating and updating task_plan.md, findings.md, and progress.md in your project.
npx playbooks add skill benchflow-ai/skillsbench --skill planning-with-filesReview the files below or copy the command above to add this skill to your agents.
---
name: planning-with-files
description: Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
allowed-tools:
- Read
- Write
- Edit
- Bash
- Glob
- Grep
- WebFetch
- WebSearch
metadata:
version: "2.1.2"
user-invocable: true
hooks:
SessionStart:
- hooks:
- type: command
command: "echo '[planning-with-files] Ready. Auto-activates for complex tasks, or invoke manually with /planning-with-files'"
PreToolUse:
- matcher: "Write|Edit|Bash"
hooks:
- type: command
command: "cat task_plan.md 2>/dev/null | head -30 || true"
PostToolUse:
- matcher: "Write|Edit"
hooks:
- type: command
command: "echo '[planning-with-files] File updated. If this completes a phase, update task_plan.md status.'"
Stop:
- hooks:
- type: command
command: "${CLAUDE_PLUGIN_ROOT}/scripts/check-complete.sh"
---
# Planning with Files
Work like Manus: Use persistent markdown files as your "working memory on disk."
## Important: Where Files Go
When using this skill:
- **Templates** are stored in the skill directory at `${CLAUDE_PLUGIN_ROOT}/templates/`
- **Your planning files** (`task_plan.md`, `findings.md`, `progress.md`) should be created in **your project directory** — the folder where you're working
| Location | What Goes There |
|----------|-----------------|
| Skill directory (`${CLAUDE_PLUGIN_ROOT}/`) | Templates, scripts, reference docs |
| Your project directory | `task_plan.md`, `findings.md`, `progress.md` |
This ensures your planning files live alongside your code, not buried in the skill installation folder.
## Quick Start
Before ANY complex task:
1. **Create `task_plan.md`** in your project — Use [templates/task_plan.md](templates/task_plan.md) as reference
2. **Create `findings.md`** in your project — Use [templates/findings.md](templates/findings.md) as reference
3. **Create `progress.md`** in your project — Use [templates/progress.md](templates/progress.md) as reference
4. **Re-read plan before decisions** — Refreshes goals in attention window
5. **Update after each phase** — Mark complete, log errors
> **Note:** All three planning files should be created in your current working directory (your project root), not in the skill's installation folder.
## The Core Pattern
```
Context Window = RAM (volatile, limited)
Filesystem = Disk (persistent, unlimited)
→ Anything important gets written to disk.
```
## File Purposes
| File | Purpose | When to Update |
|------|---------|----------------|
| `task_plan.md` | Phases, progress, decisions | After each phase |
| `findings.md` | Research, discoveries | After ANY discovery |
| `progress.md` | Session log, test results | Throughout session |
## Critical Rules
### 1. Create Plan First
Never start a complex task without `task_plan.md`. Non-negotiable.
### 2. The 2-Action Rule
> "After every 2 view/browser/search operations, IMMEDIATELY save key findings to text files."
This prevents visual/multimodal information from being lost.
### 3. Read Before Decide
Before major decisions, read the plan file. This keeps goals in your attention window.
### 4. Update After Act
After completing any phase:
- Mark phase status: `in_progress` → `complete`
- Log any errors encountered
- Note files created/modified
### 5. Log ALL Errors
Every error goes in the plan file. This builds knowledge and prevents repetition.
```markdown
## Errors Encountered
| Error | Attempt | Resolution |
|-------|---------|------------|
| FileNotFoundError | 1 | Created default config |
| API timeout | 2 | Added retry logic |
```
### 6. Never Repeat Failures
```
if action_failed:
next_action != same_action
```
Track what you tried. Mutate the approach.
## The 3-Strike Error Protocol
```
ATTEMPT 1: Diagnose & Fix
→ Read error carefully
→ Identify root cause
→ Apply targeted fix
ATTEMPT 2: Alternative Approach
→ Same error? Try different method
→ Different tool? Different library?
→ NEVER repeat exact same failing action
ATTEMPT 3: Broader Rethink
→ Question assumptions
→ Search for solutions
→ Consider updating the plan
AFTER 3 FAILURES: Escalate to User
→ Explain what you tried
→ Share the specific error
→ Ask for guidance
```
## Read vs Write Decision Matrix
| Situation | Action | Reason |
|-----------|--------|--------|
| Just wrote a file | DON'T read | Content still in context |
| Viewed image/PDF | Write findings NOW | Multimodal → text before lost |
| Browser returned data | Write to file | Screenshots don't persist |
| Starting new phase | Read plan/findings | Re-orient if context stale |
| Error occurred | Read relevant file | Need current state to fix |
| Resuming after gap | Read all planning files | Recover state |
## The 5-Question Reboot Test
If you can answer these, your context management is solid:
| Question | Answer Source |
|----------|---------------|
| Where am I? | Current phase in task_plan.md |
| Where am I going? | Remaining phases |
| What's the goal? | Goal statement in plan |
| What have I learned? | findings.md |
| What have I done? | progress.md |
## When to Use This Pattern
**Use 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
## Templates
Copy these templates to start:
- [templates/task_plan.md](templates/task_plan.md) — Phase tracking
- [templates/findings.md](templates/findings.md) — Research storage
- [templates/progress.md](templates/progress.md) — Session logging
## Scripts
Helper scripts for automation:
- `scripts/init-session.sh` — Initialize all planning files
- `scripts/check-complete.sh` — Verify all phases complete
## Advanced Topics
- **Manus Principles:** See [reference.md](reference.md)
- **Real Examples:** See [examples.md](examples.md)
## Anti-Patterns
| Don't | Do Instead |
|-------|------------|
| Use TodoWrite for persistence | Create task_plan.md file |
| State goals once and forget | Re-read plan before decisions |
| Hide errors and retry silently | Log errors to plan file |
| Stuff everything in context | Store large content in files |
| Start executing immediately | Create plan file FIRST |
| Repeat failed actions | Track attempts, mutate approach |
| Create files in skill directory | Create files in your project |
This skill implements a Manus-style file-based planning workflow that turns ephemeral context into persistent project files. It creates and maintains task_plan.md, findings.md, and progress.md in your project directory to guide multi-step tasks, capture discoveries, and log session progress. Use it to impose discipline on complex workflows and avoid losing important state between tool calls.
On initialization, the skill provides templates and scripts and instructs you to create three markdown files in your project root: task_plan.md, findings.md, and progress.md. During work, it enforces a pattern of writing key outputs to disk, reading the plan before major decisions, and updating files after each phase or discovery. It also prescribes an error-tracking and 3-strike remediation protocol to prevent repeated failures.
Where should the planning files be stored?
Always create task_plan.md, findings.md, and progress.md in your project directory (the working folder), not in the skill installation folder.
What triggers an immediate write to disk?
After every two view/browser/search operations or any time you discover new information, save the key findings to findings.md immediately.
What if a phase fails repeatedly?
Follow the 3-strike protocol: diagnose and fix, try an alternative method, then broaden the rethink. After three failures, escalate to the user with detailed logs.