planning-with-files
npx machina-cli add skill Taoidle/plan-cascade/planning-with-files --openclawPlanning with Files
Work like Manus: Use persistent markdown files as your "working memory on disk."
FIRST: Check for Previous Session (v2.2.0)
Before starting work, check for unsynced context from a previous session:
# Linux/macOS
uv run python ${CLAUDE_PLUGIN_ROOT}/scripts/session-catchup.py "$(pwd)"
# Windows PowerShell
& (Get-Command python -ErrorAction SilentlyContinue).Source "$env:USERPROFILE\.claude\skills\planning-with-files\scripts\session-catchup.py" (Get-Location)
If catchup report shows unsynced context:
- Run
git diff --statto see actual code changes - Read current planning files
- Update planning files based on catchup + git diff
- Then proceed with task
Important: Where Files Go
- Templates are in
${CLAUDE_PLUGIN_ROOT}/templates/ - Your planning files go in your project directory
| Location | What Goes There |
|---|---|
Skill directory (${CLAUDE_PLUGIN_ROOT}/) | Templates, scripts, reference docs |
| Your project directory | task_plan.md, findings.md, progress.md |
Quick Start
Standard Mode
Before ANY complex task:
- Create
task_plan.md— Use templates/task_plan.md as reference - Create
findings.md— Use templates/findings.md as reference - Create
progress.md— Use templates/progress.md as reference - Re-read plan before decisions — Refreshes goals in attention window
- Update after each phase — Mark complete, log errors
Worktree Mode (Multi-Task Parallel Development)
For parallel multi-task development with isolated Git worktrees:
-
Start worktree mode — Use
/planning-with-files:worktree [task-name] [target-branch]- Example:
/planning-with-files:worktree feature-auth main - Creates a new Git worktree directory (
.worktree/feature-auth/) - Creates a task branch with planning files inside the worktree
- Main directory stays on original branch (no switching!)
- Multiple worktrees can exist simultaneously for parallel tasks
- Example:
-
Navigate to worktree —
cd .worktree/feature-auth- Work on your task in this isolated environment
- Follow standard planning workflow
-
Complete and merge — Use
/planning-with-files:complete [target-branch]from inside the worktree- Deletes planning files from worktree
- Navigates to root directory
- Merges task branch to target
- Removes the worktree directory
- Deletes the task branch
Multi-Task Example:
# Start task 1
/planning-with-files:worktree fix-auth-bug
cd .worktree/fix-auth-bug
# In another terminal, start task 2 (parallel!)
/planning-with-files:worktree refactor-api
cd .worktree/refactor-api
# Each task has its own directory and branch
# No conflicts, no branch switching needed
Benefits:
- Work on multiple tasks simultaneously without conflicts
- Each task has its own isolated environment
- No need to switch branches in the main directory
- Easy cleanup when tasks are complete
Note: Planning files go in your project root, not the skill 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.
## 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 — Phase tracking
- templates/findings.md — Research storage
- templates/progress.md — Session logging
Scripts
Helper scripts for automation:
Standard Mode Scripts
scripts/init-session.sh— Initialize all planning filesscripts/check-complete.sh— Verify all phases completescripts/session-catchup.py— Recover context from previous session (v2.2.0)
Worktree Mode Scripts (v2.7.2)
scripts/worktree-init.sh— Start a new worktree session (bash)scripts/worktree-init.ps1— Start a new worktree session (PowerShell)scripts/worktree-complete.sh— Complete and merge worktree (bash)scripts/worktree-complete.ps1— Complete and merge worktree (PowerShell)
Advanced Topics
- Manus Principles: See reference.md
- Real Examples: See 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 |
Source
git clone https://github.com/Taoidle/plan-cascade/blob/master/skills/planning-with-files/SKILL.mdView on GitHub Overview
This skill uses on disk markdown files as persistent memory to enable structured planning for complex tasks. It creates three core files task_plan.md, findings.md, and progress.md to capture scope, insights, and milestones. It also supports automatic session recovery after /clear and an optional Git worktree mode.
How This Skill Works
Start by working in your project with three planning files stored on disk. The system updates task_plan.md with the planned steps, findings.md with insights from tool use, and progress.md with milestones as you work. PreToolUse hooks enforce worktree location checks and contextual visibility, while PostToolUse and Stop hooks manage summaries and completion checks.
When to Use It
- Starting a complex multi step task that will involve more than five tool calls
- Conducting a research project with evolving findings and milestones
- Long running tasks that benefit from persistent on disk memory
- Recovering a disrupted session after a reset using the built in recovery flow
- Working in a Git worktree or isolated repository where location verification matters
Quick Start
- Step 1: Change to your project directory and ensure the planning system templates exist
- Step 2: Initialize planning by creating task_plan.md findings.md and progress.md and add an initial plan in task_plan.md
- Step 3: Run tools as needed and update findings.md and progress.md; if you need to reset, use the recovery flow after /clear
Best Practices
- Create and maintain the three core files task_plan.md findings.md and progress.md in your project root
- Update findings.md after each tool call with decisions and insights
- Regularly review and update task_plan.md to reflect next steps and status
- Enable and respect worktree mode by configuring a .planning-config.json and verifying location for writes
- When resuming after a disruption, use the session catchup flow to synchronize context
Example Use Cases
- Plan a data analysis workflow from data collection to results and log steps in task_plan.md Findings.md captures insights
- Draft a literature review workflow with experiments and documented findings
- Outline a software feature spec and break work into tasks while recording decisions in findings.md
- Run a security configuration audit across multiple settings with consolidated findings and progress
- Coordinate grant writing or research proposals with milestones and expected outcomes