planning-with-files
A persistent file-based planning system for AI coding agents that maintains task_plan.md, findings.md, and progress.md in the project directory to survive context loss and session resets.
Is planning-with-files safe to install?
Review the source first: our audit of planning-with-files's source files found 8 shell commands, 0 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes arbitrary shell commands and PowerShell scripts to manage planning files and session state. It reads and writes markdown files in the project directory.
How we audit skills: our security review methodology.
Who is this skill for?
Developers and AI agents working on complex, multi-step projects requiring persistent state management across long-running sessions.
What can you do with it?
- Multi-step projects requiring 5+ tool calls
- Research tasks involving discovery and documentation
- Building and creating software projects
- Parallel task workflows using isolated planning directories
How good is this skill?
Quality score: 5/10. The skill provides a robust, well-documented framework for persistent agent memory. It includes clear instructions, templates, and automated hooks for session management.
What does the skill file contain?
# Planning with Files
Work like Manus: Use persistent markdown files as your "working memory on disk."
## FIRST: Restore Context (v2.2.0)
**Before doing anything else**, check if planning files exist and read them:
1. If `task_plan.md` exists, read `task_plan.md`, `progress.md`, and `findings.md` immediately.
2. Then check for unsynced context from a previous session:
```bash
# Linux/macOS — auto-detects skill directory (plugin env or default install path)
SKILL_DIR="${CLAUDE_PLUGIN_ROOT:-$HOME/.claude/skills/planning-with-files}"
$(command -v python3 || command -v python) "${SKILL_DIR}/s...Frequently asked questions
Where should I store my planning files?
Store task_plan.md, findings.md, and progress.md in your project root directory.
How do I recover my plan after a session reset?
The skill provides a session-catchup.py script to recover context from previous sessions after a /clear command.
Can I work on multiple tasks at once?
Yes, use the init-session.sh script to create isolated plan directories under .planning/ for parallel workflows.
What happens to my plan during context compaction?
The PreCompact hook triggers to remind the agent to flush progress to disk, ensuring the plan remains available for re-reading after compaction.
Related skills
find-skills
2.3MUsers seeking to extend agent capabilities with specialized tools, workflows, or knowledge packages
The find-skills skill enables agents to search for, discover, and install modular packages from the open agent skills ecosystem using the Skills CLI.
image-to-video
355.0KDevelopers and users who need to automate video generation from images using the RunComfy platform
The image-to-video skill routes user requests to specific RunComfy animation models based on intent. It selects HappyHorse 1.0 I2V for general animation, Wan 2.7 for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal composition. The skill executes the RunComfy CLI to process inputs and download generated video files.
video-edit
338.7KUsers of the RunComfy CLI who need to automate video editing tasks like restyling, background swapping, or motion transfer
The video-edit skill acts as a router for the RunComfy CLI, selecting between Wan 2.7 Edit-Video, Kling 2.6 Pro Motion Control, and Lucy Edit Restyle models based on user intent to perform video transformations.
lark-base
314.2KUsers who need to programmatically interact with Lark Bitable data, automate table management, or perform data analysis within the Lark ecosystem
The lark-base skill provides a command-line interface for managing Lark Bitable (Base) resources, including tables, records, fields, views, forms, dashboards, workflows, and role-based permissions.