Release v2.3.0 - Multi-IDE support (Codex + OpenCode)

- Version bump to 2.3.0 - Updated CHANGELOG with new features - Updated SKILL.md version fields New features: - Codex IDE support via personal skills - OpenCode IDE support via personal/project skills - oh-my-opencode compatibility - Based on real analysis of obra/superpowers Closes #27 Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Update documentation for Codex and OpenCode support
2026-01-17 22:55:23 +01:00 · 2026-01-17 22:55:19 +01:00 · 2026-01-17 22:55:14 +01:00 · 2026-01-17 22:55:09 +01:00 · 2026-01-17 22:44:18 +01:00 · 2026-01-17 21:49:15 +01:00
14 changed files with 1211 additions and 45 deletions
@@ -1,6 +1,6 @@
 {
  "name": "planning-with-files",
-  "version": "2.2.0",
+  "version": "2.3.0",
  "description": "Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Includes hooks for automatic plan re-reading and completion verification. Use when starting complex tasks, multi-step projects, research tasks, or when you want structured output.",
  "author": {
    "name": "OthmanAdi",
@@ -0,0 +1,92 @@
+# Installing planning-with-files for Codex
+
+## Prerequisites
+
+- Codex IDE installed
+- Git installed (optional, for cloning)
+
+## Installation
+
+### Option 1: Clone Repository (Recommended)
+
+```bash
+mkdir -p ~/.codex/skills
+cd ~/.codex/skills
+git clone https://github.com/OthmanAdi/planning-with-files.git
+```
+
+### Option 2: Manual Copy
+
+1. Download or clone this repository
+2. Copy the entire `planning-with-files/` directory to `~/.codex/skills/`
+3. Ensure the structure matches:
+   ```
+   ~/.codex/skills/planning-with-files/
+   ├── planning-with-files/
+   │   ├── SKILL.md
+   │   ├── templates/
+   │   └── scripts/
+   ```
+
+## Usage
+
+### If Using Superpowers
+
+If you have [obra/superpowers](https://github.com/obra/superpowers) installed:
+
+```bash
+~/.codex/superpowers/.codex/superpowers-codex use-skill planning-with-files
+```
+
+Superpowers will find it in your personal skills directory.
+
+### If NOT Using Superpowers
+
+Manually read the skill file when starting complex tasks:
+
+```bash
+cat ~/.codex/skills/planning-with-files/planning-with-files/SKILL.md
+```
+
+Or add to your `~/.codex/AGENTS.md`:
+
+```markdown
+## Planning with Files
+
+<IMPORTANT>
+For complex multi-step tasks (3+ steps, research, building projects):
+1. Read the planning-with-files skill: `cat ~/.codex/skills/planning-with-files/planning-with-files/SKILL.md`
+2. Create task_plan.md, findings.md, progress.md in your project directory
+3. Follow the 3-file pattern throughout the task
+</IMPORTANT>
+```
+
+## Verification
+
+Check that the skill exists:
+
+```bash
+ls -la ~/.codex/skills/planning-with-files/planning-with-files/SKILL.md
+```
+
+## Troubleshooting
+
+### Skill not found
+
+- Verify path: `~/.codex/skills/planning-with-files/planning-with-files/SKILL.md`
+- Check file exists and is readable
+- Ensure SKILL.md has proper YAML frontmatter
+
+### Scripts not executing
+
+**Windows users:**
+- Use PowerShell versions: `*.ps1`
+- Set execution policy: `Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser`
+
+**Unix/Mac users:**
+- Make scripts executable: `chmod +x ~/.codex/skills/planning-with-files/scripts/*.sh`
+
+## Getting Help
+
+- Issues: https://github.com/OthmanAdi/planning-with-files/issues
+- Documentation: https://github.com/OthmanAdi/planning-with-files
@@ -0,0 +1,139 @@
+# Installing planning-with-files for OpenCode
+
+## Prerequisites
+
+- OpenCode.ai installed
+- Git installed (optional, for cloning)
+
+## Installation
+
+### Option 1: Global Installation (All Projects)
+
+```bash
+mkdir -p ~/.config/opencode/skills
+cd ~/.config/opencode/skills
+git clone https://github.com/OthmanAdi/planning-with-files.git
+```
+
+### Option 2: Project-Specific Installation
+
+```bash
+# In your OpenCode project root
+mkdir -p .opencode/skills
+cd .opencode/skills
+git clone https://github.com/OthmanAdi/planning-with-files.git
+```
+
+### Option 3: Manual Copy
+
+**For global installation:**
+1. Download or clone this repository
+2. Copy to `~/.config/opencode/skills/planning-with-files/`
+
+**For project installation:**
+1. Download or clone this repository
+2. Copy to `.opencode/skills/planning-with-files/` in your project
+
+## File Structure
+
+After installation:
+
+```
+~/.config/opencode/skills/planning-with-files/  (or .opencode/skills/planning-with-files/)
+├── planning-with-files/
+│   ├── SKILL.md              # Main skill file
+│   ├── templates/
+│   │   ├── task_plan.md
+│   │   ├── findings.md
+│   │   └── progress.md
+│   └── scripts/
+│       ├── check-complete.sh
+│       ├── check-complete.ps1
+│       ├── init-session.sh
+│       ├── init-session.ps1
+│       └── session-catchup.py
+```
+
+## Usage
+
+### If Using Superpowers Plugin
+
+If you have [obra/superpowers](https://github.com/obra/superpowers) installed as an OpenCode plugin:
+
+```
+Use the use_skill tool with skill_name: "planning-with-files"
+```
+
+OpenCode will find it automatically (personal skills override superpowers skills).
+
+### If NOT Using Superpowers
+
+You can still manually load the skill:
+
+1. Navigate to `~/.config/opencode/skills/planning-with-files/planning-with-files/`
+2. Read SKILL.md
+3. Follow the instructions for creating task_plan.md, findings.md, progress.md
+
+Or create a custom tool/command to load it.
+
+## Skill Priority
+
+If installed as:
+- **Project skill** (`.opencode/skills/planning-with-files/`) - Highest priority
+- **Personal skill** (`~/.config/opencode/skills/planning-with-files/`) - Medium priority
+- If superpowers has a planning-with-files skill - Lowest priority
+
+Project skills override personal skills, which override superpowers skills.
+
+## Verification
+
+**Global installation:**
+```bash
+ls -la ~/.config/opencode/skills/planning-with-files/planning-with-files/SKILL.md
+```
+
+**Project installation:**
+```bash
+ls -la .opencode/skills/planning-with-files/planning-with-files/SKILL.md
+```
+
+## Troubleshooting
+
+### Skill not loading
+
+1. Verify SKILL.md exists at the correct path
+2. Check YAML frontmatter is valid:
+   ```yaml
+   ---
+   name: planning-with-files
+   description: ...
+   ---
+   ```
+3. If using superpowers plugin, use `find_skills` tool to verify it's discovered
+
+### Scripts not executing
+
+**Windows:**
+- Use PowerShell versions: `*.ps1`
+- Set execution policy: `Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser`
+
+**Unix/Mac:**
+- Make executable: `chmod +x ~/.config/opencode/skills/planning-with-files/scripts/*.sh`
+
+### oh-my-opencode Blocking
+
+If using oh-my-opencode and the skill isn't recognized:
+
+1. Check `~/.config/opencode/oh-my-opencode.json`
+2. Ensure planning-with-files is NOT in `disabled_skills` array:
+   ```json
+   {
+     "disabled_skills": []
+   }
+   ```
+3. Restart OpenCode
+
+## Getting Help
+
+- Issues: https://github.com/OthmanAdi/planning-with-files/issues
+- Documentation: https://github.com/OthmanAdi/planning-with-files
@@ -2,6 +2,111 @@

 All notable changes to this project will be documented in this file.

+## [2.3.0] - 2026-01-17
+
+### Added
+
+- **Codex IDE Support**
+  - Created `.codex/INSTALL.md` with installation instructions
+  - Skills install to `~/.codex/skills/planning-with-files/`
+  - Works with obra/superpowers or standalone
+  - Added `docs/codex.md` for user documentation
+  - Based on analysis of obra/superpowers Codex implementation
+
+- **OpenCode IDE Support** (Issue #27)
+  - Created `.opencode/INSTALL.md` with installation instructions
+  - Global installation: `~/.config/opencode/skills/planning-with-files/`
+  - Project installation: `.opencode/skills/planning-with-files/`
+  - Works with obra/superpowers plugin or standalone
+  - oh-my-opencode compatibility documented
+  - Added `docs/opencode.md` for user documentation
+  - Based on analysis of obra/superpowers OpenCode plugin
+
+### Changed
+
+- Updated README.md with Supported IDEs table
+- Updated README.md file structure diagram
+- Updated docs/installation.md with Codex and OpenCode sections
+- Version bump to 2.3.0
+
+### Documentation
+
+- Added Codex and OpenCode to IDE support table in README
+- Created comprehensive installation guides for both IDEs
+- Documented skill priority system for OpenCode
+- Documented integration with superpowers ecosystem
+
+### Research
+
+This implementation is based on real analysis of:
+- [obra/superpowers](https://github.com/obra/superpowers) repository
+- Codex skill system and CLI architecture
+- OpenCode plugin system and skill resolution
+- Skill priority and override mechanisms
+
+### Thanks
+
+- @Realtyxxx for feedback on Issue #27 about OpenCode support
+- obra for the superpowers reference implementation
+
+---
+
+## [2.2.2] - 2026-01-17
+
+### Fixed
+
+- **Restored Skill Activation Language** (PR #34)
+  - Restored the activation trigger in SKILL.md description
+  - Description now includes: "Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls"
+  - This language was accidentally removed during the v2.2.1 merge
+  - Helps Claude auto-activate the skill when detecting appropriate tasks
+
+### Changed
+
+- Updated version to 2.2.2 in all SKILL.md files and plugin.json
+
+### Thanks
+
+- Community members for catching this issue
+
+---
+
+## [2.2.1] - 2026-01-17
+
+### Added
+
+- **Session Recovery Feature** (PR #33 by @lasmarois)
+  - Automatically detect and recover unsynced work from previous sessions after `/clear`
+  - New `scripts/session-catchup.py` analyzes previous session JSONL files
+  - Finds last planning file update and extracts conversation that happened after
+  - Recovery triggered automatically when invoking `/planning-with-files`
+  - Pure Python stdlib implementation, no external dependencies
+
+- **PreToolUse Hook Enhancement**
+  - Now triggers on Read/Glob/Grep in addition to Write/Edit/Bash
+  - Keeps task_plan.md in attention during research/exploration phases
+  - Better context management throughout workflow
+
+### Changed
+
+- SKILL.md restructured with session recovery as first instruction
+- Description updated to mention session recovery feature
+- README updated with session recovery workflow and instructions
+
+### Documentation
+
+- Added "Session Recovery" section to README
+- Documented optimal workflow for context window management
+- Instructions for disabling auto-compact in Claude Code settings
+
+### Thanks
+
+Special thanks to:
+- @lasmarois for session recovery implementation (PR #33)
+- Community members for testing and feedback
+
+---
+
 ## [2.2.0] - 2026-01-17

 ### Added
@@ -76,11 +181,6 @@ Special thanks to:
 - @mtuwei for reporting Windows compatibility issues (#32)
 - All community members who tested and provided feedback

-## [2.1.2] - 2026-01-11
-
-### Fixed
-
- **Template Files Not Found in Cache** (Fixes #18)
  - Root cause: `${CLAUDE_PLUGIN_ROOT}` resolves to repo root, but templates were only in subfolders
  - Added `templates/` and `scripts/` directories at repo root level
  - Now templates are accessible regardless of how `CLAUDE_PLUGIN_ROOT` resolves
@@ -25,6 +25,13 @@ These amazing people have contributed code, documentation, or significant improv
  - Created workflow diagram showing task lifecycle
  - **Impact:** Dramatically improved beginner onboarding

+- **[@lasmarois](https://github.com/lasmarois)** - [PR #33](https://github.com/OthmanAdi/planning-with-files/pull/33)
+  - Created session recovery feature for context preservation after `/clear`
+  - Built `session-catchup.py` script to analyze previous session JSONL files
+  - Enhanced PreToolUse hook to include Read/Glob/Grep operations
+  - Restructured SKILL.md for better session recovery workflow
+  - **Impact:** Solves context loss problem, enables seamless work resumption
+
 - **[@aimasteracc](https://github.com/aimasteracc)** - [PR #30](https://github.com/OthmanAdi/planning-with-files/pull/30)
  - Added Kilocode IDE support and documentation
  - Created PowerShell scripts for Windows compatibility
@@ -16,7 +16,7 @@ A Claude Code plugin that transforms your workflow to use persistent markdown fi
 [![Claude Code Plugin](https://img.shields.io/badge/Claude%20Code-Plugin-blue)](https://code.claude.com/docs/en/plugins)
 [![Claude Code Skill](https://img.shields.io/badge/Claude%20Code-Skill-green)](https://code.claude.com/docs/en/skills)
 [![Cursor Rules](https://img.shields.io/badge/Cursor-Rules-purple)](https://docs.cursor.com/context/rules-for-ai)
-[![Version](https://img.shields.io/badge/version-2.2.0-brightgreen)](https://github.com/OthmanAdi/planning-with-files/releases)
+[![Version](https://img.shields.io/badge/version-2.3.0-brightgreen)](https://github.com/OthmanAdi/planning-with-files/releases)

 ## Quick Install

@@ -27,6 +27,16 @@ A Claude Code plugin that transforms your workflow to use persistent markdown fi

 See [docs/installation.md](docs/installation.md) for all installation methods.

+## Supported IDEs
+
+| IDE | Status | Installation Guide | Format |
+|-----|--------|-------------------|--------|
+| Claude Code | ✅ Full Support | [Installation](docs/installation.md) | Plugin + SKILL.md |
+| Cursor | ✅ Full Support | [Cursor Setup](docs/cursor.md) | Rules |
+| Kilocode | ✅ Full Support | [Kilocode Setup](docs/kilocode.md) | Rules |
+| OpenCode | ✅ Full Support | [OpenCode Setup](docs/opencode.md) | Personal/Project Skill |
+| Codex | ✅ Full Support | [Codex Setup](docs/codex.md) | Personal Skill |
+
 ## Documentation

 | Document | Description |
@@ -38,15 +48,19 @@ See [docs/installation.md](docs/installation.md) for all installation methods.
 | [Cursor Setup](docs/cursor.md) | Cursor IDE-specific instructions |
 | [Windows Setup](docs/windows.md) | Windows-specific notes |
 | [Kilo Code Support](docs/kilocode.md) | Kilo Code integration guide |
+| [Codex Setup](docs/codex.md) | Codex IDE installation and usage |
+| [OpenCode Setup](docs/opencode.md) | OpenCode IDE installation, oh-my-opencode config |

 ## Versions

 | Version | Features | Install |
 |---------|----------|---------|
-| **v2.2.0** (current) | Kilo Code IDE support, Windows PowerShell support, OS-aware hooks | `/plugin install planning-with-files@planning-with-files` |
+| **v2.3.0** (current) | Codex & OpenCode IDE support | `/plugin install planning-with-files@planning-with-files` |
+| **v2.2.2** | Restored skill activation language | See [releases](https://github.com/OthmanAdi/planning-with-files/releases) |
+| **v2.2.1** | Session recovery after /clear, enhanced PreToolUse hook | See [releases](https://github.com/OthmanAdi/planning-with-files/releases) |
+| **v2.2.0** | Kilo Code IDE support, Windows PowerShell support, OS-aware hooks | See [releases](https://github.com/OthmanAdi/planning-with-files/releases) |
 | **v2.1.2** | Fix template cache issue (Issue #18) | See [releases](https://github.com/OthmanAdi/planning-with-files/releases) |
-| **v2.1.1** | Fix plugin template paths | See [releases](https://github.com/OthmanAdi/planning-with-files/releases) |
-| **v2.1.0** | Claude Code v2.1 compatible, SessionStart hook, PostToolUse hook, user-invocable | See [releases](https://github.com/OthmanAdi/planning-with-files/releases) |
+| **v2.1.0** | Claude Code v2.1 compatible, PostToolUse hook, user-invocable | See [releases](https://github.com/OthmanAdi/planning-with-files/releases) |
 | **v2.0.x** | Hooks, templates, scripts | See [releases](https://github.com/OthmanAdi/planning-with-files/releases) |
 | **v1.0.0** (legacy) | Core 3-file pattern | `git clone -b legacy` |

@@ -102,6 +116,45 @@ Or invoke manually with `/planning-with-files`.

 See [docs/quickstart.md](docs/quickstart.md) for the full 5-step guide.

+## Session Recovery (NEW in v2.2.0)
+
+When your context window fills up and you run `/clear`, this skill automatically recovers unsynced work from your previous session.
+
+### Optimal Workflow
+
+For the best experience, we recommend:
+
+1. **Disable auto-compact** in Claude Code settings (use full context window)
+2. **Start a fresh session** in your project
+3. **Run `/planning-with-files`** when ready to work on a complex task
+4. **Work until context fills up** (Claude will warn you)
+5. **Run `/clear`** to start fresh
+6. **Run `/planning-with-files`** again — it will automatically recover where you left off
+
+### How Recovery Works
+
+When you invoke `/planning-with-files`, the skill:
+
+1. Checks for previous session data (stored in `~/.claude/projects/`)
+2. Finds the last time planning files were updated
+3. Extracts conversation that happened after (potentially lost context)
+4. Shows a catchup report so you can sync planning files
+
+This means even if context filled up before you could update your planning files, the skill will recover that context in your next session.
+
+### Disabling Auto-Compact
+
+To use the full context window without automatic compaction:
+
+```bash
+# In your Claude Code settings or .claude/settings.json
+{
+  "autoCompact": false
+}
+```
+
+This lets you maximize context usage before manually clearing with `/clear`.
+
 ## Key Rules

 1. **Create Plan First** — Never start without `task_plan.md`
@@ -122,7 +175,9 @@ planning-with-files/
 │   ├── troubleshooting.md
 │   ├── cursor.md
 │   ├── windows.md
-│   └── kilocode.md
+│   ├── kilocode.md
+│   ├── codex.md
+│   └── opencode.md
 ├── planning-with-files/     # Plugin skill folder
 │   ├── SKILL.md
 │   ├── templates/
@@ -138,6 +193,10 @@ planning-with-files/
 │           ├── check-complete.sh
 │           ├── init-session.ps1   # Windows PowerShell
 │           └── check-complete.ps1 # Windows PowerShell
+├── .codex/                  # Codex IDE installation guide
+│   └── INSTALL.md
+├── .opencode/               # OpenCode IDE installation guide
+│   └── INSTALL.md
 ├── .claude-plugin/          # Plugin manifest
 ├── .cursor/                 # Cursor rules
 ├── .kilocode/               # Kilo Code rules
@@ -185,6 +244,7 @@ See [docs/kilocode.md](docs/kilocode.md) for detailed Kilo Code integration guid

 | Fork | Author | Features |
 |------|--------|----------|
+| [devis](https://github.com/st01cs/devis) | [@st01cs](https://github.com/st01cs) | Interview-first workflow, `/devis:intv` and `/devis:impl` commands, guaranteed activation |
 | [multi-manus-planning](https://github.com/kmichels/multi-manus-planning) | [@kmichels](https://github.com/kmichels) | Multi-project support, SessionStart git sync |

 *Built something? Open an issue to get listed!*
@@ -0,0 +1,52 @@
+# Codex IDE Support
+
+## Overview
+
+planning-with-files works with Codex as a personal skill in `~/.codex/skills/`.
+
+## Installation
+
+See [.codex/INSTALL.md](../.codex/INSTALL.md) for detailed installation instructions.
+
+### Quick Install
+
+```bash
+mkdir -p ~/.codex/skills
+cd ~/.codex/skills
+git clone https://github.com/OthmanAdi/planning-with-files.git
+```
+
+## Usage with Superpowers
+
+If you have [obra/superpowers](https://github.com/obra/superpowers) installed:
+
+```bash
+~/.codex/superpowers/.codex/superpowers-codex use-skill planning-with-files
+```
+
+## Usage without Superpowers
+
+Add to your `~/.codex/AGENTS.md`:
+
+```markdown
+## Planning with Files
+
+<IMPORTANT>
+For complex tasks (3+ steps, research, projects):
+1. Read skill: `cat ~/.codex/skills/planning-with-files/planning-with-files/SKILL.md`
+2. Create task_plan.md, findings.md, progress.md in your project directory
+3. Follow 3-file pattern throughout the task
+</IMPORTANT>
+```
+
+## Verification
+
+```bash
+ls -la ~/.codex/skills/planning-with-files/planning-with-files/SKILL.md
+```
+
+## Learn More
+
+- [Installation Guide](installation.md)
+- [Quick Start](quickstart.md)
+- [Workflow Diagram](workflow.md)
@@ -153,6 +153,14 @@ See [docs/windows.md](windows.md) for Windows-specific installation notes.

 See [docs/cursor.md](cursor.md) for Cursor IDE installation.

+### Codex
+
+See [docs/codex.md](codex.md) for Codex IDE installation.
+
+### OpenCode
+
+See [docs/opencode.md](opencode.md) for OpenCode IDE installation.
+
 ---

 ## Need Help?
@@ -0,0 +1,70 @@
+# OpenCode IDE Support
+
+## Overview
+
+planning-with-files works with OpenCode as a personal or project skill.
+
+## Installation
+
+See [.opencode/INSTALL.md](../.opencode/INSTALL.md) for detailed installation instructions.
+
+### Quick Install (Global)
+
+```bash
+mkdir -p ~/.config/opencode/skills
+cd ~/.config/opencode/skills
+git clone https://github.com/OthmanAdi/planning-with-files.git
+```
+
+### Quick Install (Project)
+
+```bash
+mkdir -p .opencode/skills
+cd .opencode/skills
+git clone https://github.com/OthmanAdi/planning-with-files.git
+```
+
+## Usage with Superpowers Plugin
+
+If you have [obra/superpowers](https://github.com/obra/superpowers) OpenCode plugin:
+
+```
+Use the use_skill tool with skill_name: "planning-with-files"
+```
+
+## Usage without Superpowers
+
+Manually read the skill file when starting complex tasks:
+
+```bash
+cat ~/.config/opencode/skills/planning-with-files/planning-with-files/SKILL.md
+```
+
+## oh-my-opencode Compatibility
+
+If using oh-my-opencode, ensure planning-with-files is not in the `disabled_skills` array:
+
+**~/.config/opencode/oh-my-opencode.json:**
+```json
+{
+  "disabled_skills": []
+}
+```
+
+## Verification
+
+**Global:**
+```bash
+ls -la ~/.config/opencode/skills/planning-with-files/planning-with-files/SKILL.md
+```
+
+**Project:**
+```bash
+ls -la .opencode/skills/planning-with-files/planning-with-files/SKILL.md
+```
+
+## Learn More
+
+- [Installation Guide](installation.md)
+- [Quick Start](quickstart.md)
+- [Workflow Diagram](workflow.md)
@@ -1,7 +1,7 @@
 ---
 name: planning-with-files
-version: "2.2.0"
-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.
+version: "2.3.0"
+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. Now with automatic session recovery after /clear.
 user-invocable: true
 allowed-tools:
  - Read
@@ -13,12 +13,8 @@ allowed-tools:
  - WebFetch
  - WebSearch
 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"
+    - matcher: "Write|Edit|Bash|Read|Glob|Grep"
      hooks:
        - type: command
          command: "cat task_plan.md 2>/dev/null | head -30 || true"
@@ -42,31 +38,41 @@ hooks:

 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:
+
+```bash
+python3 ${CLAUDE_PLUGIN_ROOT}/scripts/session-catchup.py "$(pwd)"
+```
+
+If catchup report shows unsynced context:
+1. Run `git diff --stat` to see actual code changes
+2. Read current planning files
+3. Update planning files based on catchup + git diff
+4. Then proceed with task
+
 ## Important: Where Files Go

-When using this skill:
-
- **Templates** are stored in the skill directory at `${CLAUDE_PLUGIN_ROOT}/templates/`
- **Your planning files** (`task_plan.md`, `findings.md`, `progress.md`) should be created in **your project directory** — the folder where you're working
+- **Templates** are in `${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` |

-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
+1. **Create `task_plan.md`** — Use [templates/task_plan.md](templates/task_plan.md) as reference
+2. **Create `findings.md`** — Use [templates/findings.md](templates/findings.md) as reference
+3. **Create `progress.md`** — 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.
+> **Note:** Planning files go in your project root, not the skill installation folder.

 ## The Core Pattern

@@ -197,6 +203,7 @@ Helper scripts for automation:

 - `scripts/init-session.sh` — Initialize all planning files
 - `scripts/check-complete.sh` — Verify all phases complete
+- `scripts/session-catchup.py` — Recover context from previous session (v2.2.0)

 ## Advanced Topics

@@ -0,0 +1,208 @@
+#!/usr/bin/env python3
+"""
+Session Catchup Script for planning-with-files
+
+Analyzes the previous session to find unsynced context after the last
+planning file update. Designed to run on SessionStart.
+
+Usage: python3 session-catchup.py [project-path]
+"""
+
+import json
+import sys
+import os
+from pathlib import Path
+from typing import List, Dict, Optional, Tuple
+from datetime import datetime
+
+PLANNING_FILES = ['task_plan.md', 'progress.md', 'findings.md']
+
+
+def get_project_dir(project_path: str) -> Path:
+    """Convert project path to Claude's storage path format."""
+    sanitized = project_path.replace('/', '-')
+    if not sanitized.startswith('-'):
+        sanitized = '-' + sanitized
+    sanitized = sanitized.replace('_', '-')
+    return Path.home() / '.claude' / 'projects' / sanitized
+
+
+def get_sessions_sorted(project_dir: Path) -> List[Path]:
+    """Get all session files sorted by modification time (newest first)."""
+    sessions = list(project_dir.glob('*.jsonl'))
+    main_sessions = [s for s in sessions if not s.name.startswith('agent-')]
+    return sorted(main_sessions, key=lambda p: p.stat().st_mtime, reverse=True)
+
+
+def parse_session_messages(session_file: Path) -> List[Dict]:
+    """Parse all messages from a session file, preserving order."""
+    messages = []
+    with open(session_file, 'r') as f:
+        for line_num, line in enumerate(f):
+            try:
+                data = json.loads(line)
+                data['_line_num'] = line_num
+                messages.append(data)
+            except json.JSONDecodeError:
+                pass
+    return messages
+
+
+def find_last_planning_update(messages: List[Dict]) -> Tuple[int, Optional[str]]:
+    """
+    Find the last time a planning file was written/edited.
+    Returns (line_number, filename) or (-1, None) if not found.
+    """
+    last_update_line = -1
+    last_update_file = None
+
+    for msg in messages:
+        msg_type = msg.get('type')
+
+        if msg_type == 'assistant':
+            content = msg.get('message', {}).get('content', [])
+            if isinstance(content, list):
+                for item in content:
+                    if item.get('type') == 'tool_use':
+                        tool_name = item.get('name', '')
+                        tool_input = item.get('input', {})
+
+                        if tool_name in ('Write', 'Edit'):
+                            file_path = tool_input.get('file_path', '')
+                            for pf in PLANNING_FILES:
+                                if file_path.endswith(pf):
+                                    last_update_line = msg['_line_num']
+                                    last_update_file = pf
+
+    return last_update_line, last_update_file
+
+
+def extract_messages_after(messages: List[Dict], after_line: int) -> List[Dict]:
+    """Extract conversation messages after a certain line number."""
+    result = []
+    for msg in messages:
+        if msg['_line_num'] <= after_line:
+            continue
+
+        msg_type = msg.get('type')
+        is_meta = msg.get('isMeta', False)
+
+        if msg_type == 'user' and not is_meta:
+            content = msg.get('message', {}).get('content', '')
+            if isinstance(content, list):
+                for item in content:
+                    if isinstance(item, dict) and item.get('type') == 'text':
+                        content = item.get('text', '')
+                        break
+                else:
+                    content = ''
+
+            if content and isinstance(content, str):
+                if content.startswith(('<local-command', '<command-', '<task-notification')):
+                    continue
+                if len(content) > 20:
+                    result.append({'role': 'user', 'content': content, 'line': msg['_line_num']})
+
+        elif msg_type == 'assistant':
+            msg_content = msg.get('message', {}).get('content', '')
+            text_content = ''
+            tool_uses = []
+
+            if isinstance(msg_content, str):
+                text_content = msg_content
+            elif isinstance(msg_content, list):
+                for item in msg_content:
+                    if item.get('type') == 'text':
+                        text_content = item.get('text', '')
+                    elif item.get('type') == 'tool_use':
+                        tool_name = item.get('name', '')
+                        tool_input = item.get('input', {})
+                        if tool_name == 'Edit':
+                            tool_uses.append(f"Edit: {tool_input.get('file_path', 'unknown')}")
+                        elif tool_name == 'Write':
+                            tool_uses.append(f"Write: {tool_input.get('file_path', 'unknown')}")
+                        elif tool_name == 'Bash':
+                            cmd = tool_input.get('command', '')[:80]
+                            tool_uses.append(f"Bash: {cmd}")
+                        else:
+                            tool_uses.append(f"{tool_name}")
+
+            if text_content or tool_uses:
+                result.append({
+                    'role': 'assistant',
+                    'content': text_content[:600] if text_content else '',
+                    'tools': tool_uses,
+                    'line': msg['_line_num']
+                })
+
+    return result
+
+
+def main():
+    project_path = sys.argv[1] if len(sys.argv) > 1 else os.getcwd()
+    project_dir = get_project_dir(project_path)
+
+    # Check if planning files exist (indicates active task)
+    has_planning_files = any(
+        Path(project_path, f).exists() for f in PLANNING_FILES
+    )
+
+    if not project_dir.exists():
+        # No previous sessions, nothing to catch up on
+        return
+
+    sessions = get_sessions_sorted(project_dir)
+    if len(sessions) < 1:
+        return
+
+    # Find a substantial previous session
+    target_session = None
+    for session in sessions:
+        if session.stat().st_size > 5000:
+            target_session = session
+            break
+
+    if not target_session:
+        return
+
+    messages = parse_session_messages(target_session)
+    last_update_line, last_update_file = find_last_planning_update(messages)
+
+    # Only output if there's unsynced content
+    if last_update_line < 0:
+        messages_after = extract_messages_after(messages, len(messages) - 30)
+    else:
+        messages_after = extract_messages_after(messages, last_update_line)
+
+    if not messages_after:
+        return
+
+    # Output catchup report
+    print("\n[planning-with-files] SESSION CATCHUP DETECTED")
+    print(f"Previous session: {target_session.stem}")
+
+    if last_update_line >= 0:
+        print(f"Last planning update: {last_update_file} at message #{last_update_line}")
+        print(f"Unsynced messages: {len(messages_after)}")
+    else:
+        print("No planning file updates found in previous session")
+
+    print("\n--- UNSYNCED CONTEXT ---")
+    for msg in messages_after[-15:]:  # Last 15 messages
+        if msg['role'] == 'user':
+            print(f"USER: {msg['content'][:300]}")
+        else:
+            if msg.get('content'):
+                print(f"CLAUDE: {msg['content'][:300]}")
+            if msg.get('tools'):
+                print(f"  Tools: {', '.join(msg['tools'][:4])}")
+
+    print("\n--- RECOMMENDED ---")
+    print("1. Run: git diff --stat")
+    print("2. Read: task_plan.md, progress.md, findings.md")
+    print("3. Update planning files based on above context")
+    print("4. Continue with task")
+
+
+if __name__ == '__main__':
+    main()
@@ -0,0 +1,208 @@
+#!/usr/bin/env python3
+"""
+Session Catchup Script for planning-with-files
+
+Analyzes the previous session to find unsynced context after the last
+planning file update. Designed to run on SessionStart.
+
+Usage: python3 session-catchup.py [project-path]
+"""
+
+import json
+import sys
+import os
+from pathlib import Path
+from typing import List, Dict, Optional, Tuple
+from datetime import datetime
+
+PLANNING_FILES = ['task_plan.md', 'progress.md', 'findings.md']
+
+
+def get_project_dir(project_path: str) -> Path:
+    """Convert project path to Claude's storage path format."""
+    sanitized = project_path.replace('/', '-')
+    if not sanitized.startswith('-'):
+        sanitized = '-' + sanitized
+    sanitized = sanitized.replace('_', '-')
+    return Path.home() / '.claude' / 'projects' / sanitized
+
+
+def get_sessions_sorted(project_dir: Path) -> List[Path]:
+    """Get all session files sorted by modification time (newest first)."""
+    sessions = list(project_dir.glob('*.jsonl'))
+    main_sessions = [s for s in sessions if not s.name.startswith('agent-')]
+    return sorted(main_sessions, key=lambda p: p.stat().st_mtime, reverse=True)
+
+
+def parse_session_messages(session_file: Path) -> List[Dict]:
+    """Parse all messages from a session file, preserving order."""
+    messages = []
+    with open(session_file, 'r') as f:
+        for line_num, line in enumerate(f):
+            try:
+                data = json.loads(line)
+                data['_line_num'] = line_num
+                messages.append(data)
+            except json.JSONDecodeError:
+                pass
+    return messages
+
+
+def find_last_planning_update(messages: List[Dict]) -> Tuple[int, Optional[str]]:
+    """
+    Find the last time a planning file was written/edited.
+    Returns (line_number, filename) or (-1, None) if not found.
+    """
+    last_update_line = -1
+    last_update_file = None
+
+    for msg in messages:
+        msg_type = msg.get('type')
+
+        if msg_type == 'assistant':
+            content = msg.get('message', {}).get('content', [])
+            if isinstance(content, list):
+                for item in content:
+                    if item.get('type') == 'tool_use':
+                        tool_name = item.get('name', '')
+                        tool_input = item.get('input', {})
+
+                        if tool_name in ('Write', 'Edit'):
+                            file_path = tool_input.get('file_path', '')
+                            for pf in PLANNING_FILES:
+                                if file_path.endswith(pf):
+                                    last_update_line = msg['_line_num']
+                                    last_update_file = pf
+
+    return last_update_line, last_update_file
+
+
+def extract_messages_after(messages: List[Dict], after_line: int) -> List[Dict]:
+    """Extract conversation messages after a certain line number."""
+    result = []
+    for msg in messages:
+        if msg['_line_num'] <= after_line:
+            continue
+
+        msg_type = msg.get('type')
+        is_meta = msg.get('isMeta', False)
+
+        if msg_type == 'user' and not is_meta:
+            content = msg.get('message', {}).get('content', '')
+            if isinstance(content, list):
+                for item in content:
+                    if isinstance(item, dict) and item.get('type') == 'text':
+                        content = item.get('text', '')
+                        break
+                else:
+                    content = ''
+
+            if content and isinstance(content, str):
+                if content.startswith(('<local-command', '<command-', '<task-notification')):
+                    continue
+                if len(content) > 20:
+                    result.append({'role': 'user', 'content': content, 'line': msg['_line_num']})
+
+        elif msg_type == 'assistant':
+            msg_content = msg.get('message', {}).get('content', '')
+            text_content = ''
+            tool_uses = []
+
+            if isinstance(msg_content, str):
+                text_content = msg_content
+            elif isinstance(msg_content, list):
+                for item in msg_content:
+                    if item.get('type') == 'text':
+                        text_content = item.get('text', '')
+                    elif item.get('type') == 'tool_use':
+                        tool_name = item.get('name', '')
+                        tool_input = item.get('input', {})
+                        if tool_name == 'Edit':
+                            tool_uses.append(f"Edit: {tool_input.get('file_path', 'unknown')}")
+                        elif tool_name == 'Write':
+                            tool_uses.append(f"Write: {tool_input.get('file_path', 'unknown')}")
+                        elif tool_name == 'Bash':
+                            cmd = tool_input.get('command', '')[:80]
+                            tool_uses.append(f"Bash: {cmd}")
+                        else:
+                            tool_uses.append(f"{tool_name}")
+
+            if text_content or tool_uses:
+                result.append({
+                    'role': 'assistant',
+                    'content': text_content[:600] if text_content else '',
+                    'tools': tool_uses,
+                    'line': msg['_line_num']
+                })
+
+    return result
+
+
+def main():
+    project_path = sys.argv[1] if len(sys.argv) > 1 else os.getcwd()
+    project_dir = get_project_dir(project_path)
+
+    # Check if planning files exist (indicates active task)
+    has_planning_files = any(
+        Path(project_path, f).exists() for f in PLANNING_FILES
+    )
+
+    if not project_dir.exists():
+        # No previous sessions, nothing to catch up on
+        return
+
+    sessions = get_sessions_sorted(project_dir)
+    if len(sessions) < 1:
+        return
+
+    # Find a substantial previous session
+    target_session = None
+    for session in sessions:
+        if session.stat().st_size > 5000:
+            target_session = session
+            break
+
+    if not target_session:
+        return
+
+    messages = parse_session_messages(target_session)
+    last_update_line, last_update_file = find_last_planning_update(messages)
+
+    # Only output if there's unsynced content
+    if last_update_line < 0:
+        messages_after = extract_messages_after(messages, len(messages) - 30)
+    else:
+        messages_after = extract_messages_after(messages, last_update_line)
+
+    if not messages_after:
+        return
+
+    # Output catchup report
+    print("\n[planning-with-files] SESSION CATCHUP DETECTED")
+    print(f"Previous session: {target_session.stem}")
+
+    if last_update_line >= 0:
+        print(f"Last planning update: {last_update_file} at message #{last_update_line}")
+        print(f"Unsynced messages: {len(messages_after)}")
+    else:
+        print("No planning file updates found in previous session")
+
+    print("\n--- UNSYNCED CONTEXT ---")
+    for msg in messages_after[-15:]:  # Last 15 messages
+        if msg['role'] == 'user':
+            print(f"USER: {msg['content'][:300]}")
+        else:
+            if msg.get('content'):
+                print(f"CLAUDE: {msg['content'][:300]}")
+            if msg.get('tools'):
+                print(f"  Tools: {', '.join(msg['tools'][:4])}")
+
+    print("\n--- RECOMMENDED ---")
+    print("1. Run: git diff --stat")
+    print("2. Read: task_plan.md, progress.md, findings.md")
+    print("3. Update planning files based on above context")
+    print("4. Continue with task")
+
+
+if __name__ == '__main__':
+    main()
@@ -1,7 +1,7 @@
 ---
 name: planning-with-files
-version: "2.2.0"
-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.
+version: "2.3.0"
+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. Now with automatic session recovery after /clear.
 user-invocable: true
 allowed-tools:
  - Read
@@ -13,12 +13,8 @@ allowed-tools:
  - WebFetch
  - WebSearch
 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"
+    - matcher: "Write|Edit|Bash|Read|Glob|Grep"
      hooks:
        - type: command
          command: "cat task_plan.md 2>/dev/null | head -30 || true"
@@ -42,31 +38,41 @@ hooks:

 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:
+
+```bash
+python3 ${CLAUDE_PLUGIN_ROOT}/scripts/session-catchup.py "$(pwd)"
+```
+
+If catchup report shows unsynced context:
+1. Run `git diff --stat` to see actual code changes
+2. Read current planning files
+3. Update planning files based on catchup + git diff
+4. Then proceed with task
+
 ## Important: Where Files Go

-When using this skill:
-
- **Templates** are stored in the skill directory at `${CLAUDE_PLUGIN_ROOT}/templates/`
- **Your planning files** (`task_plan.md`, `findings.md`, `progress.md`) should be created in **your project directory** — the folder where you're working
+- **Templates** are in `${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` |

-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
+1. **Create `task_plan.md`** — Use [templates/task_plan.md](templates/task_plan.md) as reference
+2. **Create `findings.md`** — Use [templates/findings.md](templates/findings.md) as reference
+3. **Create `progress.md`** — 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.
+> **Note:** Planning files go in your project root, not the skill installation folder.

 ## The Core Pattern

@@ -197,6 +203,7 @@ Helper scripts for automation:

 - `scripts/init-session.sh` — Initialize all planning files
 - `scripts/check-complete.sh` — Verify all phases complete
+- `scripts/session-catchup.py` — Recover context from previous session (v2.2.0)

 ## Advanced Topics

@@ -0,0 +1,208 @@
+#!/usr/bin/env python3
+"""
+Session Catchup Script for planning-with-files
+
+Analyzes the previous session to find unsynced context after the last
+planning file update. Designed to run on SessionStart.
+
+Usage: python3 session-catchup.py [project-path]
+"""
+
+import json
+import sys
+import os
+from pathlib import Path
+from typing import List, Dict, Optional, Tuple
+from datetime import datetime
+
+PLANNING_FILES = ['task_plan.md', 'progress.md', 'findings.md']
+
+
+def get_project_dir(project_path: str) -> Path:
+    """Convert project path to Claude's storage path format."""
+    sanitized = project_path.replace('/', '-')
+    if not sanitized.startswith('-'):
+        sanitized = '-' + sanitized
+    sanitized = sanitized.replace('_', '-')
+    return Path.home() / '.claude' / 'projects' / sanitized
+
+
+def get_sessions_sorted(project_dir: Path) -> List[Path]:
+    """Get all session files sorted by modification time (newest first)."""
+    sessions = list(project_dir.glob('*.jsonl'))
+    main_sessions = [s for s in sessions if not s.name.startswith('agent-')]
+    return sorted(main_sessions, key=lambda p: p.stat().st_mtime, reverse=True)
+
+
+def parse_session_messages(session_file: Path) -> List[Dict]:
+    """Parse all messages from a session file, preserving order."""
+    messages = []
+    with open(session_file, 'r') as f:
+        for line_num, line in enumerate(f):
+            try:
+                data = json.loads(line)
+                data['_line_num'] = line_num
+                messages.append(data)
+            except json.JSONDecodeError:
+                pass
+    return messages
+
+
+def find_last_planning_update(messages: List[Dict]) -> Tuple[int, Optional[str]]:
+    """
+    Find the last time a planning file was written/edited.
+    Returns (line_number, filename) or (-1, None) if not found.
+    """
+    last_update_line = -1
+    last_update_file = None
+
+    for msg in messages:
+        msg_type = msg.get('type')
+
+        if msg_type == 'assistant':
+            content = msg.get('message', {}).get('content', [])
+            if isinstance(content, list):
+                for item in content:
+                    if item.get('type') == 'tool_use':
+                        tool_name = item.get('name', '')
+                        tool_input = item.get('input', {})
+
+                        if tool_name in ('Write', 'Edit'):
+                            file_path = tool_input.get('file_path', '')
+                            for pf in PLANNING_FILES:
+                                if file_path.endswith(pf):
+                                    last_update_line = msg['_line_num']
+                                    last_update_file = pf
+
+    return last_update_line, last_update_file
+
+
+def extract_messages_after(messages: List[Dict], after_line: int) -> List[Dict]:
+    """Extract conversation messages after a certain line number."""
+    result = []
+    for msg in messages:
+        if msg['_line_num'] <= after_line:
+            continue
+
+        msg_type = msg.get('type')
+        is_meta = msg.get('isMeta', False)
+
+        if msg_type == 'user' and not is_meta:
+            content = msg.get('message', {}).get('content', '')
+            if isinstance(content, list):
+                for item in content:
+                    if isinstance(item, dict) and item.get('type') == 'text':
+                        content = item.get('text', '')
+                        break
+                else:
+                    content = ''
+
+            if content and isinstance(content, str):
+                if content.startswith(('<local-command', '<command-', '<task-notification')):
+                    continue
+                if len(content) > 20:
+                    result.append({'role': 'user', 'content': content, 'line': msg['_line_num']})
+
+        elif msg_type == 'assistant':
+            msg_content = msg.get('message', {}).get('content', '')
+            text_content = ''
+            tool_uses = []
+
+            if isinstance(msg_content, str):
+                text_content = msg_content
+            elif isinstance(msg_content, list):
+                for item in msg_content:
+                    if item.get('type') == 'text':
+                        text_content = item.get('text', '')
+                    elif item.get('type') == 'tool_use':
+                        tool_name = item.get('name', '')
+                        tool_input = item.get('input', {})
+                        if tool_name == 'Edit':
+                            tool_uses.append(f"Edit: {tool_input.get('file_path', 'unknown')}")
+                        elif tool_name == 'Write':
+                            tool_uses.append(f"Write: {tool_input.get('file_path', 'unknown')}")
+                        elif tool_name == 'Bash':
+                            cmd = tool_input.get('command', '')[:80]
+                            tool_uses.append(f"Bash: {cmd}")
+                        else:
+                            tool_uses.append(f"{tool_name}")
+
+            if text_content or tool_uses:
+                result.append({
+                    'role': 'assistant',
+                    'content': text_content[:600] if text_content else '',
+                    'tools': tool_uses,
+                    'line': msg['_line_num']
+                })
+
+    return result
+
+
+def main():
+    project_path = sys.argv[1] if len(sys.argv) > 1 else os.getcwd()
+    project_dir = get_project_dir(project_path)
+
+    # Check if planning files exist (indicates active task)
+    has_planning_files = any(
+        Path(project_path, f).exists() for f in PLANNING_FILES
+    )
+
+    if not project_dir.exists():
+        # No previous sessions, nothing to catch up on
+        return
+
+    sessions = get_sessions_sorted(project_dir)
+    if len(sessions) < 1:
+        return
+
+    # Find a substantial previous session
+    target_session = None
+    for session in sessions:
+        if session.stat().st_size > 5000:
+            target_session = session
+            break
+
+    if not target_session:
+        return
+
+    messages = parse_session_messages(target_session)
+    last_update_line, last_update_file = find_last_planning_update(messages)
+
+    # Only output if there's unsynced content
+    if last_update_line < 0:
+        messages_after = extract_messages_after(messages, len(messages) - 30)
+    else:
+        messages_after = extract_messages_after(messages, last_update_line)
+
+    if not messages_after:
+        return
+
+    # Output catchup report
+    print("\n[planning-with-files] SESSION CATCHUP DETECTED")
+    print(f"Previous session: {target_session.stem}")
+
+    if last_update_line >= 0:
+        print(f"Last planning update: {last_update_file} at message #{last_update_line}")
+        print(f"Unsynced messages: {len(messages_after)}")
+    else:
+        print("No planning file updates found in previous session")
+
+    print("\n--- UNSYNCED CONTEXT ---")
+    for msg in messages_after[-15:]:  # Last 15 messages
+        if msg['role'] == 'user':
+            print(f"USER: {msg['content'][:300]}")
+        else:
+            if msg.get('content'):
+                print(f"CLAUDE: {msg['content'][:300]}")
+            if msg.get('tools'):
+                print(f"  Tools: {', '.join(msg['tools'][:4])}")
+
+    print("\n--- RECOMMENDED ---")
+    print("1. Run: git diff --stat")
+    print("2. Read: task_plan.md, progress.md, findings.md")
+    print("3. Update planning files based on above context")
+    print("4. Continue with task")
+
+
+if __name__ == '__main__':
+    main()
Author	SHA1	Message	Date
OthmanAdiandClaude Sonnet 4.5	c84f56574e	Release v2.3.0 - Multi-IDE support (Codex + OpenCode) - Version bump to 2.3.0 - Updated CHANGELOG with new features - Updated SKILL.md version fields New features: - Codex IDE support via personal skills - OpenCode IDE support via personal/project skills - oh-my-opencode compatibility - Based on real analysis of obra/superpowers Closes #27 Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>	2026-01-17 22:55:23 +01:00
OthmanAdiandClaude Sonnet 4.5	4f2586691a	Update documentation for Codex and OpenCode support - Added Codex and OpenCode to IDE support table - Updated file structure diagram - Added documentation links - Updated installation guide with new IDE sections Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>	2026-01-17 22:55:19 +01:00
OthmanAdiandClaude Sonnet 4.5	1844bbb90f	Add OpenCode IDE support with real installation guide - Created .opencode/INSTALL.md with installation instructions - Global: ~/.config/opencode/skills/planning-with-files/ - Project: .opencode/skills/planning-with-files/ - Works with obra/superpowers plugin or standalone - oh-my-opencode compatibility documented - Added docs/opencode.md for user documentation Based on analysis of obra/superpowers OpenCode plugin Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>	2026-01-17 22:55:14 +01:00
OthmanAdiandClaude Sonnet 4.5	ab10960a4b	Add Codex IDE support with real installation guide - Created .codex/INSTALL.md with installation instructions - Skills install to ~/.codex/skills/planning-with-files/ - Works with obra/superpowers or standalone - Added docs/codex.md for user documentation Based on analysis of obra/superpowers Codex implementation Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>	2026-01-17 22:55:09 +01:00
OthmanAdiandClaude Sonnet 4.5	8ee4328ef8	Hotfix: Restore skill activation language lost in v2.2.1 merge - Restore full description in SKILL.md files - Description now includes activation context - Fixes issue where skill purpose was unclear Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>	2026-01-17 22:44:18 +01:00
OthmanAdi	ce59730881	Release v2.2.1: Session recovery after /clear Merging feature/session-catchup-recovery from @lasmarois (PR #33) This fast-follow release adds automatic session recovery for seamless work continuation after running /clear when context fills up. New Features: - Session recovery via session-catchup.py script - Analyzes previous session JSONL files in ~/.claude/projects/ - Finds last planning file update - Extracts unsynced conversation after that point - Automatic recovery when invoking /planning-with-files Enhanced Hooks: - PreToolUse now includes Read/Glob/Grep operations - Keeps task_plan.md in attention during research phases - Better context management throughout workflow Files Added: - scripts/session-catchup.py (all 3 locations) - Session recovery instructions in SKILL.md - README session recovery documentation Version Updates: - Version bumped to 2.2.1 in all manifests - Updated CHANGELOG.md with v2.2.1 release notes - Added @lasmarois to CONTRIBUTORS.md Conflicts resolved: - CHANGELOG: Combined v2.2.1 and v2.2.0 entries - README: Added session recovery to v2.2.1, kept v2.2.0 features - SKILL.md: Merged session recovery with existing hooks Contributors: - @lasmarois (session recovery implementation) - Ahmad Othman Ammar Adi (conflict resolution, version management)	2026-01-17 21:49:15 +01:00
OthmanAdi	74d37d96ff	Add devis to Community Forks section Recognition of @st01cs's devis project which adds: - Interview-first workflow before implementation - /devis:intv and /devis:impl commands for guaranteed activation - Extends planning-with-files with structured requirement gathering This addresses the community contribution mentioned in issue #28.	2026-01-17 21:44:20 +01:00
nicolasandClaude Opus 4.5	69ded714b7	feat: Add session recovery after /clear (v2.2.0) Automatically detect and recover unsynced work from previous sessions when context fills up and user runs /clear. New features: - session-catchup.py: Analyzes previous session JSONL to find unsynced context - Recovery triggered automatically when invoking /planning-with-files - PreToolUse hook now includes Read/Glob/Grep for better attention management Optimal workflow: 1. Disable auto-compact in Claude Code settings 2. Start fresh session 3. Run /planning-with-files when ready for complex task 4. Work until context fills up 5. Run /clear 6. Run /planning-with-files again — automatically recovers where you left off How recovery works: - SKILL.md instructs Claude to first run session-catchup.py - Script checks ~/.claude/projects/ for previous session JSONL - Finds last planning file update, extracts conversation after that point - Claude updates planning files based on catchup + git diff Changes: - SKILL.md: Added session recovery section, preserved all original content - README: Added optimal workflow and setup instructions - Removed SessionStart hook (doesn't work per Issue #24) - Version bumped to 2.2.0 Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2026-01-17 15:28:08 -05:00