Add a Codex migration flow for toolkit skills and commands

.claude/commands/generate-voiceover.md

@@ -154,34 +154,34 @@ Before gathering configuration, check if we're in a project context:
 
    **ElevenLabs — Per-scene mode (recommended):**
    ```bash
-   cd PROJECT_DIR
-   python /Users/conalmullan/work/video/tools/voiceover.py \
+   cd REPO_ROOT/PROJECT_DIR
+   python ../tools/voiceover.py \
      --scene-dir public/audio/scenes \
      --json
    ```
 
    **ElevenLabs — With concat for SadTalker:**
    ```bash
-   cd PROJECT_DIR
-   python /Users/conalmullan/work/video/tools/voiceover.py \
+   cd REPO_ROOT/PROJECT_DIR
+   python ../tools/voiceover.py \
      --scene-dir public/audio/scenes \
      --concat public/audio/voiceover-concat.mp3 \
      --json
    ```
 
    **ElevenLabs — Single-file mode (legacy):**
    ```bash
-   cd PROJECT_DIR
-   python /Users/conalmullan/work/video/tools/voiceover.py \
+   cd REPO_ROOT/PROJECT_DIR
+   python ../tools/voiceover.py \
      --script "SCRIPT_PATH" \
      --output "public/audio/voiceover.mp3" \
      --json
    ```
 
    **Qwen3-TTS — Per-scene mode:**
    ```bash
-   cd PROJECT_DIR
-   python /Users/conalmullan/work/video/tools/voiceover.py \
+   cd REPO_ROOT/PROJECT_DIR
+   python ../tools/voiceover.py \
      --provider qwen3 \
      --speaker SPEAKER_NAME \
      --scene-dir public/audio/scenes \
@@ -190,8 +190,8 @@ Before gathering configuration, check if we're in a project context:
 
    **Qwen3-TTS — With brand clone profile:**
    ```bash
-   cd PROJECT_DIR
-   python /Users/conalmullan/work/video/tools/voiceover.py \
+   cd REPO_ROOT/PROJECT_DIR
+   python ../tools/voiceover.py \
      --provider qwen3 \
      --brand BRAND_NAME \
      --scene-dir public/audio/scenes \
@@ -200,8 +200,8 @@ Before gathering configuration, check if we're in a project context:
 
    **Qwen3-TTS — With tone preset:**
    ```bash
-   cd PROJECT_DIR
-   python /Users/conalmullan/work/video/tools/voiceover.py \
+   cd REPO_ROOT/PROJECT_DIR
+   python ../tools/voiceover.py \
      --provider qwen3 \
      --speaker Ryan \
      --tone warm \
@@ -211,8 +211,8 @@ Before gathering configuration, check if we're in a project context:
 
    **Qwen3-TTS — With custom instruction (overrides --tone):**
    ```bash
-   cd PROJECT_DIR
-   python /Users/conalmullan/work/video/tools/voiceover.py \
+   cd REPO_ROOT/PROJECT_DIR
+   python ../tools/voiceover.py \
      --provider qwen3 \
      --speaker Ryan \
      --instruct "Speak warmly and calmly" \
@@ -222,8 +222,8 @@ Before gathering configuration, check if we're in a project context:
 
    **Qwen3-TTS — Single-file mode:**
    ```bash
-   cd PROJECT_DIR
-   python /Users/conalmullan/work/video/tools/voiceover.py \
+   cd REPO_ROOT/PROJECT_DIR
+   python ../tools/voiceover.py \
      --provider qwen3 \
      --speaker Ryan \
      --script "SCRIPT_PATH" \
@@ -264,8 +264,8 @@ Before gathering configuration, check if we're in a project context:
 
 ## Tool Location
 
-- Voiceover tool: `/Users/conalmullan/work/video/tools/voiceover.py`
-- Qwen3-TTS tool: `/Users/conalmullan/work/video/tools/qwen3_tts.py`
+- Voiceover tool: `tools/voiceover.py` (run from the toolkit root, or use `../tools/voiceover.py` from a project directory)
+- Qwen3-TTS tool: `tools/qwen3_tts.py`
 - Config: `_internal/toolkit-registry.json` (voice ID)
 - API Key: `.env` file (`ELEVENLABS_API_KEY` for ElevenLabs, `RUNPOD_API_KEY` + `RUNPOD_QWEN3_TTS_ENDPOINT_ID` for Qwen3)
 

.claude/commands/record-demo.md

@@ -76,7 +76,7 @@ Before gathering configuration, check if we're in a project context:
    **For Interactive Mode:**
    Run the interactive recording script:
    ```bash
-   cd /Users/conalmullan/work/video/playwright
+   cd REPO_ROOT/playwright
    npx tsx scripts/record-interactive.ts \
      --url "USER_URL" \
      --name "USER_NAME" \
@@ -106,9 +106,9 @@ Before gathering configuration, check if we're in a project context:
 
 ## Script Locations
 
-- Interactive script: `/Users/conalmullan/work/video/playwright/scripts/record-interactive.ts`
-- Flow templates: `/Users/conalmullan/work/video/playwright/scripts/flows/`
-- Output (default): `/Users/conalmullan/work/video/playwright/output/`
+- Interactive script: `playwright/scripts/record-interactive.ts`
+- Flow templates: `playwright/scripts/flows/`
+- Output (default): `playwright/output/`
 
 ## Viewport Presets
 

CONTRIBUTING.md

@@ -75,6 +75,14 @@ When adding or modifying commands, skills, or templates, update these files:
 | New component | `CLAUDE.md` (Shared Components table) |
 | New transition | `README.md` (Scene Transitions), `lib/transitions/README.md` |
 
+If your change affects Codex compatibility, also update:
+
+| What Changed | Update These Files |
+|--------------|-------------------|
+| Codex migration flow | `README.md` ("Using with Codex"), `docs/getting-started.md`, `scripts/migrate_to_codex.py` |
+| Claude guidance source | `CLAUDE.md` and then re-run `python3 scripts/migrate_to_codex.py --force` to regenerate the Codex block in `AGENTS.md` |
+| Generated resource list or warnings | `README.md` and `docs/getting-started.md` |
+
 **Quick verification:** After adding a command, grep for it across docs:
 ```bash
 grep -r "/your-command" README.md CLAUDE.md

README.md

@@ -26,6 +26,62 @@ Then in Claude Code:
 
 **That's it.** `/setup` walks you through everything interactively — cloud GPU provider, file transfer, voice config. `/video` creates a project from a template and guides you through the whole workflow.
 
+## Using with Codex
+
+This toolkit is built around Claude Code assets in `.claude/` and `CLAUDE.md`, but it also ships an experimental migration script for Codex.
+
+```bash
+python3 scripts/migrate_to_codex.py --force
+```
+
+This does two things:
+
+1. Installs Codex skills into `~/.codex/skills`
+2. Appends or updates a generated Codex block in the repository root `AGENTS.md` from `CLAUDE.md`
+
+Resources created or updated by `python3 scripts/migrate_to_codex.py --force`:
+
+1. `~/.codex/skills/acestep/`
+2. `~/.codex/skills/elevenlabs/`
+3. `~/.codex/skills/ffmpeg/`
+4. `~/.codex/skills/frontend-design/`
+5. `~/.codex/skills/ltx2/`
+6. `~/.codex/skills/moviepy/`
+7. `~/.codex/skills/playwright-recording/`
+8. `~/.codex/skills/qwen-edit/`
+9. `~/.codex/skills/remotion/`
+10. `~/.codex/skills/remotion-best-practices/`
+11. `~/.codex/skills/runpod/`
+12. `~/.codex/skills/brand/`
+13. `~/.codex/skills/contribute/`
+14. `~/.codex/skills/design/`
+15. `~/.codex/skills/generate-voiceover/`
+16. `~/.codex/skills/record-demo/`
+17. `~/.codex/skills/redub/`
+18. `~/.codex/skills/scene-review/`
+19. `~/.codex/skills/setup/`
+20. `~/.codex/skills/skills/`
+21. `~/.codex/skills/template/`
+22. `~/.codex/skills/versions/`
+23. `~/.codex/skills/video/`
+24. `~/.codex/skills/video-toolkit/`
+25. `~/.codex/skills/voice-clone/`
+26. A generated Codex block inside `AGENTS.md` in the repository root
+
+Important:
+
+1. The migration script manages only a generated block inside the repository root `AGENTS.md`.
+2. Manual `AGENTS.md` content outside that block is preserved.
+3. The generated block is derived from `CLAUDE.md`, so changes to `CLAUDE.md` should be followed by `python3 scripts/migrate_to_codex.py --force`.
+
+To remove the installed Codex skills later:
+
+```bash
+python3 scripts/migrate_to_codex.py --reset
+```
+
+`--reset` removes the toolkit skills previously installed under `~/.codex/skills` and removes the generated Codex block from `AGENTS.md`. It does not delete other user skills and it does not remove the rest of `AGENTS.md`.
+
 **What's free:** The toolkit leans heavily on open-source AI models — voiceovers (Qwen3-TTS), image generation (FLUX.2), music (ACE-Step), and more. You deploy them to your own cloud GPU account and run them at cost. Cloudflare R2 has a generous free tier (10GB, zero egress), and Modal gives $30/month free compute on the Starter plan — more than enough for a few 5-minute videos a month.
 
 **Requirements:** [Node.js](https://nodejs.org/) 18+ and [Claude Code](https://docs.anthropic.com/en/docs/claude-code). Python 3.9+ recommended for AI tools. FFmpeg optional.

codex/migration_map.json

@@ -0,0 +1,8 @@
+{
+  "skip_commands": [],
+  "skip_skills": [
+    "openclaw-video-toolkit"
+  ],
+  "command_name_overrides": {},
+  "skill_name_overrides": {}
+}

docs/getting-started.md

@@ -61,6 +61,37 @@ No API keys needed. Edit `src/config/sprint-config.ts` to customize content.
 
    Or configure manually: `cp .env.example .env` and edit with your API keys.
 
+## Optional: Codex Setup
+
+If you use Codex instead of Claude Code, install the toolkit's Codex-compatible wrappers and regenerate `AGENTS.md` from `CLAUDE.md`:
+
+```bash
+python3 scripts/migrate_to_codex.py --force
+```
+
+This installs toolkit skills into `~/.codex/skills` and appends or updates a generated Codex block in the repository root `AGENTS.md`.
+
+Resources created or updated by the migration script:
+
+1. Toolkit skills under `~/.codex/skills/`
+2. Command-wrapper skills under `~/.codex/skills/`
+3. A generated Codex block inside repository root `AGENTS.md`
+
+Important:
+
+1. The script manages only a generated block inside the repository root `AGENTS.md`.
+2. Manual `AGENTS.md` content outside that block is preserved.
+3. The generated block is derived from `CLAUDE.md`.
+4. Re-run `python3 scripts/migrate_to_codex.py --force` after updating `CLAUDE.md`.
+
+To remove the installed toolkit skills later:
+
+```bash
+python3 scripts/migrate_to_codex.py --reset
+```
+
+`--reset` removes the generated Codex block from `AGENTS.md`, but does not remove the rest of the file.
+
 ## Your First Video
 
 The easiest way to create a video is using the `/video` command:

docs/qwen-edit-patterns.md

@@ -153,8 +153,8 @@ python tools/test_qwen_edit.py --image photo.jpg --prompt "description" --seed 4
 
 ## Files Created
 
-```
-/Users/conalmullan/work/video/
+```text
+<toolkit-root>/
 ├── conor_bond.png
 ├── conor_neo.png
 ├── conor_wick.png