/ghost-decode
Decode a ghost-font video and reveal the hidden text
> /plugin marketplace add haroontrailblazer/ghost-font-decoder > /plugin install ghost-font-decoder@ghost-font-tools
How it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/ghost-decode
Context preview
What this command does when you run it.
Decode a ghost-font video and reveal the hidden text
Command definition
ghost-decode.mddescription: Decode a ghost-font video and reveal the hidden text
argument-hint: [video-path]
Immediately decode a ghost-font video (text hidden in moving dots / noise) by running the bundled decoder. Do the work now — do NOT ask the user to set up a folder, install the plugin differently, or point at files beyond the video path.
Target video: $ARGUMENTS
If `$ARGUMENTS` is empty, use the most recently modified `.mp4`, `.mov`, `.avi`, or `.webm` file in the current directory. Only ask the user if there is more than one plausible candidate.
Then, without further prompting:
1. Check deps: `python -c "import cv2, numpy"`. If it fails, run `pip install -r "${CLAUDE_PLUGIN_ROOT}/requirements.txt"`. 2. Run the decoder (it writes `revealed.png` and `revealed_heatmap.png`):
python "${CLAUDE_PLUGIN_ROOT}/decode.py" "<video-path>" -o "<scratch-out-dir>"`${CLAUDE_PLUGIN_ROOT}` is the plugin's install directory. On Windows PowerShell it is `$env:CLAUDE_PLUGIN_ROOT`; if it expands empty, substitute the install path literally. 3. Read `revealed.png` with vision to confirm the text (the heatmap `revealed_heatmap.png` shows faint detail the clean mask may drop). 4. Reply with the recovered text on its own line, plus the output image paths:
Text in the video: **<DECODED TEXT>**
Never OCR a raw frame — every frame is uniform noise; the message is only in the motion. Do not claim success unless the decoder actually ran and you inspected `revealed.png`.
Read more
description: Decode a ghost-font video and reveal the hidden text argument-hint: [video-path]
Immediately decode a ghost-font video (text hidden in moving dots / noise) by running the bundled decoder. Do the work now — do NOT ask the user to set up a folder, install the plugin differently, or point at files beyond the video path.
Target video: $ARGUMENTS
If `$ARGUMENTS` is empty, use the most recently modified `.mp4`, `.mov`, `.avi`, or `.webm` file in the current directory. Only ask the user if there is more than one plausible candidate.
Then, without further prompting:
1. Check deps: `python -c "import cv2, numpy"`. If it fails, run `pip install -r "${CLAUDE_PLUGIN_ROOT}/requirements.txt"`. 2. Run the decoder (it writes `revealed.png` and `revealed_heatmap.png`):
python "${CLAUDE_PLUGIN_ROOT}/decode.py" "<video-path>" -o "<scratch-out-dir>"`${CLAUDE_PLUGIN_ROOT}` is the plugin's install directory. On Windows PowerShell it is `$env:CLAUDE_PLUGIN_ROOT`; if it expands empty, substitute the install path literally. 3. Read `revealed.png` with vision to confirm the text (the heatmap `revealed_heatmap.png` shows faint detail the clean mask may drop). 4. Reply with the recovered text on its own line, plus the output image paths:
Text in the video: **<DECODED TEXT>**
Never OCR a raw frame — every frame is uniform noise; the message is only in the motion. Do not claim success unless the decoder actually ran and you inspected `revealed.png`.
Give AI agents motion vision, decode hidden messages inside random-dot “ghost font” videos.
Repo: haroontrailblazer/ghost-font-decoder