This skill covers the grepai watch command and daemon management for real-time code indexing.
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versiongrepai-watch-daemonExecute the skills CLI command in your project's root directory to begin installation:
Fetches grepai-watch-daemon from yoanbernabeu/grepai-skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate grepai-watch-daemon. Access via /grepai-watch-daemon in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Automate repetitive workflows and reduce manual effort
Example
Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example
Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example
Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
0
total installs
0
this week
16
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
16
stars
This skill covers the grepai watch command and daemon management for real-time code indexing.
The watch daemon:
cd /your/project
grepai watch
Output:
🔍 GrepAI Watch
Scanning files...
Found 245 files
Processing chunks...
████████████████████████████████ 100%
Indexed 1,234 chunks
Watching for changes...
Press Ctrl+C to stop.
grepai watch --background
Output:
🔍 GrepAI Watch (background)
Daemon started with PID 12345
Log file: ~/.grepai/daemon.log
grepai watch --status
Output:
✅ GrepAI Daemon Running
PID: 12345
Started: 2025-01-28 10:30:00
Project: /path/to/project
Statistics:
- Files indexed: 245
- Chunks: 1,234
- Last update: 2 minutes ago
grepai watch --stop
Output:
✅ Daemon stopped (PID 12345)
| Command | Description |
|---|---|
grepai watch |
Start daemon in foreground |
grepai watch --background |
Start daemon in background |
grepai watch --status |
Check daemon status |
grepai watch --stop |
Stop running daemon |
# .grepai/config.yaml
watch:
# Debounce delay in milliseconds
# Groups rapid file changes together
debounce_ms: 500
When you save a file, editors often write multiple times quickly. Debouncing waits for changes to settle:
| Value | Behavior |
|---|---|
100 |
More responsive, more reindexing |
500 |
Balanced (default) |
1000 |
Less responsive, fewer reindexing |
The daemon indexes files:
.gitignoreLarge codebases show progress:
Scanning files...
Found 10,245 files
Processing chunks...
████████████████░░░░░░░░░░░░░░░░ 50% (5,122/10,245)
| Codebase | Files | Time (Ollama) | Time (OpenAI) |
|---|---|---|---|
| Small | 100 | ~30s | ~10s |
| Medium | 1,000 | ~5min | ~1min |
| Large | 10,000 | ~30min | ~5min |
After initial indexing, the daemon watches for:
Uses OS-native file watching:
| Action | Result |
|---|---|
| Save existing file | Re-embed file chunks |
| Create new file | Index new chunks |
| Delete file | Remove from index |
| Rename file | Update path, keep vectors |
Create ~/Library/LaunchAgents/com.grepai.watch.plist:
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
<key>Label</key>
<string>com.grepai.watch</string>
<key>ProgramArguments</key>
<array>
<string>/usr/local/bin/grepai</string>
<string>watch</string>
</array>
<key>WorkingDirectory</key>
<string>/path/to/your/project</string>
<key>RunAtLoad</key>
<true/>
<key>KeepAlive</key>
<true/>
</dict>
</plist>
Load:
launchctl load ~/Library/LaunchAgents/com.grepai.watch.plist
Create ~/.config/systemd/user/grepai-watch.service:
[Unit]
Description=GrepAI Watch Daemon
After=network.target
[Service]
Type=simple
WorkingDirectory=/path/to/your/project
ExecStart=/usr/local/bin/grepai watch
Restart=always
[Install]
WantedBy=default.target
Enable:
systemctl --user enable grepai-watch
systemctl --user start grepai-watch
# Background daemon logs
tail -f ~/.grepai/daemon.log
# Or with systemd
journalctl --user -u grepai-watch -f
Run separate daemons for each project:
# Terminal 1: Project A
cd /path/to/project-a
grepai watch --background
# Terminal 2: Project B
cd /path/to/project-b
grepai watch --background
For multi-project setups:
grepai workspace create my-workspace
grepai workspace add my-workspace /path/to/project-a
grepai workspace add my-workspace /path/to/project-b
grepai watch --workspace my-workspace
❌ Problem: "Another daemon is already running" ✅ Solution:
grepai watch --stop
grepai watch --background
❌ Problem: "Config not found" ✅ Solution: Initialize first:
grepai init
grepai watch
❌ Problem: "Embedder connection failed" ✅ Solution: Start your embedding provider:
ollama serve # For Ollama
❌ Problem: Files not being indexed ✅ Solution: Check ignore patterns in config, ensure file extension is supported
❌ Problem: Indexing very slow ✅ Solutions:
❌ Problem: Index seems outdated ✅ Solution: Clear and reindex:
rm .grepai/index.gob
grepai watch
❌ Problem: Changes not detected ✅ Solutions:
echo 65536 | sudo tee /proc/sys/fs/inotify/max_user_watches
Regular health check:
grepai status
Output:
✅ GrepAI Status
Project: /path/to/project
Config: .grepai/config.yaml
Embedder: Ollama (nomic-embed-text)
Storage: GOB (.grepai/index.gob)
Index:
- Files: 245
- Chunks: 1,234
- Size: 12.5 MB
- Last updated: 2025-01-28 10:30:00
Daemon: Running (PID 12345)
Watch daemon status:
✅ Watch Daemon Active
Mode: Background
PID: 12345
Project: /path/to/project
Initial Index:
- Files scanned: 245
- Chunks created: 1,234
- Duration: 45s
Real-time Monitor:
- Debounce: 500ms
- Events processed: 23
- Last event: 5 minutes ago
Next steps:
- Run 'grepai search "query"' to search
- Run 'grepai watch --status' to check status
- Run 'grepai watch --stop' to stop daemon
Prerequisites
Time Estimate
15-45 minutes depending on use case complexity
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
davila7/claude-code-templates
intellectronica/agent-skills
am-will/codex-skills
sickn33/antigravity-awesome-skills
myzy-ai/dokie-ai-ppt
sickn33/antigravity-awesome-skills
grepai-watch-daemon fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
grepai-watch-daemon is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
We added grepai-watch-daemon from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
I recommend grepai-watch-daemon for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
grepai-watch-daemon is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
Solid pick for teams standardizing on skills: grepai-watch-daemon is focused, and the summary matches what you get after install.
grepai-watch-daemon fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
Useful defaults in grepai-watch-daemon — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
I recommend grepai-watch-daemon for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
We added grepai-watch-daemon from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
showing 1-10 of 45