Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add yoanbernabeu/grepai-skills --skill grepai-watch-daemongit clone --depth 1 https://github.com/yoanbernabeu/grepai-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/yoanbernabeu/grepai-skills/grepai-watch-daemon)<a href="https://agentmods.dev/skills/yoanbernabeu/grepai-skills/grepai-watch-daemon"><img src="https://agentmods.dev/badge/skills/yoanbernabeu/grepai-skills/grepai-watch-daemon/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yoanbernabeu/grepai-skills/grepai-watch-daemon"><img src="https://agentmods.dev/badge/skills/yoanbernabeu/grepai-skills/grepai-watch-daemon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00028 | $0.02068 |
| Opus 5.5 | $0.00011 | $0.00827 |
| Sonnet 5.5 | $0.00006 | $0.00414 |
| Haiku 4.5 | $0.00003 | $0.00207 |
Grade B, and why
grepai-watch-daemon scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
echo 65536 | sudo tee /proc/sys/fs/inotify/max_user_watches How it starts
The opening of the file, as written. The whole thing — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GrepAI Watch Daemon
This skill covers the grepai watch command and daemon management for real-time code indexing.
When to Use This Skill
- Starting initial code indexing
- Setting up real-time file monitoring
- Running the daemon in background
- Troubleshooting indexing issues
What the Watch Daemon Does
The watch daemon:
- Scans all source files in your project
- Chunks code into segments (~512 tokens)
- Generates embeddings via your configured provider
- Stores vectors in your configured backend
- Monitors for file changes in real-time
- Updates the index when files change
Basic Usage
Start Watching (Foreground)
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.
Start in Background
grepai watch --background
Output:
🔍 GrepAI Watch (background)
Daemon started with PID 12345
Log file: ~/.grepai/daemon.log
Check Daemon Status
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
Stop the Daemon
grepai watch --stop
Output:
✅ Daemon stopped (PID 12345)
Command Reference
| 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 |
Configuration
Watch Settings
# .grepai/config.yaml
watch:
# Debounce delay in milliseconds
# Groups rapid file changes together
debounce_ms: 500
Debounce Explained
When you save a file, editors often write multiple times quickly. Debouncing waits for changes to settle:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 386 lines · 28 tokens per session scan B 2c50aacf951b
grepai-watch-daemon is a skill published in the GitHub repository yoanbernabeu/grepai-skills (20 stars, last pushed 9mo ago), licensed MIT. It adds 28 tokens to every session and 2,068 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
codesage-retrieval
Route semantic and structural code queries through CodeSage. Use for definitions, references, dependencies, impact, features, context, history, risk, test selection, edit checks, and stack traces.
rawq
Context retrieval engine. Semantic + lexical hybrid search over codebases. Returns ranked code chunks with file paths, line ranges, scope labels, and confidence scores.
cs-onboard
Structured C-suite onboarding via a founder interview that captures company context into a persistent file used by all advisory skills. Use when setting up advisory context, refreshing stale context, or onboarding a new executive.
decision-logger
Two-layer memory for executive decisions, separating raw deliberation from approved decisions to prevent hallucinated consensus. Use when logging decisions, reviewing past decisions, or checking overdue action items.
context-engine
Context management engine for AI coding agents. Use when building agent memory systems, optimizing context windows, allocating token budgets, designing RAG pipelines for code, or managing persistent multi-session agent state.
self-improving-agent
Patterns for AI agents that learn from their own execution, detect failure modes, and improve autonomously. Use when building agents that get better over time, managing auto- memory, or designing self-correcting feedback loops.