install-watchdog

install-watchdog is a skill for Claude Code from athola/claude-night-market. It costs 43 tokens per session (841 once invoked), scanned A, original, MIT.

A setup skill that installs a background watchdog using macOS launchd or Linux systemd, so egregore sessions can be relaunched automatically.

In plain words
What is it for?
Use it to configure egregore for unattended work on a regular machine; it is not intended for CI/CD runners.
Why use it?
It keeps autonomous processing available after a session exits, when active work and budget conditions allow another session.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash plugins/egregore/scripts/install_launchd.sh.

Part of the egregore plugin — 4 skills, 5 commands, 2 agents shipped together

Good fit Use it to configure egregore for unattended work on a regular machine; it is not intended for CI/CD runners.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/athola/claude-night-market
agentmods
npx agentmods add skills/athola/claude-night-market/install-watchdog

Made for: Claude Code.

Or install egregore, the plugin that ships this one along with the rest of its 4 skills, 5 commands, 2 agents.

Wrote 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.

agentmods badge for install-watchdog

README.md
[![agentmods](https://agentmods.dev/badge/skills/athola/claude-night-market/install-watchdog/github.svg)](https://agentmods.dev/skills/athola/claude-night-market/install-watchdog)
Your own site
<a href="https://agentmods.dev/skills/athola/claude-night-market/install-watchdog"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/install-watchdog/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.

agentmods 80×15 button for install-watchdog

Your own site · 80×15
<a href="https://agentmods.dev/skills/athola/claude-night-market/install-watchdog"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/install-watchdog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 841 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 54
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 55
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 107
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 118
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.00841
Opus 5 $0.00022 $0.00420
Sonnet 5 $0.00009 $0.00168
Haiku 4.5 $0.00004 $0.00084

Measured 9d ago against content hash 62addb644867, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

install-watchdog scanned grade A with 0 findings 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 9d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/egregore/skills/install-watchdog/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Install Watchdog

Overview

Installs a persistent daemon that monitors the egregore process and relaunches it when needed. The daemon uses the OS-native scheduler (launchd on macOS, systemd on Linux) to run a watchdog script every 5 minutes.

The watchdog script checks:

  • Whether an egregore session is already running.
  • Whether the budget is in cooldown.
  • Whether there are active work items in the manifest.

If all conditions are met, it launches a new egregore session.

When To Use

  • After initializing an egregore project (egregore init) when you want autonomous relaunching.
  • When setting up egregore on a new machine.

When NOT To Use

  • On CI/CD runners (use the orchestrator directly).
  • When you want manual control over session launches.

Installation Steps

1. Detect the operating system

OS=$(uname -s)

2. Run the appropriate installer

macOS (launchd):

bash plugins/egregore/scripts/install_launchd.sh

This script creates a plist at ~/Library/LaunchAgents/com.egregore.watchdog.plist that runs the watchdog script every 300 seconds (5 minutes).

Linux (systemd):

bash plugins/egregore/scripts/install_systemd.sh

This script creates a systemd timer and service unit at ~/.config/systemd/user/ that fires every 5 minutes.

3. Verify installation

macOS:

launchctl list | grep egregore

Expected output: a line containing com.egregore.watchdog with a PID or - status.

Linux:

systemctl --user status egregore-watchdog.timer

Expected output: active (waiting) status.

4. Confirm to the user

Report the installation result, the schedule interval, and the log file location:

  • macOS: ~/.egregore/watchdog.log
  • Linux: journalctl --user -u egregore-watchdog

Uninstall Command

To remove the watchdog, run:

Skill(egregore:uninstall-watchdog)

Or invoke the uninstall skill directly via the command /egregore:uninstall-watchdog.

Troubleshooting

Read the full file on GitHub · 129 lines

Changes

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.

  1. 9d ago First seen · 129 lines · 43 tokens per session scan A 62addb644867

Subscribe to this mod's changes

install-watchdog is a skill published in the GitHub repository athola/claude-night-market (337 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 841 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

hf-cloud-python-env-setup

Set up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3. Use this skill whenever Python code will be executed for a SageMaker deployment, training job, or any AWS automation — including when about to run pip install, when about to invoke boto3, when creating or…

PracticalSwan/agent-skills · 128 tokens

aws-cli

Safety-first AWS CLI v2 skill for full control of AWS from the terminal — EC2, S3, IAM, Lambda, RDS, DynamoDB, CloudFormation, Route 53, EKS/ECS, logs, billing & 300+ services. Classifies every command by risk tier via a deterministic classifier script and gates destructive/breaking/cost-incurring ops behind…

georgekhananaev/claude-skills-vault · 110 tokens

firebase-cli

Safety-first Firebase CLI (firebase-tools v15) skill for full project control — deploy, Hosting (sites/channels/rollback), Cloud Functions (+secrets), Firestore (databases/indexes/backups/delete), Realtime Database, Auth import/export, Remote Config, App Distribution, App Hosting, Extensions, Data Connect, Emulator…

georgekhananaev/claude-skills-vault · 172 tokens

vercel-cli

Safety-first Vercel CLI (vercel/vc) skill to fully manage projects from the terminal — deploys, env vars, domains, DNS, certs, projects, teams, logs, rollbacks, promotions, firewall, and vercel api. Classifies each command by risk tier and gates destructive/forbidden ops behind confirmation. Self-heals via embedded…

georgekhananaev/claude-skills-vault · 85 tokens

lastlight-server

Install and configure a Last Light SERVER — the GitHub maintenance agent plus its docker-compose stack — on a host. Use when the user wants to "set up / install / deploy / stand up a Last Light server or instance", configure its GitHub App, models, managed repos, or domain, or get the agent running for the first time.…

nearform/lastlight · 109 tokens

wireguard

WireGuard VPN setup and management — server/client config, key management, peer routing, split-tunnel vs full-tunnel, multi-peer topologies, and systemd integration for production admin access.

LuuOW/meridian-mcp · 41 tokens