SKILLEMALL.ai
GitHub ↗ RU Sign in

FB agent-defibrillator

Watchdog that monitors your AI agent gateway and restarts it when it crashes. Triggers on "install defibrillator", "agent watchdog", "gateway monitor", "auto-restart agent", or "keep agent alive". macOS launchd service with optional Discord notifications.

Not recommendedcritical or high security findings · low grade F
modbender/skill-library-mcp Agent Skills author: modbender MIT 4 files · 2 scripts body ≈ 406 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Watchdog that monitors your AI agent gateway and restarts it when it crashes.

As a process B 70/100 · Nearly there — weak spots: result and completion, progress reporting

IntegrationDiscordAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
F
36/100
safety, quality, tests
Safety 60%
0
Quality 40%
89
Run on models
none yet
Process rating
B
70/100
Nearly there
Result and completion w 14
0
Progress reporting w 2
0
Failures and branches w 10
50
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 8

  • high Dangerous commands cmd-persistence defibrillator.sh:160
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl bootstrap "gui/$(id -u)" "$GATEWAY_PLIST" 2>> "$LOG_FILE"
  • high Dangerous commands cmd-persistence install.sh:109
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl bootstrap "gui/$(id -u)" "$PLIST_DIR/$PLIST_NAME"
  • high Dangerous commands cmd-persistence README.md:139
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    rm ~/Library/LaunchAgents/com.openclaw.defibrillator.plist
  • high Dangerous commands cmd-persistence README.md:160
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    ls ~/Library/LaunchAgents/*gateway* ~/Library/LaunchAgents/*openclaw*
  • high Dangerous commands cmd-persistence SKILL.md:65
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    rm ~/Library/LaunchAgents/com.openclaw.defibrillator.plist
Medium and low: 3
  • medium Dangerous commands cmd-persistence defibrillator.sh:17
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    GATEWAY_PLIST="$HOME/Library/LaunchAgents/ai.openclaw.gateway.plist"
    code literal
  • medium Dangerous commands cmd-pipe-to-shell-known-host README.md:50
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://raw.githubusercontent.com/hazy2go/agent-defibrillator/main/install.sh | bash
  • medium Dangerous commands cmd-persistence README.md:145
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    Because your agent has a heart. And sometimes hearts stop. And when they do, you need 200 joules of `launchctl bootstrap` straight to the chest.
    quoted

Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

✓ No remarks against the Agent Skills spec

Process rating: all ten parameters 70/100

  • 0Result and completion. Does not say what the result is
  • 0Progress reporting. Says nothing while it works
  • 50Failures and branches. 0 branches, has a failure section
  • 70When it triggers. States when to use, but not when not to
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 7 steps, 1 vague phrases
  • 100Tools and files. No external tools needed
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 406 tokens
  • 100Running it twice. No mutating operations

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 5 example trigger phrases
  • +3Description length 255: enough signal without eating the budget
  • +4Structure: 8 headings
  • +3Step-by-step instructions: 7 items
  • +4Has examples (4 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.