SKILLEMALL.ai
GitHub ↗ RU Sign in

FC gateway-watchdog-lite

Self-healing OpenClaw gateway watchdog (Lite). Use when: gateway keeps crashing, auto-recovery needed, gateway reliability issues. Installs a launchd service (macOS) or systemd service (Linux / VPS) that probes the gateway every 2 minutes and auto-recovers it on failure. Sends Telegram alerts on recovery success or failure. Lite version — no crash loop detection.

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: ConfusedUser.com v1.0.2 MIT-0 8 files · 4 scripts body ≈ 766 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationTelegramInfrastructuretype 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
30/100
safety, quality, tests
Safety 60%
0
Quality 40%
75
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
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 · 13

  • high Dangerous commands cmd-persistence README.md:101
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    rm ~/Library/LaunchAgents/ai.openclaw.gateway-watchdog.plist
  • high Dangerous commands cmd-persistence references/gotchas.md:56
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl bootstrap gui/$UID ~/Library/LaunchAgents/ai.openclaw.gateway.plist
  • high Dangerous commands cmd-persistence references/gotchas.md:117
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl bootstrap gui/$UID ~/Library/LaunchAgents/ai.openclaw.gateway-watchdog.plist
  • high Dangerous commands cmd-persistence scripts/gateway-watchdog.sh:68
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl bootstrap "gui/$UID" "$PLIST" 2>/dev/null
  • high Dangerous commands cmd-persistence scripts/install.sh:90
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    if launchctl bootstrap "gui/$UID" "$PLIST_PATH" 2>/dev/null; then
  • high Dangerous commands cmd-persistence SKILL.md:112
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    rm ~/Library/LaunchAgents/ai.openclaw.gateway-watchdog.plist
Medium and low: 7
  • medium Dangerous commands cmd-persistence references/gotchas.md:111
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    **Symptom:** `launchctl bootstrap` returns an error like `Load failed: 5: Input/output error` or `service already exists`.
    quoted
  • medium Dangerous commands cmd-persistence scripts/gateway-watchdog.sh:13
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    PLIST="$HOME/Library/LaunchAgents/ai.openclaw.gateway.plist"
    code literal
  • medium Dangerous commands cmd-persistence scripts/gateway-watchdog.sh:79
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    send_alert "🔴 Gateway auto-recovery FAILED. Manual restart needed: launchctl bootout gui/\$UID/ai.openclaw.gateway && sleep 2 && launchctl bootstrap gui/\$(id -u) ~/Library/LaunchAgents/ai.openclaw.g
    code literal
  • medium Dangerous commands cmd-persistence scripts/install.sh:31
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    PLIST_PATH="$HOME/Library/LaunchAgents/ai.openclaw.gateway-watchdog.plist"
    code literal
  • medium Dangerous commands cmd-persistence scripts/install.sh:98
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    echo "[FAIL] launchctl bootstrap failed — try: launchctl bootstrap gui/\$UID $PLIST_PATH"
    code literal
  • medium Dangerous commands cmd-persistence SKILL.md:20
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    - "~/Library/LaunchAgents/ai.openclaw.gateway-watchdog.plist (macOS)"
    quoted
  • medium Dangerous commands cmd-persistence SKILL.md:42
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation table row)
    | Auto-recovery | `launchctl bootout` + `launchctl bootstrap` (macOS) / `systemctl restart` (Linux) |
    table

Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning frontmatter-yaml SKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Self-healing OpenClaw gateway watchdog (Lite). Use when: gateway k… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value

Process rating: all ten parameters 51/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 1 mutating operations with no state check
  • 55Failures and branches. 1 branches
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 100Steps. 7 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 766 tokens
  • 100Progress reporting. Reports progress

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

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -31 of 4 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 365: enough signal without eating the budget
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 7 items
  • +4Has examples (10 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.

External checks

ClawHub: clean
This skill is a disclosed OpenClaw gateway watchdog that installs a user-level background service to monitor and restart the local gateway.
LLM: benign (high) · VirusTotal: · 29 May 2026