FF macos-launchdaemon

Run OpenClaw as a system-level LaunchDaemon on macOS for 24/7 operation, surviving screen lock, logout, and user switching. Uses caffeinate to prevent sleep. Verified working for long-term locked screen scenarios.

Not recommendedcritical or high security findings · low grade F

modbender/skill-library-mcp Agent Skills author: modbender MIT 4 files · 1 script body ≈ 4 377 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Run OpenClaw as a system-level LaunchDaemon on macOS for 24/7 operation, surviving screen lock, logout, and user switching.

As a process F 29/100 · Will not run — References files that are not bundled: ../macos-lock-screen-fix/, ../healthcheck/

Procedure AI and agents Customer support Designtype 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

29/100

safety, quality, tests

Safety 60%: 0
Quality 40%: 73
Run on models: none yet

Process rating

29/100

Will not run

References files that are not bundled: ../macos-lock-screen-fix/, ../healthcheck/

Tools and files w 18: 0
Result and completion w 14: 0
Inputs and preconditions w 11: 0

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

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.
The text references files that are not there: add them or drop the references.

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 · 30

high Dangerous commands cmd-persistence install.sh:143

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
if [ -f ~/Library/LaunchAgents/ai.openclaw.gateway.plist ]; then
```
high Dangerous commands cmd-persistence install.sh:144

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
mv ~/Library/LaunchAgents/ai.openclaw.gateway.plist ~/Library/LaunchAgents/ai.openclaw.gateway.plist.backup
```
high Dangerous commands cmd-persistence install.sh:165

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
sudo launchctl bootstrap system "$PLIST_PATH"
```
high Dangerous commands cmd-persistence README.md:125

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
sudo rm /Library/LaunchDaemons/ai.openclaw.gateway.plist
```
high Dangerous commands cmd-persistence README.md:128

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
mv ~/Library/LaunchAgents/ai.openclaw.gateway.plist.disabled \
```
high Dangerous commands cmd-persistence README.md:129

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
~/Library/LaunchAgents/ai.openclaw.gateway.plist
```
high Dangerous commands cmd-persistence README.md:130

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl bootstrap gui/$(id -u) ~/Library/LaunchAgents/ai.openclaw.gateway.plist
```
high Dangerous commands cmd-persistence README.zh-CN.md:125

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
sudo rm /Library/LaunchDaemons/ai.openclaw.gateway.plist
```
high Dangerous commands cmd-persistence README.zh-CN.md:128

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
mv ~/Library/LaunchAgents/ai.openclaw.gateway.plist.disabled \
```
high Dangerous commands cmd-persistence README.zh-CN.md:129

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
~/Library/LaunchAgents/ai.openclaw.gateway.plist
```
high Dangerous commands cmd-persistence README.zh-CN.md:130

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl bootstrap gui/$(id -u) ~/Library/LaunchAgents/ai.openclaw.gateway.plist
```
high Dangerous commands cmd-persistence SKILL.md:139

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
mv ~/Library/LaunchAgents/ai.openclaw.gateway.plist ~/Library/LaunchAgents/ai.openclaw.gateway.plist.disabled 2>/dev/null
```
high Dangerous commands cmd-persistence SKILL.md:146

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
sudo cp /tmp/ai.openclaw.gateway.plist /Library/LaunchDaemons/
```
high Dangerous commands cmd-persistence SKILL.md:149

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
sudo chown root:wheel /Library/LaunchDaemons/ai.openclaw.gateway.plist
```
high Dangerous commands cmd-persistence SKILL.md:150

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
sudo chmod 644 /Library/LaunchDaemons/ai.openclaw.gateway.plist
```
high Dangerous commands cmd-persistence SKILL.md:153

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
sudo launchctl bootstrap system /Library/LaunchDaemons/ai.openclaw.gateway.plist
```

Medium and low: 14

medium Dangerous commands cmd-persistence install.sh:15

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
```
PLIST_PATH="/Library/LaunchDaemons/ai.openclaw.gateway.plist"
```
code literal
medium Dangerous commands cmd-privilege install.sh:155

Privilege escalation / world-writable permissions
```
sudo cp "$TEMP_PLIST" "$PLIST_PATH"
```
medium Dangerous commands cmd-privilege install.sh:156

Privilege escalation / world-writable permissions
```
sudo chown root:wheel "$PLIST_PATH"
```
medium Dangerous commands cmd-privilege install.sh:157

Privilege escalation / world-writable permissions
```
sudo chmod 644 "$PLIST_PATH"
```
medium Dangerous commands cmd-pipe-to-shell-known-host README.md:25

Pipe-to-shell installer from a well-known host (still executes remote code)
```
curl -fsSL https://raw.githubusercontent.com/happydog-intj/openclaw-macos-always-on/master/install.sh | bash
```
medium Dangerous commands cmd-privilege README.md:125

Privilege escalation / world-writable permissions
```
sudo rm /Library/LaunchDaemons/ai.openclaw.gateway.plist
```
medium Dangerous commands cmd-pipe-to-shell-known-host README.zh-CN.md:25

Pipe-to-shell installer from a well-known host (still executes remote code)
```
curl -fsSL https://raw.githubusercontent.com/happydog-intj/openclaw-macos-always-on/master/install.sh | bash
```
medium Dangerous commands cmd-privilege README.zh-CN.md:125

Privilege escalation / world-writable permissions
```
sudo rm /Library/LaunchDaemons/ai.openclaw.gateway.plist
```
medium Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:35

Pipe-to-shell installer from a well-known host (still executes remote code)
```
curl -fsSL https://raw.githubusercontent.com/YOUR_USERNAME/clawd/master/skills/macos-launchdaemon/install.sh | bash
```
medium Dangerous commands cmd-privilege SKILL.md:146

Privilege escalation / world-writable permissions
```
sudo cp /tmp/ai.openclaw.gateway.plist /Library/LaunchDaemons/
```
medium Dangerous commands cmd-privilege SKILL.md:149

Privilege escalation / world-writable permissions
```
sudo chown root:wheel /Library/LaunchDaemons/ai.openclaw.gateway.plist
```
medium Dangerous commands cmd-privilege SKILL.md:150

Privilege escalation / world-writable permissions
```
sudo chmod 644 /Library/LaunchDaemons/ai.openclaw.gateway.plist
```
medium Dangerous commands cmd-privilege SKILL.md:271

Privilege escalation / world-writable permissions
```
sudo rm /Library/LaunchDaemons/ai.openclaw.gateway.plist
```
medium Dangerous commands cmd-privilege SKILL.md:392

Privilege escalation / world-writable permissions
```
sudo cp "$TEMP_PLIST" "$PLIST_PATH"
```

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

Against the Agent Skills spec

warning missing-ref reference to a missing file: ../macos-lock-screen-fix/
warning missing-ref reference to a missing file: ../healthcheck/

Process rating: all ten parameters 29/100

Will not run. References files that are not bundled: ../macos-lock-screen-fix/, ../healthcheck/

0Tools and files. 2 referenced file(s) missing: ../macos-lock-screen-fix/, ../healthcheck/
0Result and completion. Does not say what the result is
0Inputs and preconditions. Does not say what the process needs to start
0Progress reporting. Says nothing while it works
20When it triggers. No condition that starts the skill
30Running it twice. 3 mutating operations with no state check
40Consistency. Frontmatter name (macos-launchdaemon) differs from the folder (openclaw-macos-always-on)
50Failures and branches. 0 branches, has a failure section
70Execution cost. Instruction body is 4377 tokens
85Steps. 40 steps, 1 vague phrases

medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
low 16 top-level sections: this looks like several domains in one skill

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
-221 emoji in the instructions: noise for the model
+1No license
+2Single-language instructions
+3Description length 213: enough signal without eating the budget
+4Structure: 39 headings
+3Step-by-step instructions: 40 items
+4Has examples (30 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.

Tests

— no evals.json

— no spec.yaml

— not run on models

Files · 4

README.md 5K
README.zh-CN.md 6K
SKILL.md 17K
install.sh 7K

When to use

**Use LaunchDaemon if:** - You need 24/7 bot availability - You lock your Mac regularly but want messages to still work - Multiple users on the same Mac need to access the bot - Running on a home server/always-on Mac **Use LaunchAgent if:** - Only need bot while logged in - Prefer simpler setup (no sudo) - Security-conscious about system-level services

Dates

In catalog since —

Updated in catalog 16 Jun 2026

First seen here 7 Sept 2026

Last analysis 11 Sept 2026, 17:02 UTC

Last seen in crawl 21 h ago

Score history

Date		Score	Qual.
10 Sept 2026	F	29	73
7 Sept 2026	F	28	70
7 Sept 2026	F	26	64

Similar skills

F macos-launchdaemon LeoYeAI/openclaw-master-skills
F macos-launchdaemon ClawHub