BC claude-notifications
Set up native macOS notifications for Claude Code on local and devpod/remote environments. Use when the user asks to 'setup notifications', 'configure devpod notifications', 'get notified when Claude needs attention', 'setup claude alerts', or 'install notification hooks'. Handles local terminal-notifier, SSH reverse tunnel for devpods, launchd listener, tmux passthrough, and Claude Code hook configuration.
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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.
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.
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.
- 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 · 3
-
high Dangerous commands
cmd-persistencescripts/setup-notifications.sh:92Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load "$PLIST_PATH"
Medium and low: 2
-
medium Dangerous commands
cmd-persistencescripts/setup-notifications.sh:17Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)PLIST_PATH="$HOME/Library/LaunchAgents/com.claude.notify-listener.plist"
code literal -
medium Dangerous commands
cmd-persistenceSKILL.md:85Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)- **Restart listener**: `launchctl unload ~/Library/LaunchAgents/com.claude.notify-listener.plist && launchctl load ~/Library/LaunchAgents/com.claude.notify-listener.plist`
detector
Files scanned: 9. 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 61/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 23 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1143 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
- -34 of 7 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 410: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.