DC janitor
Automated transcript trimming, LLM memory extraction, and session hygiene for OpenClaw gateways. Keeps transcripts from bloating, extracts structured memories before archiving, and prunes stale sessions.
As a process C 52/100 · Has gaps — weak spots: result and completion, when it triggers, consistency
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.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 9
-
high Dangerous commands
cmd-persistencescripts/setup.sh:211Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null; echo "$CRON_LINE # session-janitor") | crontab -
-
high Dangerous commands
cmd-persistencescripts/setup.sh:228Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load "$PLIST_DEST" 2>/dev/null && \
-
high Dangerous commands
cmd-persistenceSKILL.md:124Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl unload ~/Library/LaunchAgents/ai.openclaw.session-janitor-watcher.plist
-
high Dangerous commands
cmd-persistenceSKILL.md:125Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load ~/Library/LaunchAgents/ai.openclaw.session-janitor-watcher.plist
Medium and low: 5
-
medium Dangerous commands
cmd-persistencescripts/setup.sh:233Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)echo " Start: launchctl load \"$PLIST_DEST\""
code literal -
low Dangerous commands
cmd-cron-mentionscripts/setup.sh:206Mentions editing / listing crontabif crontab -l 2>/dev/null | grep -qF "session-janitor"; then
-
low Dangerous commands
cmd-persistencescripts/setup.sh:208Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition; code comment)crontab -l 2>/dev/null | grep -v "session-janitor" | { cat; echo "$CRON_LINE # session-janitor"; } | crontab -detectorcomment -
low Dangerous commands
cmd-cron-mentionscripts/setup.sh:208Mentions editing / listing crontabcrontab -l 2>/dev/null | grep -v "session-janitor" | { cat; echo "$CRON_LINE # session-janitor"; } | crontab - -
low Dangerous commands
cmd-cron-mentionscripts/setup.sh:211Mentions editing / listing crontab(crontab -l 2>/dev/null; echo "$CRON_LINE # session-janitor") | crontab -
Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 52/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 9 mutating operations with no state check
- 40Consistency. Frontmatter name (janitor) differs from the folder (session-janitor)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 21 steps
- 100Execution cost. Instruction body is 2320 tokens
- low 11 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
- +1No license
- +2Single-language instructions
- +3Description length 203: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (9 code blocks)
- +3All 10 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.