AC claude-session-warmer
Align your Claude Pro/Max usage window to your working hours. Claude's 5-hour usage window is anchored to your FIRST message of a session, so claude-session-warmer fires a tiny "primer" prompt through the official Claude Code CLI on your always-on box (the VPS where you already run OpenClaw + Claude Code) at chosen anchor times — e.g. 05:00, then each time a window closes — so a fresh window is already open when you start work and your resets line up with your day. Use this skill whenever the user mentions usage windows, the 5-hour limit, usage resets, "warming up" or "pre-starting" their Claude session/window, aligning Claude limits to working hours, getting maximum use out of a Pro/Max plan, or wants to set up or change a warm-up/primer schedule on a VPS. It only shifts WHEN the window opens — it never exceeds quota.
Align your Claude Pro/Max usage window to your working hours.
As a process C 59/100 · Has gaps — weak spots: result and completion, failures and branches, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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
- 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 · 6
✓ No critical or high findings
Medium and low: 6
-
medium Dangerous commands
cmd-persistencebin/session-warmer.mjs:142Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)console.log(`# ( crontab -l 2>/dev/null; node ${self} install --cron-only ) | crontab -`);code literal -
low Dangerous commands
cmd-cron-mentionbin/session-warmer.mjs:136Mentions editing / listing crontab (string literal in code, not executed)console.log("# Open your crontab with: crontab -e then paste the block below.");code literal -
low Dangerous commands
cmd-cron-mentionbin/session-warmer.mjs:142Mentions editing / listing crontab (string literal in code, not executed)console.log(`# ( crontab -l 2>/dev/null; node ${self} install --cron-only ) | crontab -`);code literal -
low Dangerous commands
cmd-cron-mentiondocs/index.html:170Mentions editing / listing crontabcrontab -e <span class="c"># paste it, save — done</span></pre>
-
low Dangerous commands
cmd-cron-mentionREADME.md:63Mentions editing / listing crontabcrontab -e # paste it, save — done
-
low Dangerous commands
cmd-cron-mentionSKILL.md:70Mentions editing / listing crontabcrontab -e # paste the block; save
Files scanned: 7. 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 59/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 4 mutating operations with no state check
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 14 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1132 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +3Description length 830: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Structure: 8 headings
- +3Step-by-step instructions: 14 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.