SKILLEMALL.ai

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.

ClawHub Agent Skills author: daryn-louw v1.0.0 MIT-0 7 files body ≈ 1 132 tokens Open the sourceclawhub.ai analyzed 2 d ago

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

IntegrationAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
A
90/100
safety, quality, tests
Safety 60%
90
Quality 40%
90
Run on models
none yet
Process rating
C
59/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

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

    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 · 6

    ✓ No critical or high findings

    Medium and low: 6
    • medium Dangerous commands cmd-persistence bin/session-warmer.mjs:142
      Persistence 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-mention bin/session-warmer.mjs:136
      Mentions 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-mention bin/session-warmer.mjs:142
      Mentions 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-mention docs/index.html:170
      Mentions editing / listing crontab
      crontab -e                            <span class="c"># paste it, save — done</span></pre>
    • low Dangerous commands cmd-cron-mention README.md:63
      Mentions editing / listing crontab
      crontab -e                              # paste it, save — done
    • low Dangerous commands cmd-cron-mention SKILL.md:70
      Mentions editing / listing crontab
      crontab -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.

    External checks

    ClawHub: clean
    This skill is a disclosed scheduler for sending small Claude CLI prompts from the user's own logged-in VPS, with no evidence of hidden token theft or exfiltration.
    LLM: benign (high) · VirusTotal: · 3 Jun 2026