AB openclaw-scheduler-token-auditor
Audit OpenClaw scheduler token usage for cron jobs, scheduled tasks, and heartbeat sessions. Use when the user wants to know which scheduled job is expensive, which cron is burning the most tokens, whether a cron or heartbeat run exceeds a token threshold or budget, why scheduler token usage is high, or to investigate unexpected token burn. Trigger explicitly on slash-style phrases like "/token_auditor" and "/schedule_auditor". Also match requests such as "audit scheduler tokens", "which cron uses the most tokens", "check whether this scheduled task exceeds 50000 tokens", "audit heartbeat token usage", "find expensive scheduled tasks", "查哪个 cron 最烧 token", or "检查这个定时任务有没有超 token".
As a process B 68/100 · Nearly there — weak spots: inputs and preconditions, progress reporting
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 · 0
✓ No critical or high findings
Files scanned: 2. 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 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 85Steps. 94 steps, 1 vague phrases
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1863 tokens
- 100Running it twice. No mutating operations
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)
- +1No license
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +3Description length 689: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 94 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.