AC token-cockpit
See and slash your OpenClaw / LLM token bill. Use this skill whenever the user asks about token usage, model spend, API costs, or wants to save money on their agent, including phrases like 'how much am I spending,' 'what's my token usage,' 'why is my bill so high,' 'break down my costs by model,' 'am I over budget,' 'set a budget alert,' 'how do I cut my costs,' 'which model is costing me the most,' 'should I switch to a cheaper model,' 'how much would I save with Haiku,' 'project my monthly spend,' or 'optimize my model routing.' Reads local usage logs (no API key, nothing leaves the machine), prices them with an editable model-price table, projects monthly spend, raises budget alerts, and finds expensive-model calls that could safely run on a cheaper model. The cost dashboard OpenClaw doesn't ship with.
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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: 5. 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. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 10 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1063 tokens
- 100Progress reporting. Reports progress
- medium 2 test cases, all positive: not one "should refuse" or "should ask first"
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)
- +3Description length 816: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 8 headings
- +3Step-by-step instructions: 10 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.