AB anthropic-cost-optimizer
Audits and rewrites your OpenClaw config to minimize API token costs. Use this skill whenever the user mentions high bills, API costs, billing changes, "too expensive", "save money", "optimize config", "cacheRetention", model routing, or asks how to make OpenClaw cheaper. Also trigger if the user pastes an openclaw.yaml or openclaw.json and asks for help. This skill reads the live config, identifies cost issues, shows a diff, and writes the optimized version back with user confirmation. Critical context: Anthropic changed billing on April 4 2026 — Claude subscriptions no longer cover third-party harnesses. Many users are now paying full API rates for the first time and need this immediately.
As a process B 70/100 · Nearly there — weak spots: inputs and preconditions, running it twice
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: 3. 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 70/100
- 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
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 16 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1461 tokens
- 100Progress reporting. Reports progress
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 4 example trigger phrases
- +3Description length 700: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 16 items
- +3Output format is stated explicitly
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.