AD token-saver
Reduce Claude API token consumption and track spending. Diagnoses waste patterns, recommends optimizations, and generates cost reports. Use when: (1) User asks about "tokens", "cost", "spending", "expensive", "cheaper", "optimize prompt", "token budget", or "save tokens". (2) Spending spike detected in usage logs. (3) Starting a new agent setup and want to configure cost-efficient model routing. (4) After adding new skills and want to check system prompt size impact. Never installs or modifies config without showing a diff and getting confirmation first.
As a process D 41/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 41/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (token-saver) differs from the folder (clawtrix-token-saver)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 75Steps. 3 steps
- 100Execution cost. Instruction body is 1713 tokens
- 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 560: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 3 items
- +4Has examples (10 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.