BC cost-watchdog
Tracks LLM spend across providers live, detects runaway loops, enforces budgets. Triggers on: cost/budget/token mentions, LLM API calls, agent workflows, batch processing.
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 0
✓ No critical or high findings
Files scanned: 25. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Tracks LLM spend across providers live, detects runaway loops, enf… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 52/100
- 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
- 40Consistency. Frontmatter name (cost-watchdog) differs from the folder (llm-cost-watchdog)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 36 steps
- 100Execution cost. Instruction body is 2319 tokens
- 100Progress reporting. Reports progress
- low 12 top-level sections: this looks like several domains in one skill
- low The skill ranks results itself: that belongs to the system behind the tool, not the model
- low The response is described with custom markup (6 tags): a typed call is more reliable
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)
- +3Output format is not stated: the model decides each time
- -33 of 17 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 171: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 36 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (1 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.
External checks
ClawHub: clean
This is a disclosed LLM cost-tracking skill that keeps local usage metadata and uses optional monitoring hooks for its stated purpose.
LLM: benign (high) · VirusTotal: · 29 May 2026