synthesis-model-tiers
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill establishes a naming convention (judgment, routine, bulk) to avoid hardcoding specific model identifiers in AI agent workflows. It functions primarily as a lookup table in
tiers.yamland does not perform any programmatic actions. - [NO_CODE]: There are no executable scripts (e.g., .py, .js, .sh) or binary files included in the skill. The logic for resolving model tiers is intended to be implemented by the consumer (agent or application) rather than executed by the skill itself.
- [EXTERNAL_DOWNLOADS]: The skill includes links to official documentation for Anthropic, OpenAI, and Google within the
tiers.yamlfile. These URLs are for human reference to verify model IDs and do not facilitate automated downloads or remote code execution.
Audit Metadata