Quasi Coder
Analysis
This is an instruction-only coding helper whose behavior appears aligned with translating shorthand or natural-language requests into code, with no install, credential, network, or persistence requirements shown.
Findings (1)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
Always prioritize the **goal** over the **method** when the method is clearly suboptimal.
The skill intentionally tells the agent to favor its interpretation of the user's goal over a specified implementation method when it judges the method to be poor. This is coherent with the skill's coding-assistant purpose, but it is worth noticing because it can lead to non-literal implementations.
