The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the execution of performance benchmarks through the npx agentic-flow workers benchmark CLI command.
[EXTERNAL_DOWNLOADS]: Execution of npx commands involves downloading the agentic-flow package from the NPM registry at runtime. As this package belongs to the skill's author, it is a vendor-owned resource.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing external data as part of its benchmarking flow.
Ingestion points: The skill reads performance thresholds from .claude/settings.json and evaluates various worker triggers (keywords) during the trigger-detection benchmark.
Boundary markers: No explicit markers or instructions are defined to distinguish between data and instructions when processing settings or triggers.
Capability inventory: The skill has the capability to execute shell commands via npx and read/write local configuration files.
Sanitization: There is no evidence of validation or sanitization for the inputs retrieved from the settings file or the worker triggers before they are processed by the system.

worker-benchmarks