The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references npx codometer in its instructions and examples, which triggers the download and execution of the package from the public npm registry at runtime.
[COMMAND_EXECUTION]: The instructions detail various ways to execute the codometer command-line tool, including operations that read and write files locally via flags such as --directory, --write, --json, and --readme.
[INDIRECT_PROMPT_INJECTION]: The skill directs the agent to read and interpret JSON reports and markdown blocks produced by the measurement tool, which constitutes an ingestion of external data.
Ingestion points: The agent is instructed to read the metrics, limits, and failures from the JSON report and to parse badge blocks in SKILL.md.
Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within the processed data.
Capability inventory: The agent possesses the capability to execute shell commands and write files as described in the measurement and reporting sections of SKILL.md.
Sanitization: No sanitization or verification steps are specified for the tool's output before it is used to influence the agent's context.

codometer-measure