The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes node -e to execute inline JavaScript for file system checks and data aggregation from local metrics logs.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from an external file source which creates a potential surface for indirect injection.
Ingestion points: Data is ingested from ~/.claude/metrics/costs.jsonl using fs.readFileSync as shown in the example scripts in SKILL.md.
Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the ingested log data.
Capability inventory: The skill possesses the capability to read local files and execute Node.js one-liners to process and display that data.
Sanitization: While JSON.parse is used to ensure the data is well-formed JSON, there is no sanitization of the string content within fields like model or session_id before they are processed or presented.

cost-tracking