The Agent Skills Directory

[SAFE]: The skill documentation describes a set of read-only subcommands for interacting with a Jenkins instance. It explicitly states that no commands trigger, cancel, or mutate builds.
[CREDENTIALS_UNSAFE]: The skill manages authentication via JENKINS_USER and JENKINS_API_TOKEN stored in a .env file. This is a recommended practice for handling sensitive credentials in local development environments, and the instructions specifically advise against hardcoding these values.
[COMMAND_EXECUTION]: The skill provides usage guidelines for the af jenkins CLI tool, including piping output to standard utilities like jq and grep. All operations are scoped to information retrieval from the Jenkins API.
[SAFE]: No obfuscation, persistence mechanisms, or unauthorized privilege escalation patterns were identified in the instructions.
[SAFE]: The skill exposes a surface for processing external data from Jenkins logs. 1. Ingestion points: Console and stage logs via 'log' and 'stage-log' subcommands. 2. Boundary markers: Not specified. 3. Capability inventory: Read-only CLI subcommands. 4. Sanitization: Not specified. The risk is minimized by the read-only design of the documented subcommands.

jenkins