The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a Python-based test fixture (scripts/check-coordination-fixture.py) that utilizes subprocess.run to execute local Git commands and run generated Python scripts within a temporary directory. These operations are restricted to testing the skill's coordination logic and do not interact with remote systems.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources such as issue trackers, documentation, and pull requests. The instructions mitigate the risk of indirect prompt injection by requiring the agent to perform detailed reconciliation of intended states against observed evidence and to verify the lineage of integrated changes.

work-on-spec