The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes multiple shell commands to gather context, including git log, git diff, and date. It also manages the local filesystem using mkdir to create directory structures for retrospectives.
[COMMAND_EXECUTION]: The --dig mode executes a local Python script located at ~/.claude/skills/dig/scripts/dig.py. This introduces a dependency on code residing outside the current skill's directory which cannot be verified within this scope.
[PROMPT_INJECTION]: The skill has a significant surface area for Indirect Prompt Injection (Category 8).
Ingestion points: The agent reads git commit messages, code diffs, pulse metrics from JSON files, and historical session logs from ψ/memory/logs/.
Boundary markers: Absent. There are no instructions to use delimiters or to disregard potential commands embedded within the git history or session logs.
Capability inventory: The skill has the ability to write files to the local system, commit changes to the git repository, and invoke the oracle_learn tool to persist information in the agent's long-term memory.
Sanitization: No validation or sanitization is performed on the ingested git logs or session data before they are processed and incorporated into the final retrospective output.

rrr