The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill identifies and processes instructions from local project documentation files, creating a surface for indirect prompt injection.
Ingestion points: The agent is directed to read from design.md, docs/agents/project.md, docs/specs/**, and docs/standards/testing.md.
Boundary markers: There are no specific instructions for the agent to treat content within these files as untrusted or to use delimiters.
Capability inventory: The skill involves executing test commands and performing file deletions (removing production code written without tests).
Sanitization: Content from documentation files is used directly without validation or filtering.
[COMMAND_EXECUTION]: The skill directs the agent to execute shell commands found in local documentation to verify test results.
Evidence: The skill instructs the agent to "Run the test (single-file command from docs/agents/project.md)". This is a standard development capability within the scope of the skill's purpose.

test-first