The Agent Skills Directory

[SAFE]: The skill package is limited to documentation files (SKILL.md, mocking.md, refactoring.md, and tests.md) that provide software engineering guidance and best practices.
[SAFE]: No scripts, binaries, or commands that could lead to remote code execution or unauthorized system access were found within the skill files.
[SAFE]: No hardcoded credentials, sensitive file paths, or data exfiltration vectors were detected in the provided instructional content.
[PROMPT_INJECTION]: The workflow mentions reading an external CONTEXT.md file to align vocabulary with the project's domain. While this is an ingestion surface for potentially untrusted data, its use is restricted to informing naming conventions and interface design. Evidence Chain: Ingestion point is CONTEXT.md (referenced in SKILL.md); Boundary markers are not present; Capability inventory includes writing test and implementation code to the local file system; Sanitization measures are not specified.

tdd