The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local system commands using python3 to run a coverage tool at ~/.claude/harness/fdk/tools/surface-coverage.py and performs automated testing via python3 -m pytest on the harness/tests/test_surface_coverage.py file.
[DYNAMIC_EXECUTION]: Under Branch B01, the skill instructs the agent to dynamically write and execute custom scripts to handle route discovery for web frameworks that do not use file-based routing. It also includes capabilities to modify the user's project by injecting new test gates or CI steps.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from the product's codebase directory to determine coverage.
Ingestion points: The product code directory defined in the input contract.
Boundary markers: No explicit boundary markers or instructions to ignore embedded prompts in the analyzed code are defined.
Capability inventory: The skill possesses the ability to read project files, execute Python scripts, write JSON reports, and modify project test configurations.
Sanitization: There is no evidence of sanitization or filtering of the content read from the external codebase before it is processed by the agent.

surface-coverage