coveragelisted

# Coverage ## When to use - The user wants to address coverage gaps in target code autonomously using the `test` agent. ## Goal - Run test `subagents` sequentially to cover behavioral gaps in target code. ## Input - Accept optional arguments (file or folder paths). ## Workflow 1. **Testing Loop**: - Immediately use the `subagent` tool to spawn a `test` `subagent` (pass optional arguments). - Await test result. - If `subagent` returns `No Gaps` status, exit loop and finish. - On `Failed` status or any process failure, halt immediately and surface the error. - Loop back to spawn another `test` `subagent` if the previous pass returns `Improved`. 2. **Report**: Emit execution summary. ## Directives - Always use the subagent tool for subagent invocation. - Pass the optional argument verbatim to the `test` subagent; never read or expand file-path arguments. - Rely on `subagent` status blocks to direct the loop. - Halt immediately on subagent `Failed` status or any process failure (crash, timeout, `AgentError`). - List of agents permitted to invoke: - `test` ## Constraints - Restrict your activities to: - Using the `subagent` tool to spawn `test` agents to advance the workflow. - Using agent results to direct the loop or advance the workflow. - Perform orchestration only; never edit codebase files, tests, or documentation. - Operate strictly in read-only mode; make no file writes. - Never run `subagents` in parallel or co