Menu
Test accountability policy. All failures belong to the current changeset. Commits must include test results. No failures on main.
| name | no-pre-existing-failures |
| description | Test accountability policy. All failures belong to the current changeset. Commits must include test results. No failures on main. |
| user-invocable | false |
Every test failure is caused by your changes. There are no "pre-existing," "known," "flaky," or "unrelated" failures. If a test fails, you broke it. Fix it before proceeding.
Every git commit must include a test summary. On main, all tests must pass — no exceptions. On branches, failures are permitted only if explicitly noted in the commit message with the failure name and reason.
Scaffolds a Docker "sandbox" harness into a repo so Claude Code can run in `--dangerously-skip-permissions` (YOLO) mode inside an Ubuntu container, with the project bind-mounted at /workspace and the host's ~/.claude bind-mounted for auth and session continuity. Use when the developer wants an isolated filesystem for agent writes but still wants host-visible builds, logs, and session history.
Record agent activity during Claude Code sessions. Captures plans, human input, agent decisions, and deviations via hooks and agent self-reporting.
Template-based code generation pattern using data models, templates, and helper functions to generate repetitive interface code.
Reviews a SKILL.md file or skill directory for quality, correctness, and alignment with Claude Code skill conventions. Use when you've written a new skill and want to check it before committing, or when evaluating an existing skill for improvements.
Helps with things
Transform raw/crude document drafts into structured content. Use when a document is a skeleton of ideas, notes, or stream-of-consciousness that needs generative expansion rather than review polish.
