bug-check
CommandRun automated tests and build checks first, then agent code review. For each bug found, propose or document a regression test.
Use when a build, type check, or test suite is failing and needs to be unblocked with a minimal change.
> /plugin marketplace add yeaight7/agent-powerups
Use when a build, type check, or test suite is failing and needs to be unblocked with a minimal change.
Steps:
1. Run the exact failing command. Confirm the same error reproduces. 2. Read the full error from the first line — identify the root cause, not a cascade error. 3. Read the relevant source file and surrounding context. 4. Apply one targeted fix. No adjacent cleanup, no unrelated changes. 5. Rerun the exact failing command. It must exit 0. 6. Run `npm test`. Confirm no regressions. 7. Report: what was broken, root cause, change made, verification result, deferred issues.
Do not fix adjacent issues. Do not modify test expectations to hide broken logic.
Curated power-ups for coding agents: skills, slash commands, MCP configs, hooks, AGENTS.md templates, and workflows for serious software engineering. Claude Code, Codex, Antigravity CLI, Cursor and more
Run automated tests and build checks first, then agent code review. For each bug found, propose or document a regression test.
Use when a bug needs systematic diagnosis before a fix is attempted.
Use to diagnose environment, tooling, and Agent Powerups setup problems.
Use to turn a spec or user request into working, tested code.
Use to check MCP server prerequisites before activating or using a server.
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.