bug-check
CommandRun automated tests and build checks first, then agent code review. For each bug found, propose or document a regression test.
Build or refresh graph-backed memory for a corpus, using graphify first and helper conversions only when they improve corpus quality.
> /plugin marketplace add yeaight7/agent-powerups
name: memory-build description: Build or refresh graph-backed memory for a corpus, using graphify first and helper conversions only when they improve corpus quality. argument-hint: "[path] [--update] [--obsidian]" allowed-tools: - Read - Bash - Glob - Grep
Build persistent graph-backed memory for a corpus. `graphify` is primary engine. `defuddle` and `markitdown` are preprocessing helpers only.
Inputs:
Expected outputs:
1. Resolve target path. Default to current directory. Confirm it exists before any tool invocation. 2. Check requirements:
3. If `graphify` is missing, stop immediately. Report the missing requirement and point to `apx check graphify --install-missing --dry-run`. Do not continue with helper-only output. 4. Inspect the corpus and choose one primary route:
5. Decide build mode:
6. Keep Obsidian optional:
7. Report what happened:
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 build, type check, or test suite is failing and needs to be unblocked with a minimal change.
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.
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.