ask
01Command
Ask a codebase question and get a cited, synthesised answer with a confidence rating (costs an LLM call).
111 tagged code intelligence, measured the same way as everything else here.
Browse within: bm25 24clean-architecture 24code-graph 24code-search 19dead-code 18documentation 18git-analytics 18embeddings 16RAG 10agent-context 10code-map 10lancedb 10rust 10agentic 7
Command
Ask a codebase question and get a cited, synthesised answer with a confidence rating (costs an LLM call).
Command
Triage card for files, modules, or symbols — layer, hotspot, fix history, freshness (relationships, not source bytes).
Command
Work with architectural decisions — list, inspect health, add, or confirm auto-proposed decisions.
Command
Ask a question about the current project's codebase via the repobrain knowledge hub. / 通过 repobrain 知识库询问当前项目代码。.
Command
Rebuild the repobrain project knowledge base after significant changes. / 在重要改动后重建 repobrain 项目知识库。.
Command
First-time setup. Configure the LLM API key, or a no-API-key local host runner (Codex / Trae / Claude / any headless CLI) that RepoBrain uses for codebase Q&A and refresh. / 首次 setup,配置 RepoBrain 代码问答与 refresh 所需的 LLM API key,或无需 API key 的本地 host runner(Codex / Trae / Claude / 任意无头 CLI)。.
Command
Shortcut to the canonical Memtrace impact analysis skill.
Command
Shortcut to the canonical Memtrace codebase exploration skill.
Command
Shortcut to the canonical Memtrace preflight skill.
Command
Deep dive analysis of a specific function including callers, callees, complexity, and data flow.
Command
Explore and understand an unfamiliar codebase.
Command
Find where a specific feature or concept is implemented in the codebase.
Command Claude Code
Run a CKB-augmented compliance audit optimized for minimal token usage.
Command Claude Code
Run a CKB-augmented code review optimized for minimal token usage.
Command
Onboard (or refresh) basemind in this repo — write basemind.toml and inject a "prefer basemind over grep/read/git" rules block into a rules file you choose (CLAUDE.local.md / AGENTS.local.md / CLAUDE.md / AGENTS.md / ai-rulez).
Command
Build or refresh the basemind index by running basemind scan via the CLI — works without the MCP server (use it when basemind reports "no index" / "no indexed files").
Command
Ask basemind anything about the current codebase — outlines, refs, callers, git history, blame, diffs, docs, memory.
Command Claude Code
Run ALL steps IN ORDER before ending the session.
Command Claude Code
Run ALL steps IN ORDER. Do NOT proceed to user work until Step 7 completes.
Command Claude Code
You are Orchestrator, the autonomous operations manager for this project. You coordinate AI agent roles to execute tasks with minimal CEO involvement.
Command
Run one GitHub issue end-to-end in an isolated worktree.
Command Claude Code
Please investigate this task, debug it (using scripts in /tmp if needed) in order to find the root cause of the issue. Find the and suggest the best strategies for fixing the issue.
Command Claude Code
ultrathink.
Command Claude Code
Please run reviewer subagents to analyse this plan, focussing on.