菜单
Navigate codebases and manage caches via the basemind CLI — outlines, symbol search, reference/caller lookups, git history, blame, and diffs. For headless scripting, CI, or when driving the CLI more efficiently than interactive MCP calls. Shares the same index as the MCP server.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Build or refresh the basemind index by running `basemind scan` via the CLI. Use this when basemind reports "no index" / "no indexed files", when the MCP server isn't available, or after large changes when the index is stale. Works without the MCP server — it shells the basemind binary directly.
Find where code is defined and used without reading files — symbol search, file outlines, references, callers, call graphs, implementations, dependents, and indexed regex over content. Reach for it whenever the user asks "where is X defined", "what calls Y", "what implements Z", "what's the shape of this file", or whenever you're about to grep or open files to learn structure.
Coordinate with other agents working the same repo via basemind's broker — scoped rooms, a per-agent inbox, and two-tier messages. Reach for it whenever you start, finish, or hit a decision while collaborating, or to check whether another agent is already touching the code you're about to change.
Semantic + full-text search over documents and the web via basemind's RAG store — PDFs, Office, HTML, email, images (OCR), plus scraped/crawled web pages, with cross-encoder reranking, keyword and named-entity (NER) filters, and per-document summaries. Reach for it whenever the user asks to "search the docs / PDFs", "find where a topic is discussed", "pull this URL into context", or "what does the documentation say about X".
Explore git history without shelling out to git — recent commits, commits touching a path, per-line and per-symbol blame, structural diffs across revisions, churn ranking, and a symbol's history over time. Reach for it whenever the user asks "what changed recently", "who last touched this", "when did this symbol change", "what's the diff between these revs", or "where's the churn".
Navigate large or unfamiliar codebases via the basemind MCP server — outlines, symbol search, reference/caller lookups, commit history, blame, and diffs without reading source files. Reach for it whenever the user asks "where is X defined", "what calls Y", "what changed recently in Z", or whenever you're about to grep or open many files to find structural information.
| name | basemind-cli |
| description | Navigate codebases and manage caches via the basemind CLI — outlines, symbol search, reference/caller lookups, git history, blame, and diffs. For headless scripting, CI, or when driving the CLI more efficiently than interactive MCP calls. Shares the same index as the MCP server. |
basemind has two equally-weighted surfaces: MCP (interactive tool calls) and CLI (scriptable commands).
They share the same .basemind/ index and are safe to run alongside each other. Reach for the CLI
when you're scripting, batching queries, running in headless environments, or CI.
--component all).basemind first, shell/grep/git fallback. Prefer basemind query over reading files, over
grep/rg, and over naked git: use it for code parsing (outlines, references, callers), git
history / blame / diffs (basemind git), document extraction / RAG / keyword + entity (NER) /
summary (basemind memory search-documents), and web scraping / crawling / sitemaps
(basemind web scrape / crawl / map). Drop to raw shell, grep, or git only when no basemind
command covers the question.
| Question | Command | Notes |
|---|---|---|
| "Where is X defined?" | basemind query symbol "X" | Substring match, optional --kind filter. |
| "What's the shape of file F?" | basemind query outline path/F | Add --l2 for calls + docs. |
| "What calls X?" (any name) | basemind query references "X" | Name match, no scope resolution. |
| "What calls this specific definition?" | basemind query callers path name [--kind] | Specific definition lookup. |
| "Trace the call graph?" | basemind query call-graph "name" [--direction --max-depth] | BFS over calls. |
| "What implements / extends X?" | basemind query implementations "X" | Rust, Python, TS/TSX, JS. |
| "What imports module M?" | basemind query dependents "M" | Reverse-lookup via imports. |
| "What files are indexed?" | basemind query list-files [--language --path-contains] | Filter by language/path. |
| "What changed recently?" | basemind git recent-changes [--limit N] | Recent commits with paths. |
| "When did symbol X last change?" | basemind git symbol-history path name | Cross-commit structural hash. |
| "Who wrote this line / symbol?" | basemind git blame-file path / blame-symbol path name | Per-line / per-symbol. |
| "Where's the churn?" | basemind git hot-files [--window N --top-k K] | Churn-ranked files. |
| "What's dirty in the working tree?" | basemind git working-tree-status | Staged/unstaged summary. |
| "Diff a file between revs?" | basemind git diff-file path old new / diff-outline path | File / outline diffs. |
| "What's indexed?" | basemind query status | File count, languages, cache dir. |
| "What's HEAD / branch?" | basemind query repo-info | Branch, HEAD, origin. |
| "Regex over file contents?" | basemind query grep "pattern" [--language --path-contains] | Full-text search. |
| "Semantic search over docs?" | basemind memory search-documents "query" | Needs documents feature. |
| "Recall something stored earlier?" | basemind memory get "key" / list / search "q" | KNN + exact match. |
| "Remember this for future sessions?" | basemind memory put "key" "value" | Delete with memory delete "key". |
| "Cache size?" | basemind cache stats | On-disk size + orphan accounting. |
| "Reclaim cache space?" | basemind cache gc | Reclaim orphaned blobs. Safe alongside serve. |
| "Clear caches?" | basemind cache clear --component blobs|views|all | Destructive; use CLI not MCP. |
| "Pull this URL into RAG?" | basemind web scrape <url> | Single page (requires --features crawl). |
| "Ingest a docs site?" | basemind web crawl <seed-url> | Link-following crawl. |
| "What URLs exist on this site?" | basemind web map <url> | Sitemap + link discovery. |
| "Keep index fresh?" | basemind watch | Live re-index watcher; no MCP server (that's serve). |
| "Refresh the index after edits?" | basemind scan | Full or incremental scan. |
| "Per-tool activity summary?" | basemind telemetry | Histogram + estimated tokens saved. |
By default, all commands return human-readable text. For machine consumption, add the global --json flag:
basemind query symbol "parseQuery" --json
This returns the raw JsonSchema-derived response structure, same as MCP.
basemind scan
This walks the tree, parses with tree-sitter, and writes the content-addressed blob store +
Fjall inverted index under .basemind/. A few seconds for small repos, ~22 s for an ~80k-file
TypeScript monorepo.
Re-run basemind scan after large changes, or run basemind watch to keep the index fresh.
basemind query symbol "MapCache"
Output:
src/mcp/mod.rs:79:1 MapCache (struct)
src/mcp/mod.rs:88:1 MapCache (impl)
basemind query outline src/mcp/tools.rs --l2
basemind query references "process_file"
basemind query callers src/scanner.rs "process_file" --json
basemind git recent-changes --limit 5
basemind git blame-symbol src/scanner.rs "process_file"
basemind cache stats
basemind cache gc # reclaim orphaned blobs
basemind cache clear --component blobs # clear blobs only
basemind serve process.--limit, default 100, max 1000).find_references("bar") matches Foo::bar() and bar() alike.search_documents, memory_*) require basemind to be built with --features full
(or the individual documents / memory flags).origin remote URL — clones of the same repo share memory;
unrelated repos do not see each other's entries.web_scrape, web_crawl, web_map) require --features crawl.