メニュー
Compare MCP code intelligence tiers — CLI wrappers, ast-grep, Serena, Zoekt, fff file search, embeddings. Prefer text search before heavy indexes.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
Run ProjectTwelve Unity batch validation and EditMode/PlayMode test suites via Unity 6000.5.1f1. Use when the user or ticket asks to run Unity tests, EditMode fixtures, batchmode validation, or verify test results from TestResults/*.xml.
Log agent sessions, consolidate project memory (dream), promote reviewed memory, and load context for new chats. Use when ending a session, improving cross-session recall, or when the user mentions agent memory, dream, log-session, or memory.md.
Wiki tickets under docs/wiki/tickets/ are the canonical task queue, each linked to a GitHub issue. Use when picking work, claiming an issue, or preparing PR references.
Recommend the next open wiki ticket to work on, ranked by phase then priority, without claiming or mutating anything. Use when the user asks "what's next", to pick the next task, or to start work without a specific ticket in hand.
Sync project-twelve with the Assets/_Licensed submodule via fetch_remotes.py, git hooks, and /fetch-remotes. Use at session start, before picking backlog work, or when the user asks to sync repos or get latest.
Use when the user asks to commit and push, publish, ship, or prepare a release commit. Guides staging only intended changes, writing a Conventional Commit, committing, and pushing to origin after verifying status and diff.
SOC 職業分類に基づく
| name | mcp-code-intelligence |
| description | Compare MCP code intelligence tiers — CLI wrappers, ast-grep, Serena, Zoekt, fff file search, embeddings. Prefer text search before heavy indexes. |
Choose the right code-intelligence layer: shell tools, MCP servers, embeddings.
Optional MCP: fff (ffgrep, fffind, fff-multi-grep), ast-grep MCP, Serena, Zoekt, embedding servers.
Install blocks are shared — See install-blocks.md.
Use winget blocks from the reference when provisioning a new machine.
Use apt/curl blocks from the reference; symlink fdfind → fd if needed.
Use Homebrew blocks from the reference.
Tier recommendation:
Minimal: rg + fd + read_file + git diff + patch_file (IDE/shell)
Better: above + ast-grep + gh + task runner + fff MCP (optional)
Advanced: Serena or codebase-memory-mcp + Zoekt + optional embeddings
fff MCP (optional): Install fff-mcp; add to .cursor/mcp.json from .cursor/mcp.example.json _examples.fff-mcp. Reload MCP. Prefer fff for repeated repo file/content search when connected.
Warning: Embedding-first indexing is memory-heavy — use after rg/ast-grep/fff.
Compare:
| Layer | Best for |
|---|---|
| CLI rg/fd | Fast text, gitignore-aware |
| fff MCP | Indexed repo search, multi-pattern grep |
| ast-grep MCP / sg | Structural patterns |
| Serena / ctags | Symbols, refs |
| Zoekt | Large org code search |
| Embeddings | Fuzzy conceptual search (secondary) |
In addition to generic tiers above:
project-twelve-unity-mcp) — Editor bridge when Unity is open; see AGENTS.md.project-twelve-ingame-mcp) — Play Mode / desktop build at loopback.project-twelve-fff-mcp) — indexed file search; use --no-warmup and explicit repo path per .cursor/mcp.example.json.pixellab) — async pixel art generation (characters, tilesets, UI panels); see pixellab-mcp.MCP tools that write files or run jobs need user intent. See commands-requiring-confirmation.md.
%LOCALAPPDATA%\fff-mcp\bin to PATH or use full path in mcp.json.