Menu
Choose the right search tool before running commands — fd vs rg vs grep vs ast-grep vs fff MCP vs IDE Grep. Use at the start of any code-finding task.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
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.
| name | search-tool-selection |
| description | Choose the right search tool before running commands — fd vs rg vs grep vs ast-grep vs fff MCP vs IDE Grep. Use at the start of any code-finding task. |
Route agents to the correct search tool before running commands.
rg returns too many false positivesOptional: fd, rg, ast-grep, fff MCP (ffgrep, fffind, fff-multi-grep), IDE Grep/SemanticSearch/Glob.
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.
Default escalation: fd (filename) → rg (content) → ast-grep (syntax) → bat/Read (slice).
| Task | Use | Avoid |
|---|---|---|
| File by name/path | fd | grep -r for filenames |
| Text/literals in contents | rg | bare grep -r . |
| grep fallback | grep with path scope | when rg available |
| Syntax/AST shapes | ast-grep | regex alone |
| Security rule packs | semgrep scan | ad hoc rg for policy |
| Symbol index / cross-ref | ctags, Serena MCP, Zoekt | rg for every ref |
| Repo layout | tree -L 3 | loading all paths |
| Interactive pick (human) | fzf | agents (non-interactive) |
| Config keys in JSON/YAML | jq / yq | rg on minified JSON |
| Repeated repo search (MCP connected) | fff ffgrep/fffind | many grep tool roundtrips |
| Cursor agent | Grep / SemanticSearch / Glob | shell when tool bound |
grep vs rg: Always prefer rg. Use grep only if rg is unavailable.
fff MCP: When connected, prefer fff tools for repo-wide file/content search; keep one-off bounded probes as rg/fd.
fzf: Humans only — agents use --max-count, -l, -g, explicit paths.
Exclude globs: node_modules, dist, build, .git.
ProjectTwelve / Unity: Also exclude --glob '!Library' --glob '!Temp' --glob '!Logs' --glob '!obj' --glob '!Build'. For C#, prefer rg for symbol text first; escalate to SemanticSearch before ast-grep unless C# rules are configured.
See commands-requiring-confirmation.md.
-g '!tests', or switch to ast-grep.rg/fd; see mcp-code-intelligence for setup.