菜单
Use when searching source code: text/regex (ripgrep), structural/AST patterns (ast-grep, semgrep), symbol definitions/references/callers (LSP, GNU Global, ctags), when/why code changed (git history), structural rewrites (comby), or size/complexity (tokei, scc).
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。
Use when creating or editing a plugin for a multi-host GitHub Copilot / APM / Claude Code marketplace — required manifests, the plugin.json ⇆ apm.yml mirroring rule, portable env-var and install conventions, component layout, and the catalog entry.
Use when every unit of a corpus must be accounted for rather than merely searched — auditing a document set, log archive, or file tree with provable coverage and gaps split into truly absent versus undecidable.
Use when searching non-code corpora: query JSON/YAML/config (jq, yq, gron), tabular data files (duckdb, sqlite-utils), or content inside PDFs/Office/archives (rga, pandoc, pdftotext).
Use when deciding WHERE a piece of guidance should live — always-on memory (CLAUDE.md / AGENTS.md), a path-scoped rule, an on-demand skill, a subagent, an MCP server, or a deterministic hook — and how to keep the always-on budget small.
Use for semantic search over a markdown corpus when keywords aren't enough (you know the meaning, not the exact words), or hybrid semantic plus lexical search when both meaning and exact terms matter. Index once, then query.
Use when capturing, recalling, reviewing, or consolidating durable project memory across sessions, especially decisions, constraints, procedures, and episodes that must retain provenance and freshness.
| name | code-search |
| description | Use when searching source code: text/regex (ripgrep), structural/AST patterns (ast-grep, semgrep), symbol definitions/references/callers (LSP, GNU Global, ctags), when/why code changed (git history), structural rewrites (comby), or size/complexity (tokei, scc). |
| license | MIT |
| compatibility | Requires ripgrep (rg). Optional: fd, ast-grep (sg), semgrep, comby, difftastic, tokei, scc, GNU Global (global), universal-ctags (ctags), and rtk (rtk-ai/rtk) for compact rg/git output. |
| metadata | {"author":"Mark Beacom","version":"0.1.0"} |
| allowed-tools | Bash(rg:*) Bash(fd:*) Bash(sg:*) Bash(ast-grep:*) Bash(semgrep:*) Bash(git:*) Bash(comby:*) Bash(difft:*) Bash(tokei:*) Bash(scc:*) Bash(global:*) Bash(gtags:*) Bash(ctags:*) Bash(readtags:*) Bash(rtk rg:*) Bash(rtk git:*) Read Glob Grep |
CLI search for source code. Pick the modality by what you know.
This skill is portable across GitHub Copilot, APM, and Claude Code; keep the
references/ folder next to SKILL.md when copying it into a Copilot skill
location.
| Task | Use | Reference |
|---|---|---|
| Text / regex in code | rg | ripgrep |
| Find files by name/path | fd | fd |
| Structural / syntax-aware search | sg (ast-grep) | ast-grep |
| Security/lint rule packs, taint | semgrep | semgrep |
| Symbol defs / refs / call hierarchy | LSP · global · ctags | code-intelligence |
| When/why code changed | git log -S/-G/-L | git-history |
| Structural search-and-replace | comby, sg --rewrite | comby |
| Size / complexity by language | tokei, scc | metrics |
Decision flow: text → rg | structural → sg | symbol defs/refs → LSP/global |
rule packs → semgrep | filenames → fd | change history → git pickaxe |
rewrite → comby | LOC → tokei.
rg -t py, sg --lang ts, fd -e go),
restrict dirs, and count first (rg -c pattern | wc -l) before reading.rg -g '!vendor/' -g '!*.lock', fd -E node_modules.rg -e P1 -e P2) in one walk,
or issue distinct searches as parallel tool calls. Never sequential &&.rg -t ts includes .tsx; fd -e ts does NOT — use fd -e ts -e tsx.retrieval-strategy skill or invoke the retrieval-strategist agent.rtk when installed — prefix the rtk-wrapped tools (rtk rg …,
rtk git log …) for 60–90% smaller output; other tools run directly and
rtk rg -c/-l stay raw (pipe-safe). See rtk.For non-code corpora (JSON/YAML, CSV/Parquet, PDFs/Office), use the
data-and-docs-search skill.