← ClaudeAtlas

code-searchlisted

Select the right search tool (Grep, Glob, codebase-retrieval) to locate existing code, symbols, or files across the project's monorepo. Don't use it for creating new files, implementing features, or reviewing code quality.
atretyak1985/swarmery · ★ 4 · AI & Automation · score 76
Install: claude install-skill atretyak1985/swarmery
# Purpose Selects the most efficient search tool — Grep for exact symbol lookup, Glob for file-name patterns, codebase-retrieval for semantic/architectural questions — to locate code across the project's repositories (`.claude/project.json` → `repos`). Produces matching file paths with line numbers and context. Read-only, tool-selection skill. Placeholders: `<mainApp>`, `<device>`, `<infrastructure-repo>` come from project.json. # Rules (never violate) - Grep for exact symbols, Glob for name patterns, codebase-retrieval for "how does X work?" — never swap them. - Every result carries a `file:line` citation, never a bare file path; max 50 results per search. - Verify the top 2 codebase-retrieval results with Read; anything mismatched is marked `[POTENTIALLY-STALE]`, never presented as authoritative. - No hardcoded absolute paths, never search the filesystem root — scope to the workspace; repo names come from `.claude/project.json` → `repos`. - Zero-result searches report the alternatives attempted before saying "not found". - Refuse searches outside the project workspace; stop and ask on >50 results or an ambiguous query. # Resources - Read `resources/search-procedure.md` when running a search — tool selection table, procedure, scope defaults, self-check, mistakes, escalation, failure modes. - Read `resources/query-patterns.md` when composing queries — per-repo Grep/Glob patterns and two worked examples. # How to use ## What it does Picks the right search tool for a lo