From typegraph
Explores unfamiliar TypeScript code using navigation tools like ts_navigate_to, ts_trace_chain, and ts_subgraph to trace symbols, types, implementations, and dependencies without reading full files. For understanding architecture or request flows.
npx claudepluginhub guyowen/typegraph-mcpThis skill uses the workspace's default tool permissions.
Efficiently explore unfamiliar TypeScript code using navigation tools instead of reading entire files.
Guides selection of typegraph-mcp tools for type-aware TypeScript navigation: definitions, references, types, exports, usages, blast radius, dependencies, cycles, paths, and subgraphs.
Investigates codebases using Claude-only tools to trace execution paths, understand architecture, and diagnose issues. Outputs analysis report with findings.
Mandates invoking relevant skills via tools before any response in coding sessions. Covers access, priorities, and adaptations for Claude Code, Copilot CLI, Gemini CLI.
Share bugs, ideas, or general feedback.
Efficiently explore unfamiliar TypeScript code using navigation tools instead of reading entire files.
If you know the symbol name but not the file:
ts_navigate_to with the symbol nameIf you know the file:
ts_module_exports to see what the file providests_find_symbol to locate a specific symbol within itIf ts_module_exports on a top-level index.ts is empty or mostly re-exports:
ts_dependency_tree on that composition module to get quick architectural contextCall ts_type_info on the entry point symbol. This gives you the full type signature and documentation without reading the entire file.
Call ts_trace_chain to follow the definition chain from the entry point to the implementation. Each hop shows the file, line, and a code preview.
Call ts_subgraph with the key files discovered in step 3 to see the surrounding module structure. Use direction: "both" and depth: 1 for immediate context.
For a fast system-level read, ts_dependency_tree on the composition module often gives a better first picture than reading a barrel file's exports.
Only now, read specific files at the lines identified by the tools. You have precise coordinates — no need to read entire files.
Never start by reading entire files. Use navigation tools to find the exact lines that matter, then read only those lines. This saves context tokens and produces more accurate understanding.
User: "How does the magic link authentication flow work?"
1. ts_navigate_to({ symbol: "MagicLinkHandler" })
-> Found in apps/core-api/src/entrypoints/magic-link.ts
2. ts_type_info -> Shows handler signature with ClaimToken input, AuthResult output
3. ts_trace_chain -> 4 hops:
magic-link.ts -> ClaimService.ts -> TokenRepository.ts -> tenant-context.ts
4. ts_subgraph({ files: [those 4 files], depth: 1 })
-> Shows AuthService and NotificationService also connect to ClaimService
5. Read the specific lines at each hop to explain the flow