Catalog
github/codebase-memory-mcp

github

codebase-memory-mcp

Use when a configured codebase-memory-mcp server can assist with graph-backed code discovery, architecture orientation, symbol lookup, callers and callees, dependency or data-flow tracing, impact analysis, unfamiliar modules, or an explicit Codebase Memory request.

global
New~729
v1.0Saved Jul 22, 2026

Codebase Memory MCP

Use the configured Codebase Memory graph as a discovery accelerator, not as the sole source of truth. Confirm graph-derived conclusions with source snippets or local files before editing code or making strong claims.

Workflow

  1. Discover the Codebase Memory tools exposed by the current MCP client; clients may prefix or rename tool namespaces.
  2. Call list_projects when available and use the exact indexed project name. If the repository is not indexed, continue with local exploration or ask before calling index_repository when graph access is important.
  3. Before branch-sensitive or edit-sensitive conclusions, use index_status or detect_changes when available. After a branch switch, assume the index may be stale until checked. If freshness cannot be established, disclose that limitation and verify locally.
  4. Use get_architecture once for orientation in an unfamiliar repository or subsystem. Do not repeat it for narrow follow-up questions.
  5. Use search_graph for definitions, implementations, routes, classes, interfaces, callers, and related symbols. Prefer a natural-language query for discovery and a name or qualified-name pattern for known symbols. Narrow by label or path, set a result limit, and paginate or reduce scope when the response reports more results.
  6. Use search_code or normal repository search for literal strings, configuration keys, test identifiers, error messages, and non-code files. Do not turn a precise text lookup into a broad graph query.
  7. After graph search, use get_code_snippet with the returned qualified name. If source snippets are unavailable, open the local file before relying on the result.
  8. Use trace_path for callers, callees, dependency paths, data flow, cross-service paths, and impact analysis. Include tests only when test coverage is part of the question.
  9. Use get_graph_schema before query_graph. Reserve custom queries for multi-hop or aggregate questions that simpler tools cannot answer, and apply LIMIT or the tool's row limit.
  10. When graph and checked-out source disagree, treat source as current and report likely index drift.

Safety and Fallbacks

  • Do not install Codebase Memory or another third-party skill from this workflow.
  • Do not call delete_project, ingest traces, update ADRs, or index a repository unless the user explicitly requested or approved the action; announce it before execution.
  • Fall back to normal repository exploration when the MCP server, project, index, or required capability is unavailable; do not invent tool results or stop a task that can be completed safely without the graph.
Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

88/100

Grade

A

Excellent

Safety

92

Quality

86

Clarity

88

Completeness

82

Summary

A guide for leveraging a Codebase Memory MCP server to accelerate code discovery, architecture orientation, and symbol lookup in unfamiliar repositories. The skill provides a structured 10-step workflow for using graph-backed tools (search_graph, trace_path, get_architecture) and includes explicit fallback instructions when the MCP server or index is unavailable.

Detected Capabilities

MCP server communicationgraph query executioncode discovery and searcharchitecture analysisdependency tracingrepository indexing (on explicit user request)

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

explore unfamiliar codebaseunderstand architecturefind symbol definitiontrace caller graphanalyze impact scopedependency discovery

Risk Signals

INFO

Explicit approval required for potentially destructive operations (index_repository, delete_project)

Safety and Fallbacks section
INFO

Reliance on MCP server availability with documented fallback to local exploration

Workflow steps 1-2, Safety and Fallbacks
INFO

Graph results treated as non-authoritative; source verification required before editing

Opening statement and Workflow step 7

Use Cases

  • Understand architecture in unfamiliar codebases
  • Discover symbol definitions, implementations, and routes
  • Analyze code relationships: callers, callees, dependencies
  • Perform impact analysis and data-flow tracing
  • Trace cross-service communication paths
  • Explore modules and their consumers without manual search

Quality Notes

  • Excellent scope boundaries: clearly defines what the skill does (discovery acceleration) and what it is not (sole source of truth)
  • Strong error handling: explicit fallback to local exploration when MCP is unavailable; gracefully degrades without stopping work
  • Practical workflow with numbered steps that are logically sequenced and well-justified
  • Good documentation of tool selection rationale: explains when to use search_graph vs search_code vs trace_path
  • Clear safety guardrails: users cannot be tricked into dangerous operations like delete_project without explicit approval
  • Good edge case coverage: handles stale index, branch switching, disagreement between graph and source
  • Minor: limited examples of actual query patterns or expected output shapes (would benefit from one concrete example scenario)
  • Minor: no guidance on performance implications for very large graphs or repositories with millions of symbols
Model: claude-haiku-4-5-20251001Analyzed: Jul 22, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Use github/codebase-memory-mcp in your dev environment

Command Palette

Search for a command to run...