escapeboy/ai-prompts/codebase-memory
Claude Code and agent skill by escapeboy/ai-prompts
- community
Checking that the SKILL.md file is still in the repository.
Use the codebase knowledge graph for structural code queries. Triggers on: explore the codebase, understand the architecture, what functions exist, show me the structure, who calls this function, what does X call, trace the call chain, find callers of, show dependencies, impact analysis, dead code, unused functions, high fan-out, refactor candidates, code quality audit, graph query syntax, Cypher query examples, edge types, how to use search_graph.
Install
npx vskill@latest install escapeboy/ai-prompts/codebase-memorySKILL.md
Codebase Memory — Knowledge Graph Tools
Graph tools return precise structural results in ~500 tokens vs ~80K for grep.
When to Use (and When NOT to)
| Use the graph | Use something simpler instead | |
|---|---|---|
| Who calls X / what X calls / blast radius of a change | An exact string, error message or config key → search_code or Grep | |
| Architecture overview of an unfamiliar area | Non-code files (JSON, YAML, Markdown) → Read | |
| Dead code, fan-in / fan-out, refactor candidates | Editing by symbol → Serena (replace_symbol_body, rename_symbol); the graph is read-only | |
| Cross-service HTTP / async edges | A whole-codebase audit with many agents → `code-research`, which builds on this |
Requires the codebase-memory-mcp server and an indexed project (index_repository).
Quick Decision Matrix
| Question | Tool call | |
|---|---|---|
| Who calls X? | trace_path(direction="inbound") | |
| What does X call? | trace_path(direction="outbound") | |
| Full call context | trace_path(direction="both") | |
| Find by name pattern | search_graph(name_pattern="...") | |
| Dead code | search_graph(max_degree=0, exclude_entry_points=true) | |
| Cross-service edges | query_graph with Cypher | |
| Impact of local changes | detect_changes() | |
| Risk-classified trace | trace_path(risk_labels=true) | |
| Text search | search_code or Grep |
Exploration Workflow
list_projects— check if project is indexedget_graph_schema— understand node/edge typessearch_graph(label="Function", name_pattern=".*Pattern.*")— find codeget_code_snippet(qualified_name="project.path.FuncName")— read source
Tracing Workflow
search_graph(name_pattern=".*FuncName.*")— discover exact nametrace_path(function_name="FuncName", direction="both", depth=3)— tracedetect_changes()— map git diff to affected symbols
Quality Analysis
- Dead code:
search_graph(max_degree=0, exclude_entry_points=true) - High fan-out:
search_graph(min_degree=10, relationship="CALLS", direction="outbound") - High fan-in:
search_graph(min_degree=10, relationship="CALLS", direction="inbound")
14 MCP Tools
index_repository, index_status, list_projects, delete_project, search_graph, search_code, trace_path, detect_changes, query_graph, get_graph_schema, get_code_snippet, get_architecture, manage_adr, ingest_traces
Edge Types
CALLS, HTTP_CALLS, ASYNC_CALLS, IMPORTS, DEFINES, DEFINES_METHOD, HANDLES, IMPLEMENTS, OVERRIDE, USAGE, FILE_CHANGES_WITH, CONTAINS_FILE, CONTAINS_FOLDER, CONTAINS_PACKAGE
Cypher Examples (for query_graph)
Gotchas
search_graph(relationship="HTTP_CALLS")filters nodes by degree — usequery_graphwith Cypher to see actual edges.query_graphhas a 200-row cap — usesearch_graphwith degree filters for counting.trace_pathneeds exact names — usesearch_graph(name_pattern=...)first.direction="outbound"misses cross-service callers — usedirection="both".- Results default to 10 per page — check
has_moreand useoffset.
Boundaries
Always
- Check
list_projects/index_statusfirst; index the repo if it is missing. - Trust graph results for structure — do not re-verify every edge with grep.
Ask first
- Before
delete_projector re-indexing a very large monorepo.
Never
- Treat a 0-result
trace_pathas "no callers" before confirming the exact name withsearch_graph.
Related skills
- `code-research` — multi-agent audit that grounds its findings through this graph.
- `optimize` — symbol-first exploration workflow.
- `continuity` and `self-improve` — use the graph for blast-radius checks.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryChecking01-global-optimization/skills/codebase-memory/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/escapeboy/ai-prompts/codebase-memory)