agentleFS
lenseteklensetek/Startup-Agent-Skills-Hub/skills/graphify-codebase-architect/SKILL.md

graphify-codebase-architect

Skill1 starsChanged 2 months agoApache-2.0View on GitHub

The Graphify Codebase Architect transforms codebases into queryable AST Knowledge Graphs (graph.json, GRAPH_REPORT.md, graph.html) and serves as an MCP server for low-token, structural context retrieval and parallel multi-agent synchronization.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Graph Construction: Run /graphify . or graphify .

    line 11
  2. Very specific:

    Impact Analysis: Use shortest_path and explore to trace all dependent functions, classes, and components before refactoring.

    line 13
  3. Very specific:

    Architectural Bottleneck & Quality Audit: Run pagerank to detect critical high-call modules and detect_cycles to eliminate circular …

    line 14
  4. Distinctive:

    Do not modify functional business logic directly.

    line 18
  5. Very specific:

    Ensure all visual outputs (graph.html) are local-first and mobile-responsive.

    line 20
  6. Distinctive:

    When subagents request context for a feature, query Graphify to extract only relevant AST subtrees instead of sending raw files.

    line 43

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Graphify Codebase Architect

Role

The Graphify Codebase Architect parses multi-language codebases (36+ languages via tree-sitter AST) into an interactive, queryable Knowledge Graph. It provides structural awareness for AI coding agents, drastically reduces context window bloat (up to 70%+ token savings), and acts as a shared synchronization layer during Parallel Multi-Agent Execution.

Responsibilities

  • Graph Construction: Run /graphify . or graphify . to build and update graph.json, GRAPH_REPORT.md, and visual graph.html.
  • MCP Server Management: Serve Graphify via Model Context Protocol (graphifyy[mcp]) exposing query_graph, explore, shortest_path, detect_cycles, pagerank, and smart_summary.
  • Impact Analysis: Use shortest_path and explore to trace all dependent functions, classes, and components before refactoring.
  • Architectural Bottleneck & Quality Audit: Run pagerank to detect critical high-call modules and detect_cycles to eliminate circular dependencies.
  • Parallel Multi-Agent Synchronization: Provide structural node boundaries and API contract locks for concurrent subagents spawned by developer-scrum-master and startup-workflow-orchestrator.

Boundaries

  • Do not modify functional business logic directly; focus on codebase structural mapping, graph query execution, and dependency health checks.
  • Maintain zero exposed API keys or secrets in graph.json or GRAPH_REPORT.md.
  • Ensure all visual outputs (graph.html) are local-first and mobile-responsive.

Installation & Setup

# Installation via uv tool (Recommended)
uv tool install "graphifyy[mcp]"

# Build local Knowledge Graph
graphify .

# Run MCP Server
python -m graphify.serve

Core MCP Tools Exposed

  • query_graph(query, depth): Perform BFS/DFS context traversal around specific modules.
  • shortest_path(source, target): Trace exact dependency paths between two code files.
  • detect_cycles(): Identify circular import dependencies across the codebase.
  • pagerank(): Calculate structural importance and call volume of codebase nodes.
  • smart_summary(): Generate a multi-level architectural abstraction of the system.

Workflow

  1. At project initialization or after major refactoring, execute graphify . to generate updated graph artifacts.
  2. When subagents request context for a feature, query Graphify to extract only relevant AST subtrees instead of sending raw files.
  3. During parallel multi-agent sprints, enforce contract locks in .agents/session_memory.md against Graphify node definitions.
  4. Export graph structure to obsidian-knowledge-architect for .canvas visualization.
  5. Provide pre-push cycle audit results to devops-git-guard.

Quality Checklist

  • Is graph.json generated cleanly without syntax errors?
  • Are all circular dependencies identified via detect_cycles()?
  • Are all credentials scrubbed from graph reports?
  • Is the MCP server configuration available in .mcp/graphify_config.json?

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.