depwire

depwire prompt— graph-first workflow for AI agents

# Get the graph-first workflow prompt for your agent depwire prompt # generic depwire prompt --tool claude # Claude Code optimized depwire prompt --tool cline # Cline optimized depwire prompt --tool codex # Codex optimized

Paste the output as your agent's system context before starting a complex task.

Connect Depwire to any MCP-compatible AI tool. Your AI gets 24 tools it can call autonomously.

Claude Desktop— add to~/Library/Application Support/Claude/claude_desktop_config.json:

{ "mcpServers": { "depwire": { "command": "npx", "args": ["-y", "depwire-cli", "mcp"] } } }

For large projects — instant MCP startup:

# Parse once (writes depwire-output.json) depwire parse . # MCP starts instantly from cached graph (<100ms) depwire mcp . # Flags: depwire mcp . --from-cache # error if no cache found depwire mcp . --no-cache # force full re-parse

Cursor— Settings → Features → Experimental → Enable MCP → Add Server:

After runningdepwire parse ., Depwire generates.depwire/AGENTS.md— a project-specific context file containing module structure, key files, health summary, and MCP quick-start commands.

Claude Code readsAGENTS.mdautomatically when present. Add it to yourCLAUDE.md:

# In your project root CLAUDE.md: echo "## Depwire Context" >> CLAUDE.md echo "Read .depwire/AGENTS.md for codebase architecture." >> CLAUDE.md

This gives every Claude Code session project-specific orientation without an MCP tool call.

The coordination tools (claim_files,release_files,get_active_claims,record_decision,get_decisions) write runtime state to.depwire/claims.jsonland.depwire/decisions.jsonl. Add these to your project's.gitignore:

.depwire/claims.jsonl .depwire/decisions.jsonl

Depwire detects connections between files written in different languages.

A TypeScriptfetch('/api/users')call matched to a Python@app.get('/api/users')route definition — that's a cross-language edge. Delete the Python route and Depwire shows the TypeScript callers as broken.

- REST API edges — fetch/axios calls matched to Express, FastAPI, Flask, Gin route definitions
- Subprocess edges — execSync/subprocess.run calls matched to target files in the graph

These edges flow through every existing feature: What If simulation, impact analysis, security scanner, and arc diagram visualization.

Overall: 68/100 (Grade: D) Coupling 70 C Cohesion 80 B Circular Dependencies 100 A God Files 40 F Orphans & Dead Code 20 F Dependency Depth 60 D

6 dimensions. Letter grades. Actionable recommendations. Trend tracking across runs.

Note on v1.6.1 scoring change:The dead code scoring methodology was corrected in v1.6.1 to only count exported symbols with zero dependents as candidates for dead code. Previously, local variables and class internals were incorrectly included, inflating dead code ratios for codebases with internally-complex modules. Health scores from v1.6.1+ are not directly comparable to scores from earlier versions.

Depwire exposes a stable public API for programmatic use and CI pipelines:

import { parseProject, buildGraph, calculateHealthScore, analyzeDeadCode, generateDocs, scanSecurity, SimulationEngine, detectCrossLanguageEdges, searchSymbols, getImpact, getArchitectureSummary, DepwireSDKVersion } from 'depwire-cli/sdk';

The SDK is the stable public API surface. All integrations should import fromdepwire-cli/sdk— never from internal paths.

TypeScript, JavaScript, Python, Go, Rust, C, C#, Java, C++, Kotlin, PHP, Swift, Mojo, Ruby, Dart, R — with cross-language edge detection between all supported languages.

Java / JVM— classes, interfaces, enums, records, annotations, inner classes, anonymous classes, lambda expressions, Maven pom.xml and Gradle build file dependency edges, Spring Boot cross-language edges (@GetMapping, @PostMapping, @RequestMapping), JAX-RS / Jakarta EE route detection, Spring WebFlux RouterFunction support.