AlucifyAnalyze your specs and codebase to surface risks before your AI coding agents start writing code. Alucify builds structured project context from your PRDs, design docs, and source code. It finds gaps, conflicts, and missing requirements so Claude Code produces accurate code on the first pass instead of hallucinating. Why Alucify?AI coding agents work best when they have clear, complete context. But specs drift from code, requirements contradict each other, and coverage gaps hide in plain sight. Alucify catches these problems before you start coding.
FeaturesBuild Project ContextAnalyze your codebase and specification documents to build structured project context covering your requirements, implementations, and their relationships. View AI Coding RisksSee a prioritized list of risks that would cause AI agents to write incorrect code — gaps between specs and implementation, conflicting requirements, missing validation criteria. Refine SpecsSelect risks and fix them interactively via an AI chat session. Alucify proposes spec updates, you approve or edit, and the fixes are applied directly to your documents. Generate SpecsCreate PRDs, architecture docs, research reports, UX designs, and more via interactive AI workflows (requires Claude Code CLI):
Analyze ProgressTrack implementation progress against your requirements by analyzing git commits. See which features are implemented, in progress, or still planned. Technical Debt AnalysisRun stress tests against your codebase architecture to identify structural weaknesses, coupling hotspots, and maintainability risks. Token Usage TrackingMonitor your AI token consumption across the project. Tracks both Alucify workflow usage and direct Claude Code sessions, with breakdowns by source, model, user, and time period. Available in the VS Code extension, CLI ( Ask About ProjectChat with AI about your project using project context. Ask questions about architecture, requirements, or implementation details. Language & Framework SupportAlucify uses Tree-sitter AST parsing for accurate code indexing:
Full = Tree-sitter AST + multi-tier call resolution + framework-specific classification. Supported = Tree-sitter AST + call resolution. Generic classification heuristics. Partial = File path heuristics only. No AST parsing. Planned = Tree-sitter grammar available. Not yet implemented. Getting StartedPrerequisites
Quick Start
The
|
| Feature | VS Code Extension | CLI | MCP Server |
|---|---|---|---|
| Analysis | |||
| Analyze codebase (codebase context) | Yes | Yes | |
| Analyze specs/PRDs against codebase | Yes | Yes | |
| Catalog mode (mechanical, free) | Yes | Yes | |
| Fast / full mode (LLM-powered) | Yes | Yes | |
| Project Context Querying | |||
| Query nodes by type, name, status | Yes | Yes | Yes |
| Full node detail (DSL, connections) | Yes | Yes | Yes |
| Blast radius / impact analysis | Yes | Yes | Yes |
| Coverage gaps (unimplemented, untested) | Yes | Yes | Yes |
| Version diff | Yes | Yes | Yes |
| Analysis report summaries | Yes | Yes | Yes |
| Pre-commit impact preview | Yes | Yes | Yes |
| Claude Code Integration | |||
| MCP server (9 project context tools) | Yes | Yes | Yes |
| CLAUDE.md mental model rules | Yes | Yes | Optional |
| Session-start context injection | Yes | Yes | |
| Plan validation hook | Yes | Yes | |
| Task annotation hook | Yes | Yes | |
| Plan / Continue (AI-powered) | Yes | Yes | |
| Progress Tracking | |||
| Analyze progress (committed + uncommitted) | Yes | Yes | |
| Auto-track commits against project context | Yes | Yes | |
| Implementation status updates | Yes | Yes | |
| Version snapshots | Yes | Yes | |
| Progress reporting | Yes | Yes | |
| VS Code UI | |||
| Dev Progress dashboard | Yes | ||
| Context panel (node details) | Yes | ||
| Technical debt analysis | Yes | ||
| Remediation workflows | Yes | ||
| Chat panel with project context | Yes |
- Analysis author — Use the Extension or CLI. Run
alucify enablefor full Claude Code integration with hooks and commit tracking. - Consumer developer — Use the MCP Server. A teammate commits
.alucify/and you get context-aware Claude Code with zero setup. Install viaalucify mcp-install --with-rules,npx @alucify/mcp, or clone a repo that already has it configured. - CI / automation — Use the CLI headlessly (
alucify analyze-code,alucify analyze-specs,alucify analyze-progress).
See the CLI and MCP Server sections below for details.
Configuration
Settings available in VS Code Settings UI (Cmd+, / Ctrl+,, search "Alucify"):
| Setting | Default | Description |
|---|---|---|
alucify.authMode |
apiKey |
Authentication mode: apiKey (Anthropic API) or claudeCode (CLI subscription) |
alucify.telemetry |
true |
Send anonymous usage telemetry |
alucify.notifications.os |
true |
Show OS notifications when workflows complete and VS Code is not focused |
alucify.analyzeProgressOnCommit |
true |
Auto-analyze progress after each commit (requires alucify enable) |
alucify.intentCapture.enabled |
false |
Automatically surface requirements and decisions from your Claude Code sessions in your project context |
alucify.refineSpecs.mode |
chat |
UI for Refine Specs: chat (embedded panel) or terminal (Claude Code terminal) |
Commands
Open the command palette (Cmd+Shift+P / Ctrl+Shift+P) and type "Alucify" to see all available commands:
| Command | Description |
|---|---|
| Analyze Code | Index your codebase with Tree-sitter (free, no LLM) |
| Analyze Specs | Build project context from specs + code |
| View AI Coding Risks | Open the coding risks panel |
| Refine Specs | Fix selected risks via AI chat |
| Add Spec | Import a specification document |
| Generate Spec | Create a new specification document (requires Claude Code) |
| Analyze Progress | Analyze committed + uncommitted changes against requirements |
| Capture Intent | Extract requirements and decisions from Claude Code sessions |
| Analyze Intent | Capture intent from sessions and integrate it into your project context |
| Ask about Project | Chat about your project using project context |
| View Technical Debt Analysis | Open the technical debt analysis panel |
| View Token Usage | Open the token usage tracking panel |
| Pause / Resume / Clear Workflow | Control running workflows |
| Sign In / Logout / Switch Auth Mode | Manage authentication |
CLI
Alucify ships a CLI for headless use in CI pipelines or terminal workflows.
alucify analyze-code # Index codebase (free)
alucify add-spec requirements.pdf # Add a spec
alucify analyze-specs # Analyze specs vs code
alucify analyze-progress # Analyze changes against requirements
alucify enable # Install Claude Code hooks + MCP + CLAUDE.md
alucify disable # Remove Claude Code integration
alucify mcp-install [--with-rules] # Vendor MCP server into .alucify/
alucify plan # Plan implementation with Claude Code
alucify continue # Close gaps from analyze-progress
alucify capture-intent # Extract intent from Claude Code sessions
alucify status # View implementation status
alucify context <query> # Query project context
alucify usage # View token usage summary
alucify check # Pre-commit impact check
MCP Server
For developers who just want context-aware Claude Code without the full CLI or extension.
{ "mcpServers": { "alucify": { "command": "npx", "args": ["@alucify/mcp"] } } }
Or install via the CLI: alucify mcp-install --with-rules — this vendors a self-contained server into .alucify/mcp-server.js that can be committed for zero-install team sharing.
License
MIT