SYS.ONLINE — AI CODE ANALYSIS ENGINE v2.0
◆ NEW — PLAN REVIEW MCP · CLAUDE CODE / CODEX / CURSOR / ANY AGENT

PREVENT DRIFT
BEFORE IT'S WRITTEN.
CATCH IT BEFORE IT SHIPS.

The Plan Review MCP checks your AI agent's plan against your codebase's conventions — before a line is written. PR review scores the diff before it merges. Nine architectural detectors. One score. Learn more →

ADD THE MCP
[ WHY VIBECOP ]

STOP BAD CODE.
DON'T REVIEW IT LINE BY LINE.

CI proves the code runs — it can't prove the code belongs. Bloated, AI-authored code multiplies token costs ~2× every 60 days. The cheapest place to stop a duplicate service or an unsafe migration is before it's written — not in a line-by-line PR review after the fact.

[ THE FAILURE MODE HAS SHIFTED ]

HALLUCINATED ABSTRACTIONS

Code calling modules that don't exist in your repo.

SEMANTIC DUPLICATION

The third competing payment workflow, under a new name.

REINVENTED UTILITIES

The agent didn't know a helper already existed.

PATTERN DRIFT

Each PR follows its own convention, not yours.

OVER-ENGINEERING

Five layers of wrapper around one call site.

Every drift above is invisible in a diff, invisible to linters, and compounds across hundreds of AI-authored PRs. A line-by-line review can't catch what a reviewer can't see.

44% of teams already run AI review on PRs. None of them review the plan — the one place drift can still be stopped for free.

[ THE LANDSCAPE ]

THEY REVIEW DIFFS.
WE REVIEW DECISIONS.

CodeRabbit & Copilot own inline PR comments. Greptile owns codebase context. Sonar & Aikido own quality and security gates. Nobody else owns the plan, the entropy score, or the ADRs.

CapabilityVibeCopCodeRabbitGreptileQodoCopilotSonarAikido
Pre-code plan review (MCP)
Architectural entropy score (AII)
ADR-aware review
Knowledge graph + graph Q&A
One rolled-up ticket per PR
Inline PR comments
Learns from reviewer feedback
Deep security (SAST/SCA)
✓ strong◐ partial✗ absent

We skip inline comments & feedback-learning by design — we sell the review nobody else runs, not a louder version of theirs.

[ THE MCP ]

POINT YOUR AGENT AT IT.
THE PLAN GETS REVIEWED.

That "review the plan" column is a remote MCP server. Point Claude Code, Codex, Cursor, or any MCP-capable agent at it and every plan gets checked against your codebase before a line is written.

01

AGENT DRAFTS A PLAN

Claude Code, Codex, Cursor, or any MCP-capable agent writes its implementation plan from your PRD or spec.

02

MCP SCORES IT

The agent calls vibecop_check — the plan is reviewed against YOUR codebase's conventions, ADRs, and existing utilities.

03

FLAGGED BEFORE CODE EXISTS

Would-be duplication, hallucinated abstractions, and pattern drift are caught while they're still sentences, not diffs.

04

NEXT RUN STAYS CHEAP

The codebase stays lean, so every future agent run loads less context, drifts less, and costs less.

THE COST OF DRIFT

ILLUSTRATIVE MODEL — NOT SOURCED DATA
Team size20 devs
Agentic tasks8 / dev / day
Tokens per task (clean multi-file run)~300K
Working days~250 / yr
Drift tax on every run+40%
Blended token price (illustrative)$4 / 1M tokens

A conservative one-year snapshot: ~4.8B wasted tokens ~$19K — and because drift compounds (bloat roughly doubles every ~60 days), that tax accelerates. Prevention keeps it near zero.

Illustrative example only. Your numbers depend on team size, model mix, and how much drift has already accumulated.

claude mcp add --transport http vibecop https://api.gradus.maiife.ai/mcp/vibecop --header "Authorization: Bearer <TOKEN>"

Every plan can mint an MCP token in Settings → Plan Review MCP.

FULL SETUP GUIDE →
5
DETECTOR AGENTS
< 90s
SCAN TIME
100
AII SCORE
0
CONFIGURATION
[ CAPABILITIES ]

NOT ANOTHER LINTER.
AN ARCHITECTURE GUARDIAN.

01 ///

ARCHITECTURE INTEGRITY INDEX

A single score from 0–100 that captures your codebase's structural health. Four weighted axes: Consistency, Reuse, Simplicity, and Structure.

02 ///

THE JUDGE

An LLM synthesis layer that reads all detector signals, applies your team's ADRs, and produces a narrative recommendation — approve, request changes, or reject — with cited evidence.

03 ///

CODE GRAPH

Full dependency visualization with fan-in/out analysis, coupling metrics, and cycle detection. See how a single PR impacts the broader architecture before it merges.

04 ///

ENTROPY TRACKING

Monitor drift velocity over time. Spot when duplication creeps in, when abstractions diverge, and when pattern variance accelerates — before it becomes tech debt.

[ PROTOCOL ]

THREE STEPS.
ZERO CONFIG.

01

CONNECT YOUR REPO

Link your GitHub repository. VibeCop installs as a lightweight integration — no CI changes, no config files, no pipeline modifications.

02

OPEN A PR

VibeCop automatically triggers on every pull request. Nine architectural detector agents analyze the diff against your full codebase graph in under 90 seconds.

03

REVIEW THE VERDICT

The Judge synthesizes all signals into a single narrative — with an Architecture Integrity score, cited findings, and a clear approve/reject recommendation.

[ DETECTOR AGENTS ]

FIVE SPECIALIZED AGENTS.
ONE UNIFIED ANALYSIS.

D1

HALLUCINATED ABSTRACTIONS

Detects code structures that exist without justification — interfaces nobody implements, factories that produce one product.

D2

SEMANTIC DUPLICATION

Finds logic that does the same thing in different words. Not copy-paste — conceptual overlap that fragments your domain model.

D3

OVER-ENGINEERING

Identifies unnecessary abstraction layers, premature generalization, and design patterns applied where a function would suffice.

D4

PATTERN DRIFT

Spots when new code deviates from your team's established conventions — error handling style, naming, file structure.

D5

REINVENTED UTILITIES

Catches hand-rolled implementations of functionality that already exists in your codebase or standard library.

[ FAQ ]

DIRECT QUESTIONS.
DIRECT ANSWERS.

What is VibeCop?

VibeCop is Maiife's Architecture Integrity & Product Intelligence platform. It scores repositories with a 0–100 Architecture Integrity Index and flags architectural entropy in AI-generated code — hallucinated abstractions, duplicated logic, and pattern drift — before it merges.

What is the Architecture Integrity Index?

The Architecture Integrity Index is a 0–100 score of your codebase's structural health, computed as 100 minus entropy impact. It weighs four axes: Consistency, Reuse, Simplicity, and Structure.

What does VibeCop detect?

VibeCop runs nine architectural detector agents across four axes — hallucinated abstractions, semantic duplication, over-engineering, pattern drift, reinvented utilities, architectural complexity, layer violations, orphaned modules, and reintroduced bugs — plus seven static hygiene layers (dependency CVEs, dependency health, secrets, SAST, infrastructure-as-code, vendored drift, magic numbers) tracked separately from the index.

Does VibeCop work with GitHub?

Yes. VibeCop connects directly to GitHub repositories and reviews pull requests. Webhook auto-reviews trigger a full analysis on every PR open and sync.

How much does VibeCop cost?

VibeCop is free for everyone until December 31, 2026 — no card required, and nothing is billing. Pricing has not been finalised and will be announced before any plan starts billing.

How is VibeCop different from a linter?

Linters check line-level style and syntax. VibeCop analyzes architecture-level entropy — whether new code drifts from your team's established patterns, duplicates existing logic semantically, or adds unjustified abstraction — using a full code graph of your repository.

What is the VibeCop Plan Review MCP?

A remote MCP server that reviews your AI agent's implementation plan against your codebase's conventions before any code is written. It works with Claude Code, Cursor, Codex, and any MCP-capable agent over streamable HTTP with a Bearer token minted in VibeCop Settings.

How do I connect Claude Code or Cursor to VibeCop?

Mint an MCP token in VibeCop Settings, then add the server: claude mcp add --transport http vibecop https://api.gradus.maiife.ai/mcp/vibecop --header "Authorization: Bearer <TOKEN>" — or add the equivalent mcpServers entry to your agent's MCP config. Setup guide at vibecop.maiife.ai/mcp.

[ INITIALIZE ]

STOP REVIEWING
ARCHITECTURE BLIND

Free trial includes AI credits, full detector suite, and architecture graph.