Vibe Drift Tracker — AI skill for Claude Code
Vibe coding without creating AI Slop.
How to install Vibe Drift Tracker
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open The-Vibe-Company/vibe-drift-tracker and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Vibe Drift Tracker does
Vibe coding without creating AI Slop. Check in real time your Drift. VS Code Extension that integrates with Claude Code.
Alternatives in AI
- Manifest — Real-time cost observability for OpenClaw agents — track tokens, costs, messages, and model usage 4.1k ★
- Sentrux — Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improveme 2.9k ★
- CodeIsland — Real-time AI coding agent status panel in your MacBook notch — live status, approvals & replies for 13 AI tool 2.3k ★
README
Vibe Drift Tracker
**Track your AI interactions per commit. Detect drift before it derails your project.**
You start with a clear goal, open Claude Code, and 47 prompts later you've refactored half the codebase and added three features nobody asked for. We've all been there.
Vibe Drift Tracker measures how many AI prompts go into each commit, how many lines each prompt produces, and whether your session is drifting from focused work into feature creep.
How It Works
- Install the extension — One click in VS Code.
- Code with Claude — Write code, ask questions, iterate. We silently count.
- See your drift live — Watch your drift score update in real time as you code.
- Commit your work — Every git commit saves a snapshot of your session.
- Track your history — Prompts, lines changed, drift score — commit by commit.
VibeDrift calculates a drift score on every prompt and resets it to 0 after each commit. Under the hood, it parses Claude Code session logs from `~/.claude/projects/` and combines them with git metadata (diff stats, files changed, branch) to produce a per-commit analysis.
Every commit gets a **drift score** and a **drift level**:
| Level | Score | Meaning |
|---|---|---|
| very-low | < 1.2 | Minimal interaction, on track |
| low | < 2.5 | Focused, on track |
| moderate | < 4 | Starting to wander |
| high | < 7 | Significant drift from original task |
| vibe-drift | 7+ | You've lost the plot — time to reset |
Scoring
The drift score is based on two factors:
- Prompt count — more prompts per commit = more drift
- Lines per prompt — a high ratio (50+ lines/prompt) means productive work and lowers the score; a low ratio (< 5 lines/prompt) means
Related Skills
Vibe Cockpit
Real-time monitoring dashboard for AI coding agent fleets: session health, output streaming, and observability
Claude Usage Tracker
Native macOS menu bar app for tracking Claude AI usage limits in real-time. Built with Swift/SwiftUI.
Skills Tracker
Real-time tracking of every new GitHub 'skills' repo to capture the AI agent skill ecosystem trend
Aippy
Aippy is an AI Vibe Coding platform powered by the Claude large model. It is built on the React framework and
ClaudeCodeStatusLine
Display real-time Claude Code model info, token usage, and rate limits in a compact status line without affect
Variant Skill
AI skill: convert raw HTML into a webto.id section variant (WVF). Issue tracker for @webto-id/variant-check.
Related Agents
Signature Historian
Drift / change / evolution tracker. Ships with CogSig for signature-drift detection across sessions + availabl
Visual QA
Read-heavy visual QA role for real game/app states. Captures or inspects mobile/desktop evidence, flags clippi
Execution Agent
Autonomously executes a single subtask in its own worktree. Reads plan + subtask spec + declared context, impl