claude

vibe

Persistent project context, auto-generated test harness, and disciplined development workflows for Claude Code.

3 on GitHubby dukesmith0v3.0.0MITupdated 6 months agoproductivity
/

Plugin vibe from marketplace vibe-marketplace in jwlutz/claude_code_framework. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (2)

  • risk-detection

    Detects code risks and security issues during review, risk scanning, or code evaluation. Writes findings to risks.md with impact level and file:line references.

  • vibe-context

    Auto-loads .vibe/ project context for commands and agents. Triggers on code questions, implementation, reviews, planning. Provides role-based context loading and API lookup chain.

Slash commands (13)

  • /vibe:add

    Import file or folder to .vibe/docs/ for reference - converts heavy formats, indexes automatically

  • /vibe:ask

    Answer questions about this codebase using .vibe/ context and code search

  • /vibe:commit

    Smart commit with test gate, .vibe/ sync, and optional PR creation

  • /vibe:go

    Full development workflow - explore, plan, implement, review, verify

  • /vibe:help

    Show available vibe commands and suggest next action based on project state

  • /vibe:init

    Analyze codebase and create .vibe/ context + debug/ test harness

  • /vibe:note

    Quick entry to any .vibe/ file - auto-detects type or accepts explicit type

  • /vibe:oneshot

    End-to-end workflow with minimal stops - clarify, implement, review, present

  • /vibe:plan

    Brainstorm, ask questions, create an implementation plan - then execute or save for later

  • /vibe:ralph

    Autonomous multi-task loop - decompose, implement and review each subtask, report results

  • /vibe:refresh

    Sync .vibe/ and debug/ after manual code changes outside vibe commands

  • /vibe:review

    Five-part adversarial review - code quality, bugs, functionality, risks, simplification

  • /vibe:tdd

    Test-driven development - write tests first, lock contract, implement until green

Subagents (4)

  • engineer

    Implements code changes following project patterns exactly. Use when code needs to be written or modified.

  • explorer

    Explores codebases to map architecture, patterns, and concerns. Use when you need to understand how code works before making changes.

  • reviewer

    Adversarial code review for bugs, security, functionality, and style. Use after code is written or modified.

  • tester

    Runs project tests, debug/ suite, and linters. Reports results with failure details. Use after code is written or modified.

View source on GitHub

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

caveman

claude

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

JuliusBrussee/caveman 119,462

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

Maintain vibe?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted