By chieflatif
VibeOS — Autonomous development engine with layered quality governance and source-cited evidence recall
Same-tree read-only architecture auditor for active VibeOS sessions with uncommitted code.
Isolated architecture audit agent that checks for layer violations, circular dependencies, contract breakage, and module boundary violations against the project's architecture document.
Backend implementation agent that receives a WO spec and pre-written tests, then implements code to make the tests pass while following architecture rules and the no-stub policy.
Same-tree read-only contract validator for active VibeOS sessions with uncommitted code.
Cross-boundary contract validation agent. Compares frontend API client calls, TypeScript types, and response handling against actual backend route definitions, Pydantic models, and response shapes. Finds field name mismatches, missing endpoints, and response shape divergences.
Full audit cycle that dispatches audit agents (security, architecture, correctness, test quality, evidence, product drift, flow, system invariants, dependency intelligence, delivery infrastructure, red team, contract validator), applies consensus logic, and produces a composite report with actionable findings. Use when the user says "audit the code", "review everything", "check for security issues", "do a full review", or wants a comprehensive multi-perspective code review.
Force VibeOS back into full autonomous session mode. Use when the user says "go autonomous", "stop checking in", "run on your own", "stay in autonomous mode", or wants VibeOS to keep building until it hits a real blocker, finishes the plan, or needs an explicit risk decision.
Autonomous build orchestrator that executes work orders end-to-end. Use when the user says "continue", "keep going", "build the next thing", "resume", "start building", or wants to make progress on the development plan. Dispatches investigator, tester, prompt-engineering, implementation, and documentation agents in sequence with two-layer quality enforcement (Layer 1 gates + Layer 2 audit agents) and error recovery, while checking for product drift and stale high-impact decisions.
Phase boundary audit that runs all gates and all audit agents on the entire codebase, establishes quality baselines, and enforces ratcheting (finding count cannot increase between phases). Use when the user says "phase is done", "wrap up this phase", "milestone check", or when all work orders in a phase are complete.
Complementary Audit Protocol — dispatches an independent audit via Codex (GPT-series) as auditor. Claude implements, Codex audits. Use at plan approval, WO closure, session end, or on demand. Claude must reconcile ALL material findings before closure — zero-technical-debt policy enforced (fix now or create a tracked WO, nothing dropped). Triggers: "codex audit", "audit with codex", "independent audit", "dual audit", "complementary audit", "/vibeos:codex-audit plan|complete|session|manual".
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
v2.2.0 — Evidence Recall Upgrade (2026-04-24)
This update adds a local, source-cited evidence recall utility. VibeOS can now build a compact index of work orders, audits, gate manifests, skills, session state, baselines, and checkpoints, then return bounded excerpts with citations instead of rereading large context bundles. It uses a generated
.vibeos/cache/file, has no network dependency, and does not add any external memory service.
v2.1.0 — Advanced Governance Upgrade (2026-04-03)
This update makes VibeOS smarter about how it reviews its own work. It can now check code quality while it's still building (instead of waiting until everything is saved), ask a second AI (Codex) to independently verify what it built, and automatically prevent work orders from growing too large or messy. It also blocks attempts to skip safety checks and protects test files from being weakened during implementation. If you're running multiple builds in parallel, VibeOS now enforces clear boundaries so they don't step on each other. Say "Upgrade VibeOS" inside any active session to get these improvements.
v2.0.0 — Verification Integrity Upgrade (2026-03-16)
This update came after VibeOS ran a fully autonomous 8-hour build session — 156 work orders, 6,175 passing tests, zero human intervention. Running at that scale revealed places where the system needed to be more careful about verifying its own work: catching stale code reviews, validating that the front-end and back-end agree with each other, remembering issues between sessions, and making sure old problems don't get quietly ignored forever. The system now verifies its own verification.
VibeOS turns Claude Code, Cursor, and Codex into a hands-on development partner. You do not need to learn a complicated workflow to get started. Open your project in the runtime you prefer, describe what you want in plain English, and VibeOS figures out whether to discover, plan, audit, explain, or keep building.
Think of it like this:
You can learn a few commands later if you want, but the normal way to use VibeOS is to talk to it naturally.
If you are not technical, this is the only part you really need:
That is enough to get started.
VibeOS is voice-driven and conversation-first. In practice, that means:
Examples:
| You say | VibeOS does |
|---|---|
| "I want to build a booking app for dog groomers" | Starts discovery and helps shape the product |
| "Build this as a competition-grade enterprise MVP" | Creates a compact VibOS Comp mission brief |
| "Make a plan for this" | Creates a phased development plan |
| "Keep going" | Continues the build loop |
| "What's the status?" | Gives a tactical update on the current or most recent session |
| "Give me a project status" | Gives an executive big-picture briefing on the whole project |
| "Go autonomous" | Puts VibeOS back into full autonomous session mode |
| "Audit this session" | Reviews everything completed in the current or last build session |
| "Check the code quality" | Runs quality gates and explains the result |
| "What is ratcheting?" | Explains the concept in plain English |
| "Help me understand this codebase" | Audits the project and maps what exists |
VibeOS — Autonomous development engine with layered quality governance
Your AI-powered Chief of Staff for enterprise sales. Self-personalizing — run /salessidekick:setup after installing to personalize (~45 min, one time). Then try /salessidekick:today for your first morning briefing. 22 commands, 11 skills, 6 Notion databases.
npx claudepluginhub chieflatif/codex-vibeos-plugin --plugin vibeosComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.