vibeos

Plugin vibeos from marketplace vibeos in chieflatif/codex-vibeos-plugin. Commands read from the repo's manifest — 1 month ago.

Skills (27)

• vibeos-audit

  VibeOS audit flow for Codex. Use when the user asks for a code audit, quality review, governance review, architecture review, security review, or wants a full audit cycle before or after implementation work.

• vibeos-autonomous

  Full autonomous-session override for VibeOS in Codex. 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 a real blocker or decision appears.

• vibeos-build

  Autonomous VibeOS work-order execution for Codex. Use when the user says continue, resume, keep going, build the next thing, start implementing, or wants progress against the current VibeOS plan.

• vibeos-checkpoint

  Phase-boundary checkpoint and ratchet review for VibeOS in Codex. Use when the user says phase is done, milestone check, checkpoint this phase, or wants a boundary audit before starting the next phase.

• vibeos-comp

  Compact enterprise MVP mission intake for VibOS Comp. Use for competition-grade builds, enterprise design-partner MVPs, rapid production-quality prototypes, battle harness runs, or explicit VibOS Comp/VibeOS Comp requests.

• vibeos-discover

  Discovery, project shaping, and codebase understanding for VibeOS in Codex. Use when the user describes what they want to build, wants help understanding an existing codebase, needs initial governance artifacts, or wants product and architecture context created before planning.

• vibeos-gate

  Run VibeOS quality gates from Codex. Use when the user says check the code, run quality checks, validate this, are we passing, pre-commit check, or wants gate status before closing a work order.

• vibeos-help

  Explain VibeOS concepts and route the user to the right Codex workflow. Use when the user asks what a VibeOS term means, wants the difference between status and project status, needs help choosing a workflow, or wants the system explained in plain English.

• vibeos-plan

  VibeOS planning and work-order generation for Codex. Use when the user says make a plan, break the work down, organize the roadmap, create work orders, or wants governance and sequencing created after discovery.

• vibeos-project-status

  Executive VibeOS project briefing for Codex. Use when the user asks for project status, the big picture, overall progress, founder update, executive summary, or wants business meaning rather than session details.

• vibeos-session-audit

  Closeout audit for the current or most recent VibeOS build session in Codex. Use when the user says audit this session, review this run, session audit, or wants a trustworthy end-to-end review of what happened in the latest build session.

• vibeos-status

  Tactical VibeOS session status for Codex. Use when the user asks what's the status, what's in flight, where are we in this session, or wants a near-term update on current work rather than a strategic project briefing.

• vibeos-wo

  Work Order management for VibeOS in Codex. Use when the user wants to create a WO, inspect WO status, mark a WO complete, audit a WO, or manage an individual unit of work inside the VibeOS plan.

• audit

  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 actionabl

• autonomous

  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.

• checkpoint

  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 p

• codex-audit

  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

• comp

  Create a compact VibOS Comp enterprise MVP mission brief. Use when the user wants a competition-grade build, rapid but production-quality MVP, enterprise design-partner prototype, battle harness run, or says VibOS Comp/VibeOS Comp.

• discover

  Run product discovery to turn a rough idea into validated product, anchor, and governance documents. Use when a user describes what they want to build, shares a product idea, says "I want to build/create/make...", mentions a "new project/app/product", or needs help defining scope, requirements, arch

• gate

  Run quality gates for a specific WO lifecycle phase. Use when the user says "check the code", "run quality checks", "are we passing?", "validate this", or wants to run pre-commit checks or verify code quality before completing a work order.

• help

  Get help with VibeOS concepts, glossary terms, and system orientation. Use when the user asks "what is/are...", "explain...", "how does X work?", "what does Y mean?", or wants to understand any term or concept used by the plugin, or to re-trigger the onboarding introduction.

• plan

  Run project intake questionnaire, apply decision engine, and generate a complete development plan with phased work orders. Use when the user says "make a plan", "break this down", "organize the work", "create a roadmap", or wants to structure their project into phases. Requires product discovery to

• project-status

  Show a founder-style executive project status briefing. Use when the user asks "project status", "where are we overall?", "give me the big picture", "executive briefing", "founder update", "program status", or wants a strategic, evidence-based view of overall progress, risks, business impact, and de

• session-audit

  Audit the current or most recent VibeOS build session end-to-end. Use when the user says "audit this session", "review what happened in this session", "session audit", or wants a closeout review of the work completed during an autonomous run.

• status

  Show tactical session status for the current or most recent work session. Use when the user asks "what's the status?", "where are we in this session?", "remind me what we're doing", "what's in flight?", "what still needs doing right now?", or wants a micro-level update on the active work.

• upgrade

  Framework upgrade orchestrator that copies new framework files, reconciles configuration, re-evaluates the decision engine against the project, runs all gates and auditors as a discovery sweep (not a baseline), and produces prioritized recommendations for integration and correction. Use when the use

• wo

  Work order management with subcommands for creating, checking status, completing, and auditing individual work orders. Use when the user says "create a work order", "add a task", "what's the status of WO-X?", or wants to manage individual units of work.

Subagents (32)

• architecture-auditor-same-tree

  Same-tree read-only architecture auditor for active VibeOS sessions with uncommitted code.

• architecture-auditor

  Isolated architecture audit agent that checks for layer violations, circular dependencies, contract breakage, and module boundary violations against the project's architecture document.

• backend

  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.

• contract-validator-same-tree

  Same-tree read-only contract validator for active VibeOS sessions with uncommitted code.

• contract-validator

  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.

• correctness-auditor-same-tree

  Same-tree read-only correctness auditor for active VibeOS sessions with uncommitted code.

• correctness-auditor

  Isolated correctness audit agent that uses deep reasoning to find logic errors, missing error paths, incomplete implementations, and hardcoded values. Each finding includes a "would a user notice?" impact statement.

• delivery-infrastructure-auditor-same-tree

  Same-worktree Delivery Infrastructure Auditor for fast session-scoped review of CI/CD, deployment path, environment/secrets, observability, smoke checks, rollback, and runbook evidence.

• delivery-infrastructure-auditor

  Read-only auditor that validates CI/CD, deployment path, environment configuration, secrets handling, runtime observability, smoke/health checks, rollback, and operational evidence. Use for Comp outputs, production-ready MVPs, deployment changes, infrastructure changes, or autonomous delivery claims

• dependency-intelligence-auditor-same-tree

  Same-worktree Dependency Intelligence Auditor for fast session-scoped review of current dependency evidence, version choices, lockfiles, compatibility, package manager drift, and transitive risk.

• dependency-intelligence-auditor

  Read-only auditor that validates dependency decisions against current evidence, runtime compatibility, lockfile discipline, transitive risk, security posture, and upgrade paths. Use for Comp outputs, stack selection, package additions, framework upgrades, or any WO that changes dependency manifests.

• doc-writer

  Documentation agent that updates project docs after implementation, records implementation notes and evidence in the WO file, and updates tracking documents.

• evidence-auditor-same-tree

  Same-tree read-only evidence auditor for active VibeOS sessions with uncommitted code.

• evidence-auditor

  Isolated evidence audit agent that validates documentation completeness, evidence bundles, WO audit framework compliance, and tracking document accuracy across all completed work orders.

• flow-auditor-same-tree

  Same-worktree Flow Auditor for fast session-scoped review of user journeys, frontend/backend handoffs, auth/session continuity, and objective fidelity without creating an isolated worktree.

• flow-auditor

  Read-only auditor that validates whether the intended user journey actually works end to end across UI, auth, backend, data, security boundaries, errors, and objective fidelity. Use when reviewing integrated product behavior, Comp outputs, frontend/backend handoffs, or mission alignment.

• frontend

  Frontend implementation agent that follows the same TDD pattern as the backend agent, implementing UI code to make pre-written tests pass while following architecture and accessibility standards.

• integration-captain

  Integration owner for VibOS Comp parallel work. Reads COMP-PLAN.md and worktree scopes, verifies branch evidence, enforces merge order, runs integrated checks, and records unresolved risks without claiming unproven merges or deployments.

• investigator

  Pre-flight analysis agent that revalidates WO assumptions, checks dependency completion, analyzes relevant codebase, and flags risks before implementation begins. It also checks anchor alignment and whether high-impact external decisions have current evidence. Dispatched at the start of each WO.

• plan-auditor

  Read-only audit agent that evaluates a work order against the 10-question WO-AUDIT-FRAMEWORK planning checklist. Returns structured findings with severity ratings. Use before approving any WO for implementation.

• product-drift-auditor-same-tree

  Same-tree read-only product drift auditor for active VibeOS sessions with uncommitted code.

• product-drift-auditor

  Read-only audit agent that checks whether the current work is drifting from the Product Anchor, Engineering Principles, and current-evidence standards. Use when work must be validated against the product promise, intended experience, anti-shortcut rules, or freshness requirements.

• prompt-engineer

  Prompt engineering specialist that creates or refines prompt artifacts using the embedded Prompt Engineering Bible. Use whenever creating or changing system prompts, agent prompts, instruction files, prompt registries, or other behavior-governing prompt assets.

• red-team-auditor-same-tree

  Same-tree read-only red-team auditor for active VibeOS sessions with uncommitted code.

• red-team-auditor

  Adversarial agent that hunts for ways tests could pass while software is broken. Finds cheating patterns, mock-reality divergence, vacuous assertions, and status inflation. Reports a corruption score.

• security-auditor-same-tree

  Same-tree read-only security auditor for active VibeOS sessions with uncommitted code.

• security-auditor

  Isolated security audit agent that performs OWASP Top 10 analysis, secrets detection, injection pattern scanning, and PII exposure checks. Returns structured findings with severity and confidence ratings.

• system-invariant-auditor-same-tree

  Same-worktree System Invariant Auditor for fast session-scoped review of state rules, ownership guarantees, retries, concurrency, partial failure, and recovery behavior without creating an isolated worktree.

• system-invariant-auditor

  Read-only auditor that validates system invariants: rules that must always remain true across state transitions, auth boundaries, data ownership, retries, concurrency, partial failure, recovery, and future change. Use for Comp outputs, enterprise MVP foundations, critical workflows, data models, aut

• test-auditor-same-tree

  Same-tree read-only test auditor for active VibeOS sessions with uncommitted code.

• test-auditor

  Isolated test quality audit agent that evaluates whether tests were written from spec, detects fallback masking, checks mock density, verifies edge coverage, and analyzes git history for TDD compliance.

• tester

  TDD agent that reads a WO spec and acceptance criteria, then writes tests BEFORE implementation exists. Never reads implementation code. Tests define expected behavior from the spec.

Hooks (13)

• SessionStart

  ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/prereq-check.sh

• UserPromptSubmit

  ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/governance-guard.sh

• UserPromptSubmit

  ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/intent-router.sh

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/worktree-bash-guard.sh

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/secrets-scan.sh

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/frozen-files.sh

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/test-file-protection.sh

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/test-diff-audit.sh

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/worktree-scope-guard.sh

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/proof-protection.sh

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/file-budget.sh

• Stop

  ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/response-quality-stop.sh

• Stop

Similar plugins