{"slug": "show-hn-viberaven-production-workflows-for-ai-coding-agents", "title": "Show HN: VibeRaven – Production workflows for AI coding agents", "summary": "VibeRaven, a new open-source tool for AI coding agents, provides production workflows that enforce evidence-based task completion, separating code fixes from provider dashboard work and requiring approval before risky changes. The tool includes a local Studio cockpit, plugin-style metadata, and skills for tasks like RLS design, webhook handling, and launch readiness.", "body_md": "**Ship AI-built apps with evidence, not vibes.**\n\n**Open the full-quality MP4 demo**\n\nVibeRaven is the **VibeRaven Production Skills** plus a local Studio cockpit for AI-built apps. Use it while building, fixing, reviewing releases, or preparing a launch when an agent needs provider context, release context, approval-aware chat, safe repo changes, and evidence before it claims the work is ready.\n\n```\nnpx -y viberaven\n```\n\nThe public repo is the agent discovery and installation surface: plugin-style metadata, portable slash commands, production skills, MCP notes, and AI-readable docs.\n\nAI coding agents are good at patching code and bad at knowing what they cannot prove. VibeRaven Production Skills are not passive reports; they are task workflows an agent can use while implementing, reviewing, debugging, or preparing launch-sensitive work.\n\nVibeRaven gives agents a contract:\n\n- say what evidence was found;\n- say what evidence is missing;\n- separate repo-code fixes from provider dashboard work;\n- use MCP or connected provider context when available;\n- keep release and version context visible;\n- ask for approval before risky local changes.\n\nThat matters during feature work, auth fixes, billing changes, deploy debugging, release comparison, post-launch drift, and production readiness.\n\nOpen the local cockpit from any project:\n\n```\nnpx -y viberaven\n```\n\nStudio gives you agentic chat, draggable providers, draggable versions/releases, provider MCP context, terminal output, diff context, access-mode control, and CLI-agent connection checks. Installed is not the same as connected; test the agent connection before real chat control.\n\nInstall bounded VibeRaven guidance for Codex, Claude Code, Cursor, Copilot, Gemini, and related agents:\n\n```\nnpx -y viberaven init --agents all\n```\n\nPreview without writing files:\n\n```\nnpx -y viberaven init --agents all --dry-run\n```\n\nThe installer writes rules into supported agent instruction files, including `AGENTS.md`\n\n, `CLAUDE.md`\n\n, `GEMINI.md`\n\n, Cursor rules, Copilot instructions, and `.viberaven`\n\ncontext files.\n\nVibeRaven ships as a portable skill/plugin-style pack:\n\n- Codex:\n`.codex-plugin/plugin.json`\n\n- Claude Code:\n`.claude-plugin/plugin.json`\n\n- Gemini CLI:\n`gemini-extension.json`\n\n- Generic plugin hosts:\n`plugin.yaml`\n\n- Slash-command prompts:\n`commands/`\n\nCommand entry points:\n\n`/viberaven-help`\n\n: show the pack and output contract.`/viberaven-work`\n\n: use Production Skills on a task.`/viberaven-launch`\n\n: run launch readiness before saying ready.`/viberaven-provider-actions`\n\n: separate repo-code fixes from dashboard work.\n\nSee [docs/agent-portability.md](/ohad6k/VibeRaven/blob/main/docs/agent-portability.md).\n\nBrowse the skill library in [docs/production-skills.md](/ohad6k/VibeRaven/blob/main/docs/production-skills.md).\n\n| Skill | What It Helps Agents Do |\n|---|---|\n`supabase-rls` |\nDesign or repair RLS work while separating repo SQL from live dashboard state. |\n`stripe-webhooks` |\nImplement safer webhook handling, idempotency, mode separation, and provider follow-up. |\n`vercel-env-sync` |\nFix env assumptions across local, preview, and production without guessing dashboard values. |\n`clerk-callbacks` |\nDebug auth callback, redirect, preview URL, and route-protection drift. |\n`sentry-signal` |\nWire or review monitoring so installed SDKs are not mistaken for working signal. |\n`release-review` |\nReview diffs and guide release-risk fixes for provider, auth, billing, env, data, and monitoring changes. |\n`provider-actions` |\nSplit what the agent can edit in repo from what a human or MCP/provider tool must handle. |\n`launch-readiness` |\nPull together implementation status, verification output, provider gaps, and next actions. |\n`evidence-first` |\nKeep claims honest when repo code, MCP context, or provider evidence is incomplete. |\n\n```\nnpx -y skills add ohad6k/VibeRaven --skill viberaven\n```\n\nVibeRaven can be exposed to MCP-aware agents:\n\n```\n{ \"viberaven\": { \"command\": \"npx\", \"args\": [\"-y\", \"viberaven\", \"--mcp\"] } }\n```\n\nUse MCP output as provider and readiness context for Studio-aware agents. The repo also keeps MCP registry metadata in [docs/mcp-registry-submission.md](/ohad6k/VibeRaven/blob/main/docs/mcp-registry-submission.md) so maintainers can verify the public MCP discovery surface alongside npm and skills.sh metadata.\n\n[examples/nextjs-supabase-vercel-production-ready-template](/ohad6k/VibeRaven/blob/main/examples/nextjs-supabase-vercel-production-ready-template) includes agent rules and `viberaven:*`\n\nscripts for Next.js + Supabase + Vercel.\n\n[llms-full.txt](https://viberaven.dev/llms-full.txt)[llms.txt](/ohad6k/VibeRaven/blob/main/llms.txt)[skills.json](https://viberaven.dev/skills.json)[skills.sh.json](/ohad6k/VibeRaven/blob/main/skills.sh.json)[Production Protocol guide](https://viberaven.dev/viberaven-production-protocol-ai-built-apps.md)[Example evidence artifacts](/ohad6k/VibeRaven/blob/main/examples/proof)\n\nOlder VibeRaven docs and compatibility tools may mention agent-mode scans, task lists, gate results, PRP resources, or scan-derived action manifests. Treat that language as compatibility context, not the main public product surface.\n\nThe current default is the Studio:\n\n```\nnpx -y viberaven\n```\n\nNormal git push is not gated. VibeRaven language about readiness is about production-change confidence, release review, provider-aware evidence, and agent boundaries, not blocking ordinary repository work.\n\n- Website:\n[viberaven.dev](https://viberaven.dev) - npm:\n[viberaven](https://www.npmjs.com/package/viberaven) - Issues:\n[ohad6k/VibeRaven/issues](https://github.com/ohad6k/VibeRaven/issues) - Public discovery repo:\n[ohad6k/VibeRaven](https://github.com/ohad6k/VibeRaven)", "url": "https://wpnews.pro/news/show-hn-viberaven-production-workflows-for-ai-coding-agents", "canonical_source": "https://github.com/ohad6k/VibeRaven", "published_at": "2026-06-29 09:57:19+00:00", "updated_at": "2026-06-29 10:30:03.239166+00:00", "lang": "en", "topics": ["ai-agents", "developer-tools", "ai-tools"], "entities": ["VibeRaven", "Codex", "Claude Code", "Cursor", "Copilot", "Gemini", "MCP"], "alternates": {"html": "https://wpnews.pro/news/show-hn-viberaven-production-workflows-for-ai-coding-agents", "markdown": "https://wpnews.pro/news/show-hn-viberaven-production-workflows-for-ai-coding-agents.md", "text": "https://wpnews.pro/news/show-hn-viberaven-production-workflows-for-ai-coding-agents.txt", "jsonld": "https://wpnews.pro/news/show-hn-viberaven-production-workflows-for-ai-coding-agents.jsonld"}}