{ "markdown": "
\n \"VibeRaven\n\n

\n \"Website\"\n  \n \"Install\n  \n \"Join\n

\n\n

\n \"npm\n \"npm\n \"GitHub\n \"MIT\n \"skills.sh\n \"Follow\n

\n

\n Website ·\n Quickstart ·\n Agent skills ·\n Releases ·\n Discussions\n

\n
\n\nVibeRaven is an open-source local cockpit for AI-built apps. Run `npx -y viberaven` in your repo and it connects your coding agent (Claude Code, Cursor, Codex) to the context it patches blind without, your architecture, providers, and releases, then shows what is actually safe to ship to production, auth, RLS, webhooks, deploy, before real users hit it. Local-first, no login.\n\n```bash\nnpx -y viberaven\n```\n\n
\n \"VibeRaven\n
\n\n## Your stack, as a hand of cards\n\n
\n \"VibeRaven\n
\n\nVibeRaven deals your providers as a hand — each one graded, each one a card you play into your agent's next move. Supabase, Vercel, GitHub, Stripe, Sentry, Resend, Clerk, Upstash, and more.\n\n
\n \"All\n
\n\nThe Studio opens in your browser and works entirely on your machine: it detects your stack, finds your providers, puts your git releases on a timeline, and gives you a \"can I ship?\" verdict from offline checks. No login, no API key, no telemetry.\n\n## Your first 5 minutes\n\n1. **Run it.** `npx -y viberaven` in your project folder. The Studio opens in your browser and scans your repo offline.\n2. **Read your verdict.** The gate chip and Launch Signals show exactly what blocks launch, ranked. Click any signal, then click **Fix** to hand it to your agent.\n3. **Connect your coding agent.** Pick Codex, Claude Code, or Gemini CLI in the chat panel, hit **Test connection**, and choose how much access it gets (`ask`, `approve`, or `full`).\n4. **Open the Architecture map.** Pages, API, data, modules, and providers as a live draggable map. Weak boundaries glow red. Click one and press a plain-English action like *\"Protect user data (RLS)\"* or *\"Fix slow queries\"*.\n5. **Open the Worktree.** Your branches as a real tree. Uncommitted mess? One tap: *Commit with agent*. Branch ready? *Review* explains it in plain language and *Merge* does it safely.\n6. **Give your agent the skills.** Install the six-skill pack and the plugin so Codex, Claude Code, and Gemini follow the same senior-engineer loop everywhere:\n\n ```bash\n npx -y skills add ohad6k/VibeRaven --skill viberaven # skills.sh pack\n npx -y viberaven init --agents all # agent rules in-repo\n ```\n\nEverything the agent needs is also written to `.viberaven/` as markdown and JSON, readable by any tool and versioned by git.\n\n## What the Studio gives you\n\n| Capability | What it does |\n| --- | --- |\n| **Agent chat on your repo** | Drive Codex, Claude Code, or Gemini CLI from one cockpit, with connection health and live terminal output. |\n| **Access modes** | `ask`, `approve`, or `full`. The mode changes the real agent command it runs, not just the UI copy. |\n| **Context you can drag** | Drop a release, a provider card, or production memory into agent chat, so the agent patches with your product's real state instead of guessing. |\n| **Versions & releases** | Release diffs, tags, changelogs, and \"what changed since the last working release\" in plain English. |\n| **Providers via MCP** | Connect Supabase, Vercel, and Stripe. Provider status flows into agent prompts, and provider proof stays separate from repo-code fixes. |\n\n## The terminal twin: `viberaven check`\n\nFor agents and CI, the same verdict as one command:\n\n```bash\nnpx -y viberaven check\n```\n\n```text\nviberaven check · ~/my-app\n\n🔴 RLS disabled on public tables (rls_profiles)\n🟡 Service-role key referenced in client bundle (service_role_client)\n⚪ No error monitoring wired (monitoring_missing)\n\nVerdict: ❌ 1 blocker, 1 warning · score 62\nFix: viberaven fix · Details: .viberaven/agent-tasklist.md\n```\n\nOne line per finding, `file:line` evidence in the artifacts, exit code `1` on blockers. Then:\n\n```bash\nnpx -y viberaven fix # list gaps with safe automatic recipes\nnpx -y viberaven fix --gap # apply one recipe\nnpx -y viberaven --strict # final gate before deploy or CI\n```\n\nAll results land in `.viberaven/` as markdown and JSON on disk (`agent-tasklist.md`, `gate-result.json`, `context-map.json`), so any agent and your git history can read them.\n\n## Install for AI agents\n\nMake agents use release and provider context before they patch the repo:\n\n```bash\nnpx -y viberaven init --agents all\nnpx -y viberaven doctor --agents\n```\n\nPreview without writing files:\n\n```bash\nnpx -y viberaven init --agents all --dry-run\n```\n\nThis installs bounded rules (`` ... ``) into:\n\n- `AGENTS.md`, `CLAUDE.md`, `GEMINI.md`\n- `.cursor/rules/viberaven-core.mdc` (plus scoped Supabase, deploy, and payments rules)\n- `.github/copilot-instructions.md`\n- `.viberaven/agent-context.md`, `.viberaven/mission-map.md`\n\nThe rules teach the loop: `check`, read `.viberaven/`, fix one gap, then `check` again until `gate.status === \"clear\"`.\n\n## Agent skills\n\nSix [skills.sh](https://skills.sh) skills route agents through architecture questions, version evidence, and launch proof:\n\n| Skill | Job |\n| --- | --- |\n| `viberaven` | The router: local check/fix loop, Studio, and MCP context. |\n| `architecture-context` | Ask the missing product questions before any edit. |\n| `architecture-plan` | Turn answers plus repo evidence into a workstream plan. |\n| `what-broke` | Find which version broke the app before patching. |\n| `production-context` | Keep compact production memory in `.viberaven/production-context.md`. |\n| `go-live` | Local app to GitHub to Vercel, with live-URL proof. |\n\n```bash\nnpx -y skills add ohad6k/VibeRaven --skill viberaven\n```\n\nSee [agent-skills/](./agent-skills/) for the full pack.\n\nThis repo also works as an agent **plugin**: `plugin.yaml`, `.claude-plugin/`, `.codex-plugin/`, and `gemini-extension.json` expose the six skills plus `/viberaven-work`, `/viberaven-help`, `/viberaven-production-context`, and `/viberaven-launch` commands to Claude Code, Codex, and Gemini CLI.\n\n## MCP\n\nVibeRaven is listed in the MCP registry for agents that prefer tools over terminal commands:\n\n```json\n{ \"viberaven\": { \"command\": \"npx\", \"args\": [\"-y\", \"viberaven\", \"--mcp\"] } }\n```\n\nKey tools: `viberaven_check_readiness` (runs the local check), `viberaven_heal_apply`, `viberaven_verify`, `viberaven_audit`, `viberaven_provider_verify`, and `viberaven_validate_npm_package` (run it before adding npm dependencies).\n\n## Vercel + Supabase\n\n```bash\nnpx -y viberaven audit --vercel-supabase\n```\n\nLocal evidence checks for RLS proof, service-role exposure, and pooler ports before you claim \"production ready.\"\n\n## Philosophy\n\n- **Local-first.** The CLI and Studio run on your machine. No login, no API key, no telemetry, no scan quota.\n- **Markdown on disk.** All context lives in `.viberaven/` as plain files that your agent and your git history can read.\n- **Evidence over vibes.** Findings point at repo evidence. Provider dashboard state is never claimed from repo edits alone.\n- **Non-destructive.** Fix recipes are guarded, cleanup is plan-only, and nothing is pushed or deployed for you.\n\n## Contributing\n\nContributions are welcome, and most of them need no private source access:\n\n- Read the [contribution guide](./CONTRIBUTING.md) for repo structure, PR expectations, and local checks.\n- Pick up a [good first issue](https://github.com/ohad6k/VibeRaven/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22): docs, provider fixtures, examples, and translations.\n- Share ideas or questions in [Discussions](https://github.com/ohad6k/VibeRaven/discussions).\n- Join the [Discord](https://discord.gg/ZAJvazz63Y) to talk to the maintainer directly.\n\n## Resources\n\n- Agent-ready starter template: [examples/nextjs-supabase-vercel-production-ready-template](./examples/nextjs-supabase-vercel-production-ready-template/)\n- Machine-readable docs: [llms.txt](./llms.txt) · [llms-full.txt](https://viberaven.dev/llms-full.txt) · [skills.json](https://viberaven.dev/skills.json) · [skills.sh.json](./skills.sh.json)\n- Example proof artifacts: [examples/proof/](./examples/proof/)\n- Website: [viberaven.dev](https://viberaven.dev) · npm: [viberaven](https://www.npmjs.com/package/viberaven) · Issues: [ohad6k/VibeRaven/issues](https://github.com/ohad6k/VibeRaven/issues)\n\n## License\n\n[MIT](./LICENSE). Current public release: `viberaven@1.4.2`.\n\nIf VibeRaven helps you ship, star the repo so other AI app builders can find it. Use **Watch → Custom → Releases** for release notifications.\n\n> This public repo is the agent discovery and installation surface. Product source development happens in a private repository.\n", "bytes": 11211, "sha": "1c4f00db3ef15dadef62faa6ff78ec4ad84371e36be63d581e677e70c35f7f5f", "repo_slug": "ohad6k/viberaven", "fonte": "repo", "truncated": false, "api": "https://agentalog.com/api/listings/plg_ohad6k_viberaven_225e8808/readme" }