[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-84101":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":15,"stars7d":16,"stars30d":16,"stars90d":15,"forks30d":15,"starsTrendScore":16,"compositeScore":17,"rankGlobal":10,"rankLanguage":10,"license":18,"archived":19,"fork":19,"defaultBranch":20,"hasWiki":21,"hasPages":19,"topics":22,"createdAt":10,"pushedAt":10,"updatedAt":37,"readmeContent":38,"aiSummary":10,"trendingCount":15,"starSnapshotCount":15,"syncStatus":39,"lastSyncTime":40,"discoverSource":41},84101,"omnistack-agent","Ricar66\u002Fomnistack-agent","Ricar66","Platform-agnostic AI agent: one Full-Stack Software Engineer brain, compiled into ready-to-paste adapters for ChatGPT, Claude, Copilot, Gemini & Cursor. Zero-dependency, MIT.","",null,"JavaScript",66,19,51,0,5,46.9,"MIT License",false,"main",true,[23,24,25,26,27,28,29,30,31,32,33,34,35,36],"ai-agents","ai-tools","chatgpt","claude-code","cursor","developer-tools","full-stack","gemini","github-copilot","llm","open-source","prompt-engineering","software-engineering","system-prompts","2026-06-12 04:01:42","![omnistack-agent](assets\u002Fbanner.svg)\n\n![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-green.svg) · ![PRs Welcome](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPRs-welcome-brightgreen.svg) · ![Platforms](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fplatforms-ChatGPT%20%C2%B7%20Claude%20%C2%B7%20Copilot%20%C2%B7%20Gemini%20%C2%B7%20Cursor%20%C2%B7%20Generic-blue.svg)\n\n**[🇧🇷 Ler em Português](README.pt-BR.md)**\n\n## What is this\n\n**omnistack-agent** is an open-source, platform-agnostic system prompt that turns any capable AI model into a **Full Stack Software Engineering Specialist** — one agent that fluidly takes on whichever engineering role a task needs, with object-oriented design as its default lens. The agent's \"brain\" is authored once in a single source (`core\u002F` + `knowledge\u002F`) and compiled by a tested, zero-dependency Node script into ready-to-use adapter files for every major AI platform. You don't write prompts — you copy a file.\n\nIt can take on all ten of these roles:\n\n- **Software Architect** — system structure, boundaries, and trade-offs (ADRs included).\n- **Full Stack Developer** — end-to-end features across UI, API, and data.\n- **Mobile Developer** — native and cross-platform apps, offline, and push.\n- **Backend Engineer** — domain logic, services, jobs, and data integrity.\n- **Frontend Engineer** — accessible, performant UIs and predictable state.\n- **Database Administrator** — schemas, indexing, migrations, and tuning.\n- **DevOps Engineer** — CI\u002FCD, Infrastructure as Code, and rollbacks.\n- **QA Engineer** — test plans, automated suites, and sharp bug reports.\n- **Technical Writer** — READMEs, API references, and architecture docs.\n- **Software Mentor** — the *why* behind the code, with runnable examples.\n\n## ▶️ How to use\n\nPick your platform, copy the listed file's contents, and paste it where that platform expects its instructions. No build step is required to consume the agent — the adapters are pre-generated and committed.\n\n| Platform | File to copy | How to install |\n| --- | --- | --- |\n| **ChatGPT** (Custom GPT) | [`adapters\u002Fchatgpt\u002Fcustom-gpt-instructions.md`](adapters\u002Fchatgpt\u002Fcustom-gpt-instructions.md) | Create a new GPT → open **Configure** → paste the file into the **Instructions** box (this is the lean variant). For the complete knowledge inlined (larger; best used as an API system prompt), use [`adapters\u002Fchatgpt\u002Fsystem-prompt.md`](adapters\u002Fchatgpt\u002Fsystem-prompt.md). |\n| **Claude** (Skill) | [`adapters\u002Fclaude\u002FSKILL.md`](adapters\u002Fclaude\u002FSKILL.md) | Drop the file into your project's skills folder (e.g. `.claude\u002Fskills\u002Fomnistack-agent\u002FSKILL.md`); it ships with YAML frontmatter and is user-invocable. |\n| **Claude** (Agent) | [`adapters\u002Fclaude\u002Fagent.md`](adapters\u002Fclaude\u002Fagent.md) | Register it as a subagent in `.claude\u002Fagents\u002F`; the frontmatter already sets the name, description, and model. For repo-wide guidance instead, use [`adapters\u002Fclaude\u002FAGENTS.md`](adapters\u002Fclaude\u002FAGENTS.md). |\n| **GitHub Copilot** | [`adapters\u002Fcopilot\u002Fcopilot-instructions.md`](adapters\u002Fcopilot\u002Fcopilot-instructions.md) | Save it as `.github\u002Fcopilot-instructions.md` at your repository root → reload Copilot. |\n| **Gemini** (Gem) | [`adapters\u002Fgemini\u002Fgem-instructions.md`](adapters\u002Fgemini\u002Fgem-instructions.md) | Create a new Gem in Gemini → paste the file into the **Instructions** field → save. |\n| **Cursor \u002F Windsurf** | [`adapters\u002Fcursor\u002FAGENTS.md`](adapters\u002Fcursor\u002FAGENTS.md) | Place it as `AGENTS.md` at your project root so the editor picks it up automatically. |\n| **Generic** (any LLM) | [`adapters\u002Fgeneric\u002Fsystem-prompt.md`](adapters\u002Fgeneric\u002Fsystem-prompt.md) | Paste the file as the **system prompt** of any chat or API request (OpenAI, Anthropic, local models, etc.). |\n\n> Full per-platform walkthroughs with screenshots-worthy detail live in [`docs\u002Fplatforms.md`](docs\u002Fplatforms.md).\n\n## 🤝 How to contribute\n\nContributions are welcome — new knowledge modules, language seeds, fixes, and translations all help. There is **one golden rule**:\n\n> **Edit `core\u002F` or `knowledge\u002F` — never edit `adapters\u002F`.** The adapter files are *generated*. Hand-edits are overwritten by the next build and rejected by CI.\n\nThe workflow:\n\n1. **Edit the source.** Change a numbered file in `core\u002F`, or add\u002Fupdate a module under `knowledge\u002F` (and link it in `knowledge\u002F_index.md`).\n2. **Rebuild the adapters.** Run `npm run build` to regenerate every file under `adapters\u002F`.\n3. **Verify.** Run `node --test` (unit tests) and `npm run validate` (confirms the adapters match the source).\n4. **Open a PR.** CI runs `npm run validate`, so a PR fails if the committed adapters drift from `core\u002F` + `knowledge\u002F`. Always commit the regenerated adapters alongside your source change.\n\nRequirements: **Node ≥ 18**, zero npm dependencies. See [`CONTRIBUTING.md`](CONTRIBUTING.md) for the full guide, including the knowledge-module template and commit conventions.\n\n## 🗂️ Repository structure\n\n```text\nomnistack-agent\u002F\n├── core\u002F        # The agent's brain (single source): identity, principles,\n│                #   capabilities, workflow, interaction style, guardrails.\n├── knowledge\u002F   # Modular knowledge base — one topic per Markdown file,\n│                #   indexed by knowledge\u002F_index.md.\n├── adapters\u002F    # GENERATED per-platform output. Do not edit by hand.\n├── scripts\u002F     # Zero-dependency Node build (build.mjs), drift-detecting\n│                #   validate (validate.mjs), pure lib + tests.\n├── docs\u002F        # Guides: architecture, adding knowledge, platforms.\n└── assets\u002F      # Banner and other static media.\n```\n\n## 🛣️ Roadmap\n\n- More languages and frameworks in `knowledge\u002F` (Python, Go, Rust, Vue, Angular, .NET MAUI, and more).\n- Additional platform adapters as new AI tools emerge.\n- A curated `examples\u002F` folder with real prompts and the agent's responses.\n- A full Brazilian-Portuguese translation of the knowledge modules (the README and docs are already bilingual).\n- Deeper modules per domain, expanding the seeds into complete references.\n\n## 📄 License\n\nReleased under the **MIT License** — free to use, modify, and distribute. See [`LICENSE`](LICENSE).\n",2,"2026-06-11 04:12:18","CREATED_QUERY"]