{"id":47178552,"url":"https://github.com/first-fluke/oh-my-agent","last_synced_at":"2026-06-10T03:01:06.029Z","repository":{"id":335479608,"uuid":"1145914675","full_name":"first-fluke/oh-my-agent","owner":"first-fluke","description":"Portable, vendor-agnostic agent harness for project-specific skills, workflows, and agent teams aligned with your codebase, conventions, and engineering standards.","archived":false,"fork":false,"pushed_at":"2026-06-04T06:22:14.000Z","size":64650,"stargazers_count":1055,"open_issues_count":1,"forks_count":121,"subscribers_count":4,"default_branch":"main","last_synced_at":"2026-06-04T06:23:27.086Z","etag":null,"topics":["agent-harness","agent-skills","agentic-coding","ai-agents","claude-code","codex","cursor","multi-agent","multi-agent-systems","oh-my-agent","opencode","orchestration","orchestrator","serena"],"latest_commit_sha":null,"homepage":"https://firstfluke.com/oh-my-agent/","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/first-fluke.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":"SECURITY.md","support":"docs/SUPPORTED_AGENTS.md","governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null},"funding":{"github":"first-fluke","buy_me_a_coffee":"firstfluke"}},"created_at":"2026-01-30T11:29:46.000Z","updated_at":"2026-06-04T06:22:18.000Z","dependencies_parsed_at":"2026-03-30T05:03:18.993Z","dependency_job_id":null,"html_url":"https://github.com/first-fluke/oh-my-agent","commit_stats":null,"previous_names":["first-fluke/oh-my-antigravity","first-fluke/oh-my-agent","first-fluke/oh-my-ag"],"tags_count":397,"template":false,"template_full_name":null,"purl":"pkg:github/first-fluke/oh-my-agent","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/first-fluke%2Foh-my-agent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/first-fluke%2Foh-my-agent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/first-fluke%2Foh-my-agent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/first-fluke%2Foh-my-agent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/first-fluke","download_url":"https://codeload.github.com/first-fluke/oh-my-agent/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/first-fluke%2Foh-my-agent/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34134633,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-10T02:00:07.152Z","response_time":89,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent-harness","agent-skills","agentic-coding","ai-agents","claude-code","codex","cursor","multi-agent","multi-agent-systems","oh-my-agent","opencode","orchestration","orchestrator","serena"],"created_at":"2026-03-13T07:01:14.999Z","updated_at":"2026-06-10T03:01:05.934Z","avatar_url":"https://github.com/first-fluke.png","language":"TypeScript","funding_links":["https://github.com/sponsors/first-fluke","https://buymeacoffee.com/firstfluke"],"categories":[],"sub_categories":[],"readme":"# oh-my-agent: Portable Multi-Agent Harness\n\n[![npm version](https://img.shields.io/npm/v/oh-my-agent?color=cb3837\u0026logo=npm)](https://www.npmjs.com/package/oh-my-agent) [![npm downloads](https://img.shields.io/npm/dm/oh-my-agent?color=cb3837\u0026logo=npm)](https://www.npmjs.com/package/oh-my-agent) [![GitHub stars](https://img.shields.io/github/stars/first-fluke/oh-my-agent?style=flat\u0026logo=github)](https://github.com/first-fluke/oh-my-agent) [![License](https://img.shields.io/github/license/first-fluke/oh-my-agent)](https://github.com/first-fluke/oh-my-agent/blob/main/LICENSE) [![Last Updated](https://img.shields.io/github/last-commit/first-fluke/oh-my-agent?label=updated\u0026logo=git)](https://github.com/first-fluke/oh-my-agent/commits/main)\n\n[한국어](./docs/README.ko.md) | [中文](./docs/README.zh.md) | [Português](./docs/README.pt.md) | [日本語](./docs/README.ja.md) | [Français](./docs/README.fr.md) | [Español](./docs/README.es.md) | [Nederlands](./docs/README.nl.md) | [Polski](./docs/README.pl.md) | [Русский](./docs/README.ru.md) | [Deutsch](./docs/README.de.md) | [Tiếng Việt](./docs/README.vi.md) | [ภาษาไทย](./docs/README.th.md)\n\nEver wished your AI assistant had coworkers? That's what oh-my-agent does.\n\nInstead of one AI doing everything (and getting confused halfway through), oh-my-agent splits work across **specialized agents** — frontend, backend, architecture, QA, PM, DB, mobile, infra, debug, design, and more. Each one knows its domain deeply, has its own tools and checklists, and stays in its lane.\n\nWorks with all major AI IDEs: Antigravity, Claude Code, Cursor, Gemini CLI, Codex CLI, OpenCode, and more.\n\n## Quick Start\n\n```bash\n# macOS / Linux — auto-installs bun, uv \u0026 serena if missing\ncurl -fsSL https://raw.githubusercontent.com/first-fluke/oh-my-agent/main/cli/install.sh | bash\n```\n\n```powershell\n# Windows (PowerShell) — auto-installs bun, uv \u0026 serena if missing\nirm https://raw.githubusercontent.com/first-fluke/oh-my-agent/main/cli/install.ps1 | iex\n```\n\n```bash\n# Or manual (any OS, requires bun + uv + serena)\nbunx oh-my-agent@latest\n```\n\n### Install via Agent Package Manager\n\n\u003cdetails\u003e\n\u003csummary\u003eMicrosoft's \u003ca href=\"https://github.com/microsoft/apm\"\u003eAgent Package Manager\u003c/a\u003e (APM) — skills-only distribution. Click to expand.\u003c/summary\u003e\n\n\u003e Not to be confused with `oma-observability`'s APM (Application Performance Monitoring).\n\n```bash\n# All skills, deployed to every detected runtime\n# (.claude, .cursor, .codex, .opencode, .github, .agents)\napm install first-fluke/oh-my-agent\n\n# A single skill\napm install first-fluke/oh-my-agent/.agents/skills/oma-frontend\n```\n\nAPM ships skills only. For workflows, rules, `oma-config.yaml`, keyword-detection hooks, and the `oma agent:spawn` CLI, use `bunx oh-my-agent@latest`. Pick one distribution per project to avoid drift.\n\n\u003c/details\u003e\n\nPick a preset and you're ready:\n\n| Preset | What You Get |\n|--------|-------------|\n| **All** | **Every agent and skill** |\n| Backend | architecture + backend + brainstorm + db + debug + dev-workflow + pm + qa + scm |\n| Content | academic-writer + design + image + scm + translator + voice |\n| DevOps | architecture + brainstorm + debug + dev-workflow + observability + pm + qa + scm + tf-infra |\n| Frontend | architecture + brainstorm + debug + design + frontend + pm + qa + scm |\n| Fullstack | architecture + backend + brainstorm + db + debug + design + dev-workflow + frontend + mobile + pm + qa + scm + tf-infra |\n| Fullstack Mobile | architecture + backend + brainstorm + db + debug + design + dev-workflow + mobile + pm + qa + scm |\n| Fullstack Web | architecture + backend + brainstorm + db + debug + design + dev-workflow + frontend + pm + qa + scm |\n| Mobile | architecture + brainstorm + debug + mobile + pm + qa + scm |\n| Research | academic-writer + hwp + market + pdf + scholar + scm + search + translator |\n\n## Works With Every Agent\n\n`oh-my-agent` keeps `.agents/` as the single source of truth and projects it into each runtime's native layout, so every supported tool shares the same skills, workflows, and rules.\n\n\u003ctable\u003e\n\u003ccolgroup\u003e\n\u003ccol span=\"6\" style=\"width:16.67%\" /\u003e\n\u003c/colgroup\u003e\n\u003ctr\u003e\n\u003ctd align=\"center\"\u003e\n\u003ca href=\"https://claude.com/product/claude-code\"\u003e\u003cimg src=\"https://github.com/anthropics.png?size=120\" alt=\"Claude Code\" width=\"48\" height=\"48\" /\u003e\u003c/a\u003e\u003cbr/\u003e\n\u003cstrong\u003eClaude Code\u003c/strong\u003e\u003cbr/\u003e\n\u003csub\u003enative + adapter\u003c/sub\u003e\n\u003c/td\u003e\n\u003ctd align=\"center\"\u003e\n\u003ca href=\"https://github.com/openai/codex\"\u003e\u003cimg src=\"https://github.com/openai.png?size=120\" alt=\"Codex CLI\" width=\"48\" height=\"48\" /\u003e\u003c/a\u003e\u003cbr/\u003e\n\u003cstrong\u003eCodex CLI\u003c/strong\u003e\u003cbr/\u003e\n\u003csub\u003enative + adapter\u003c/sub\u003e\n\u003c/td\u003e\n\u003ctd align=\"center\"\u003e\n\u003ca href=\"https://github.com/google-gemini/gemini-cli\"\u003e\u003cimg src=\"https://github.com/google-gemini.png?size=120\" alt=\"Gemini CLI\" width=\"48\" height=\"48\" /\u003e\u003c/a\u003e\u003cbr/\u003e\n\u003cstrong\u003eGemini CLI\u003c/strong\u003e\u003cbr/\u003e\n\u003csub\u003enative + adapter\u003c/sub\u003e\n\u003c/td\u003e\n\u003ctd align=\"center\"\u003e\n\u003ca href=\"https://cursor.com\"\u003e\u003cimg src=\"https://github.com/cursor.png?size=120\" alt=\"Cursor\" width=\"48\" height=\"48\" /\u003e\u003c/a\u003e\u003cbr/\u003e\n\u003cstrong\u003eCursor\u003c/strong\u003e\u003cbr/\u003e\n\u003csub\u003enative + adapter\u003c/sub\u003e\n\u003c/td\u003e\n\u003ctd align=\"center\"\u003e\n\u003ca href=\"https://github.com/QwenLM/qwen-code\"\u003e\u003cimg src=\"https://github.com/QwenLM.png?size=120\" alt=\"Qwen Code\" width=\"48\" height=\"48\" /\u003e\u003c/a\u003e\u003cbr/\u003e\n\u003cstrong\u003eQwen Code\u003c/strong\u003e\u003cbr/\u003e\n\u003csub\u003enative dispatch\u003c/sub\u003e\n\u003c/td\u003e\n\u003ctd align=\"center\"\u003e\n\u003ca href=\"https://github.com/esengine/DeepSeek-Reasonix\"\u003e\u003cimg src=\"https://github.com/deepseek-ai.png?size=120\" alt=\"Reasonix\" width=\"48\" height=\"48\" /\u003e\u003c/a\u003e\u003cbr/\u003e\n\u003cstrong\u003eReasonix\u003c/strong\u003e\u003cbr/\u003e\n\u003csub\u003enative-compatible\u003c/sub\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"center\"\u003e\n\u003ca href=\"https://antigravity.google\"\u003e\u003cimg src=\"./docs/assets/agents/antigravity.png\" alt=\"Antigravity\" width=\"48\" height=\"48\" /\u003e\u003c/a\u003e\u003cbr/\u003e\n\u003cstrong\u003eAntigravity\u003c/strong\u003e\u003cbr/\u003e\n\u003csub\u003enative SSOT\u003c/sub\u003e\n\u003c/td\u003e\n\u003ctd align=\"center\"\u003e\n\u003ca href=\"https://github.com/anomalyco/opencode\"\u003e\u003cimg src=\"./docs/assets/agents/opencode.png\" alt=\"OpenCode\" width=\"48\" height=\"48\" /\u003e\u003c/a\u003e\u003cbr/\u003e\n\u003cstrong\u003eOpenCode\u003c/strong\u003e\u003cbr/\u003e\n\u003csub\u003enative-compatible\u003c/sub\u003e\n\u003c/td\u003e\n\u003ctd align=\"center\"\u003e\n\u003ca href=\"https://ampcode.com\"\u003e\u003cimg src=\"./docs/assets/agents/amp.png\" alt=\"Amp\" width=\"48\" height=\"48\" /\u003e\u003c/a\u003e\u003cbr/\u003e\n\u003cstrong\u003eAmp\u003c/strong\u003e\u003cbr/\u003e\n\u003csub\u003enative-compatible\u003c/sub\u003e\n\u003c/td\u003e\n\u003ctd align=\"center\"\u003e\n\u003ca href=\"https://github.com/features/copilot\"\u003e\u003cimg src=\"https://github.com/github.png?size=120\" alt=\"GitHub Copilot\" width=\"48\" height=\"48\" /\u003e\u003c/a\u003e\u003cbr/\u003e\n\u003cstrong\u003eGitHub Copilot\u003c/strong\u003e\u003cbr/\u003e\n\u003csub\u003esymlinked skills\u003c/sub\u003e\n\u003c/td\u003e\n\u003ctd align=\"center\"\u003e\n\u003ca href=\"https://grok.x.ai\"\u003e\u003cimg src=\"./docs/assets/agents/grok.png\" alt=\"Grok\" width=\"48\" height=\"48\" /\u003e\u003c/a\u003e\u003cbr/\u003e\n\u003cstrong\u003eGrok\u003c/strong\u003e\u003cbr/\u003e\n\u003csub\u003enative hooks\u003c/sub\u003e\n\u003c/td\u003e\n\u003ctd align=\"center\"\u003e\n\u003ca href=\"https://kiro.dev\"\u003e\u003cimg src=\"./docs/assets/agents/kiro.png\" alt=\"Kiro CLI\" width=\"48\" height=\"48\" /\u003e\u003c/a\u003e\u003cbr/\u003e\n\u003cstrong\u003eKiro CLI\u003c/strong\u003e\u003cbr/\u003e\n\u003csub\u003enative hooks + agents\u003c/sub\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n\u003cp align=\"center\"\u003e\u003csub\u003e\u003ca href=\"./docs/SUPPORTED_AGENTS.md\"\u003e\u0026 more\u003c/a\u003e\u003c/sub\u003e\u003c/p\u003e\n\n## Your Agent Team\n\n| Agent | What They Do |\n|-------|-------------|\n| **oma-academic-writer** | Drafts, revises, and audits academic prose to publication quality. |\n| **oma-architecture** | Weighs architecture tradeoffs and draws module boundaries, with ADR/ATAM/CBAM analysis. |\n| **oma-backend** | Builds and secures your APIs in Python, Node.js, or Rust. |\n| **oma-brainstorm** | Explores ideas with you before you commit to building. |\n| **oma-db** | Designs your schema, migrations, indexes, and vector stores. |\n| **oma-debug** | Finds the root cause, fixes the bug, and writes a regression test. |\n| **oma-deepsec** | Scans your code for security holes and blocks risky pull requests. |\n| **oma-design** | Builds design systems with tokens, accessibility, and responsive layouts. |\n| **oma-dev-workflow** | Automates your CI/CD, releases, and monorepo tasks. |\n| **oma-docs** | Checks your docs for broken references and flags ones a code change touched. |\n| **oma-frontend** | Builds your UI with React/Next.js, TypeScript, Tailwind CSS v4, and shadcn/ui. |\n| **oma-hwp** | Converts HWP, HWPX, and HWPML files to Markdown. |\n| **oma-image** | Generates images through several AI providers at once. |\n| **oma-market** | Researches your market from community signals and frames it with SWOT, 5F, and PESTEL. |\n| **oma-mobile** | Builds cross-platform mobile apps with Flutter. |\n| **oma-observability** | Routes observability work across metrics, logs, traces, SLOs, and incident forensics. |\n| **oma-orchestrator** | Runs multiple agents in parallel from the CLI. |\n| **oma-pdf** | Converts PDF files to Markdown. |\n| **oma-pm** | Plans tasks, breaks down requirements, and defines API contracts. |\n| **oma-qa** | Reviews your code for OWASP security, performance, and accessibility issues. |\n| **oma-recap** | Recaps your conversation history into themed work summaries. |\n| **oma-scholar** | Searches academic literature and helps you run peer review. |\n| **oma-scm** | Manages your branches, merges, worktrees, and Conventional Commits. |\n| **oma-search** | Routes each query to the best source and scores how much you can trust the result. |\n| **oma-skill-creator** | Writes and audits new OMA skills in the SSL-lite format. |\n| **oma-slide** | Generates distinctive, animation-rich HTML presentation decks and exports to PDF/PNG/PPTX. |\n| **oma-tf-infra** | Provisions multi-cloud infrastructure with Terraform. |\n| **oma-translator** | Translates between languages so it reads like a native wrote it. |\n| **oma-voice** | Generates voiceovers and transcribes audio on-device, no cloud needed. |\n\n## How It Works\n\nJust chat. Describe what you want and oh-my-agent figures out which agents to use.\n\n```\nYou: \"Build a TODO app with user authentication\"\n→ PM plans the work\n→ Backend builds auth API\n→ Frontend builds React UI\n→ DB designs schema\n→ QA reviews everything\n→ Done: coordinated, reviewed code\n```\n\nOr use slash commands for structured workflows:\n\n| Step | Command | What It Does |\n|------|---------|-------------|\n| 0 | `/deepinit` | Bootstrap an existing codebase (AGENTS.md, ARCHITECTURE.md, `docs/`) |\n| 1 | `/brainstorm` | Free-form ideation |\n| 2 | `/architecture` | Software architecture review, tradeoffs, ADR/ATAM/CBAM-style analysis |\n| 2 | `/design` | 7-phase design system workflow |\n| 2 | `/plan` | PM breaks down your feature into tasks |\n| 3 | `/work` | Step-by-step multi-agent execution |\n| 3 | `/orchestrate` | Automated parallel agent spawning |\n| 3 | `/ultrawork` | 5-phase quality workflow with 11 review gates |\n| 3 | `/ralph` | Wraps `/ultrawork` in an independent verifier loop until criteria pass |\n| 4 | `/review` | Security + performance + accessibility audit |\n| 4 | `/deepsec` | Deep agent-powered security scan |\n| 5 | `/debug` | Structured root-cause debugging |\n| 5 | `/docs` | Documentation drift verify + sync via `oma-docs` |\n| 6 | `/scm` | SCM + Git workflow and Conventional Commit support |\n\n**Auto-detection**: You don't even need slash commands — keywords like \"architecture\", \"plan\", \"review\", and \"debug\" in your message (in 11 languages!) auto-activate the right workflow.\n\n## CLI\n\n```bash\n# Install globally\nbun install --global oh-my-agent   # or: brew install oh-my-agent\n\n# Use anywhere (sorted alphabetically)\noma agent:parallel -i backend:\"Auth API\" frontend:\"Login form\"\noma agent:spawn backend \"Build auth API\" session-01\noma dashboard               # Real-time agent monitoring\noma doctor                  # Health check\noma image generate \"cat\"    # Multi-vendor AI image generation\noma link                    # Regenerate .claude/.codex/.gemini/etc. from .agents/\noma model:check             # Detect drift between registered models and live vendor lists\noma recap --window 1d       # Cross-tool conversation history recap\noma retro 7d --compare      # Engineering retrospective with metrics + trends\noma search fetch \u003curl\u003e      # Mechanical search with auto-escalating strategies\n```\n\nModel selection follows two layers:\n- Same-vendor native dispatch uses the generated vendor agent definition in `.claude/agents/`, `.codex/agents/`, or `.gemini/agents/`.\n- Cross-vendor or fallback CLI dispatch uses the vendor defaults in `.agents/skills/oma-orchestrator/config/cli-config.yaml`.\n\n### Per-Agent Models\n\nSet `model_preset` in `.agents/oma-config.yaml` to choose which AI models each agent uses:\n\n```yaml\nlanguage: en\nmodel_preset: mixed   # antigravity | claude | codex | cursor | grok | mixed | qwen\n\n# Optional per-agent overrides\nagents:\n  backend: { model: openai/gpt-5.5, effort: high }\n```\n\n- `oma doctor --profile` — prints the per-role resolved model matrix\n- Full guide: [`web/docs/guide/per-agent-models.md`](./web/docs/guide/per-agent-models.md)\n\n## Why oh-my-agent?\n\n\u003e [Read why →](https://github.com/first-fluke/oh-my-agent/issues/155#issuecomment-4142133589)\n\n- **Portable** — `.agents/` travels with your project, not trapped in one IDE\n- **Role-based** — Agents modeled like a real engineering team, not a pile of prompts\n- **Token-efficient** — Two-layer skill design saves ~75% of tokens\n- **Quality-first** — Charter preflight, quality gates, and review workflows built in:\n  - `oma verify \u003cagent\u003e` — 14 deterministic checks per agent type (TypeScript strict, tests, raw SQL, hardcoded secrets, Flutter analyze, inline styles, scope violation, charter alignment, …)\n  - `session.quota_cap` — per-session token / spawn / per-vendor budget caps in `oma-config.yaml`; `orchestrate` Step 5 blocks the next spawn when exceeded\n  - `ralph` workflow — independent JUDGE re-verifies every criterion each iteration to catch silent regressions; heavy-test caching for \u003e30s suites\n  - Exploration Loop — after 2 retries, `orchestrate` spawns hypothesis variants in parallel and keeps the highest-scoring result\n  - Monorepo auto-routing — `detectWorkspace` reads pnpm / nx / turbo / lerna and routes each agent to its workspace\n- **Multi-vendor** — Mix Claude, Codex, Cursor, and Qwen per agent type\n- **Observable** — Terminal and web dashboards for real-time monitoring\n\n## Architecture\n\n```mermaid\nflowchart TD\n    subgraph Workflows[\"Workflows\"]\n        direction TB\n        W0[\"/brainstorm\"]\n        W1[\"/work\"]\n        W1b[\"/ultrawork\"]\n        W2[\"/orchestrate\"]\n        W3[\"/architecture\"]\n        W4[\"/plan\"]\n        W5[\"/review\"]\n        W6[\"/debug\"]\n        W7[\"/deepinit\"]\n        W8[\"/design\"]\n    end\n\n    subgraph Orchestration[\"Orchestration\"]\n        direction TB\n        PM[oma-pm]\n        ORC[oma-orchestrator]\n    end\n\n    subgraph Domain[\"Domain Agents\"]\n        direction TB\n        ARC[oma-architecture]\n        FE[oma-frontend]\n        BE[oma-backend]\n        DB[oma-db]\n        MB[oma-mobile]\n        DES[oma-design]\n        TF[oma-tf-infra]\n    end\n\n    subgraph Quality[\"Quality\"]\n        direction TB\n        QA[oma-qa]\n        DBG[oma-debug]\n    end\n\n    Workflows --\u003e Orchestration\n    Orchestration --\u003e Domain\n    Domain --\u003e Quality\n    Quality --\u003e SCM([oma-scm])\n```\n\n## Learn More\n\n- **[Detailed Documentation](./docs/AGENTS_SPEC.md)** — Full technical spec and architecture\n- **[Supported Agents](./docs/SUPPORTED_AGENTS.md)** — Agent support matrix across IDEs\n- **[Web Docs](https://first-fluke.github.io/oh-my-agent/)** — Guides, tutorials, and CLI reference\n\n## Sponsors\n\nThis project is maintained thanks to our generous sponsors.\n\n\u003e **Like this project?** Give it a star!\n\u003e\n\u003e ```bash\n\u003e gh api --method PUT /user/starred/first-fluke/oh-my-agent\n\u003e ```\n\u003e\n\u003e Try our optimized starter template: [fullstack-starter](https://github.com/first-fluke/fullstack-starter)\n\n\u003ca href=\"https://github.com/sponsors/first-fluke\"\u003e\n  \u003cimg src=\"https://img.shields.io/badge/Sponsor-♥-ea4aaa?style=for-the-badge\" alt=\"Sponsor\" /\u003e\n\u003c/a\u003e\n\u003ca href=\"https://buymeacoffee.com/firstfluke\"\u003e\n  \u003cimg src=\"https://img.shields.io/badge/Buy%20Me%20a%20Coffee-☕-FFDD00?style=for-the-badge\" alt=\"Buy Me a Coffee\" /\u003e\n\u003c/a\u003e\n\n### 🚀 Champion\n\n\u003c!-- Champion tier ($100/mo) logos here --\u003e\n\n### 🛸 Booster\n\n\u003c!-- Booster tier ($30/mo) logos here --\u003e\n\n### ☕ Contributor\n\n\u003c!-- Contributor tier ($10/mo) names here --\u003e\n\n[Become a sponsor →](https://github.com/sponsors/first-fluke)\n\nSee [SPONSORS.md](./SPONSORS.md) for a full list of supporters.\n\n\n\n## Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=first-fluke/oh-my-agent\u0026type=date\u0026legend=bottom-right)](https://www.star-history.com/#first-fluke/oh-my-agent\u0026type=date\u0026legend=bottom-right)\n\n\n## References\n\n- Liang, Q., Wang, H., Liang, Z., \u0026 Liu, Y. (2026). *From skill text to skill structure: The scheduling-structural-logical representation for agent skills* (Version 4) [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2604.24026\n- Chen, C., Yu, Q., Gu, Y., Huang, Z., Li, H., Liu, H., Liu, S., Liu, J., Peng, D., Wang, J., Yan, Z., Meng, F., Qin, E., Che, C., \u0026 Hu, M. (2026). *The scaling laws of skills in LLM agent systems* (Version 1) [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2605.16508\n\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffirst-fluke%2Foh-my-agent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffirst-fluke%2Foh-my-agent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffirst-fluke%2Foh-my-agent/lists"}