convez.ai
Skill
first-fluke

oh-my-agent

first-fluke/oh-my-agent

Ver no GitHub
Muito bomPluginScore · de 0 a 100

Portable, vendor-agnostic agent harness for project-specific skills, workflows, and agent teams aligned with your codebase, conventions, and engineering standards.

Instalação

$npx convez-ai first-fluke/oh-my-agent

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1,5 mil
Forks
159
Acompanhando
6
Saúde
62%
Último commit
há 1 dia
Versão
web-v12.0.0
Issues abertas
0
Contribuidores
11

README

A tradução para o português deste README ainda está na fila.

oh-my-agent: Portable Multi-Agent Harness

npm version npm downloads GitHub stars License Last Updated

한국어 | 中文 | Português | 日本語 | Français | Español | Nederlands | Polski | Русский | Deutsch | Tiếng Việt | ภาษาไทย

Ever wished your AI assistant had coworkers? That's what oh-my-agent does.

Instead 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.

Works with all major AI IDEs: Pi, Claude Code, Cursor, Antigravity, Codex CLI, OpenCode, and more.

Quick Start

# macOS / Linux — auto-installs bun, uv & serena if missing
curl -fsSL https://raw.githubusercontent.com/first-fluke/oh-my-agent/main/cli/install.sh | bash
# Windows (PowerShell) — auto-installs bun, uv & serena if missing
irm https://raw.githubusercontent.com/first-fluke/oh-my-agent/main/cli/install.ps1 | iex
# Or manual (any OS, requires bun + uv + serena)
bunx oh-my-agent@latest

Install via Agent Package Manager

Not to be confused with oma-observability's APM (Application Performance Monitoring).

# All skills, deployed to every detected runtime
# (.claude, .cursor, .codex, .opencode, .github, .agents)
apm install first-fluke/oh-my-agent

# A single skill
apm install first-fluke/oh-my-agent/.agents/skills/oma-frontend

APM 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.

Pick a preset and you're ready:

PresetWhat You Get
AllEvery agent and skill
Backendarchitecture + backend + brainstorm + db + debug + dev-workflow + pm + qa + scm
Contentacademic-writer + design + image + scm + translator + voice
DevOpsarchitecture + brainstorm + debug + dev-workflow + observability + pm + qa + scm + tf-infra
Frontendarchitecture + brainstorm + debug + design + frontend + pm + qa + scm
Fullstackarchitecture + backend + brainstorm + db + debug + design + dev-workflow + frontend + mobile + pm + qa + scm + tf-infra
Fullstack Mobilearchitecture + backend + brainstorm + db + debug + design + dev-workflow + mobile + pm + qa + scm
Fullstack Webarchitecture + backend + brainstorm + db + debug + design + dev-workflow + frontend + pm + qa + scm
Mobilearchitecture + brainstorm + debug + mobile + pm + qa + scm
Researchacademic-writer + hwp + market + pdf + scholar + scm + search + translator

Works With Every Agent

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.

Your Agent Team

AgentWhat They Do
oma-academic-writerDrafts, revises, and audits academic prose to publication quality.
oma-architectureWeighs architecture tradeoffs and draws module boundaries, with ADR/ATAM/CBAM analysis.
oma-backendBuilds and secures your APIs in Python, Node.js, or Rust.
oma-brainstormExplores ideas with you before you commit to building.
oma-coordinationGuides manual step-by-step coordination of PM, frontend, backend, mobile, and QA agents.
oma-dbDesigns your schema, migrations, indexes, and vector stores.
oma-debugFinds the root cause, fixes the bug, and writes a regression test.
oma-deepsecScans your code for security holes and blocks risky pull requests.
oma-designBuilds design systems with tokens, accessibility, and responsive layouts.
oma-dev-workflowAutomates your CI/CD, releases, and monorepo tasks.
oma-docsChecks your docs for broken references and flags ones a code change touched.
oma-frontendBuilds your UI with React/Next.js, TypeScript, Tailwind CSS v4, and shadcn/ui.
oma-hwpConverts HWP, HWPX, and HWPML files to Markdown.
oma-imageGenerates images through several AI providers at once.
oma-marketResearches your market from community signals and frames it with SWOT, 5F, and PESTEL.
oma-mobileBuilds cross-platform mobile apps with Flutter.
oma-observabilityRoutes observability work across metrics, logs, traces, SLOs, and incident forensics.
oma-orchestratorRuns multiple agents in parallel from the CLI.
oma-pdfConverts PDF files to Markdown.
oma-pmPlans tasks, breaks down requirements, and defines API contracts.
oma-qaReviews your code for OWASP security, performance, and accessibility issues.
oma-recapRecaps your conversation history into themed work summaries.
oma-refactorRefactors code without changing its behavior, using hotspot targeting, characterization-test safety nets, and refactor-only commits.
oma-scholarSearches academic literature and helps you run peer review.
oma-scmManages your branches, merges, worktrees, and Conventional Commits.
oma-searchRoutes each query to the best source and scores how much you can trust the result.
oma-skill-creatorWrites and audits new OMA skills in the SSL-lite format.
oma-slideGenerates distinctive, animation-rich HTML presentation decks and exports to PDF/PNG/PPTX.
oma-tf-infraProvisions multi-cloud infrastructure with Terraform.
oma-translatorTranslates between languages so it reads like a native wrote it.
oma-videoGenerates short-form, explainer, and demo videos through a key-optional Remotion pipeline.
oma-voiceGenerates voiceovers and transcribes audio on-device, no cloud needed.

How It Works

Just chat. Describe what you want and oh-my-agent figures out which agents to use.

You: "Build a TODO app with user authentication"
→ PM plans the work
→ Backend builds auth API
→ Frontend builds React UI
→ DB designs schema
→ QA reviews everything
→ Done: coordinated, reviewed code

Or use slash commands for structured workflows:

StepCommandWhat It Does
0/deepinitBootstrap an existing codebase (AGENTS.md, ARCHITECTURE.md, docs/)
1/brainstormFree-form ideation
2/architectureSoftware architecture review, tradeoffs, ADR/ATAM/CBAM-style analysis
2/design7-phase design system workflow
2/planPM breaks down your feature into tasks
3/workStep-by-step multi-agent execution
3/orchestrateAutomated parallel agent spawning
3/ultrawork5-phase quality workflow with 11 review gates
3/ralphWraps /ultrawork in an independent verifier loop until criteria pass
4/reviewSecurity + performance + accessibility audit
4/deepsecDeep agent-powered security scan
5/debugStructured root-cause debugging
5/docsDocumentation drift verify + sync via oma-docs
6/scmSCM + Git workflow and Conventional Commit support

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.

Per-Agent Models

Set model_preset in .agents/oma-config.yaml to choose which AI models each agent uses:

language: en
model_preset: mixed   # antigravity | claude | codex | cursor | grok | mixed | qwen

# Optional per-agent overrides
agents:
  backend: { model: openai/gpt-5.5, effort: high }

Why oh-my-agent?

Read why →

  • Portable — .agents/ travels with your project, not trapped in one IDE
  • Role-based — Agents modeled like a real engineering team, not a pile of prompts
  • Token-efficient — Two-layer skill design saves ~75% of tokens
  • Quality-first — Charter preflight, quality gates, and review workflows built in:
    • oma verify <agent> — a deterministic check battery per agent type: a shared core (scope violation, charter alignment, hardcoded secrets, TODO scan, declared outputs) plus type-specific checks (TypeScript strict, tests, raw SQL, Flutter analyze, inline styles, …)
    • session.quota_cap — per-session token / spawn / per-vendor budget caps in oma-config.yaml; orchestrate Step 5 blocks the next spawn when exceeded
    • ralph workflow — independent JUDGE re-verifies every criterion each iteration to catch silent regressions; heavy-test caching for >30s suites
    • Exploration Loop — after 2 retries, orchestrate spawns hypothesis variants in parallel and keeps the highest-scoring result
    • Monorepo auto-routing — detectWorkspace reads pnpm / nx / turbo / lerna and routes each agent to its workspace
  • Multi-vendor — Mix Claude, Codex, Cursor, and Qwen per agent type
  • Observable — Terminal and web dashboards for real-time monitoring

Architecture

flowchart TD
    subgraph Workflows["Workflows"]
        direction TB
        W0["/brainstorm"]
        W1["/work"]
        W1b["/ultrawork"]
        W2["/orchestrate"]
        W3["/architecture"]
        W4["/plan"]
        W5["/review"]
        W6["/debug"]
        W7["/deepinit"]
        W8["/design"]
    end

    subgraph Orchestration["Orchestration"]
        direction TB
        PM[oma-pm]
        ORC[oma-orchestrator]
    end

    subgraph Domain["Domain Agents"]
        direction TB
        ARC[oma-architecture]
        FE[oma-frontend]
        BE[oma-backend]
        DB[oma-db]
        MB[oma-mobile]
        DES[oma-design]
        TF[oma-tf-infra]
    end

    subgraph Quality["Quality"]
        direction TB
        QA[oma-qa]
        DBG[oma-debug]
    end

    Workflows --> Orchestration
    Orchestration --> Domain
    Domain --> Quality
    Quality --> SCM([oma-scm])

Learn More

Sponsors

This project is maintained thanks to our generous sponsors.

Like this project? Give it a star!

gh api --method PUT /user/starred/first-fluke/oh-my-agent

Try our optimized starter template: fullstack-starter

🚀 Champion

🛸 Booster

☕ Contributor

Become a sponsor →

See SPONSORS.md for a full list of supporters.

Star History

Star History Chart

References

  • Liang, Q., Wang, H., Liang, Z., & 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
  • 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., & Hu, M. (2026). The scaling laws of skills in LLM agent systems (Version 1) [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2605.16508
  • Yang, Y., Gong, Z., Huang, W., Yang, Q., Zhou, Z., Huang, Z., Li, Y., Gao, X., Dai, Q., Liu, B., Qiu, K., Yang, Y., Chen, D., Yang, X., & Luo, C. (2026). SkillOpt: Executive strategy for self-evolving agent skills [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2605.23904
  • Huang, Z., Xu, J., Yang, Y., Gong, Z., Yang, Q., Tian, M., Wang, X., Lv, C., Gao, X., Dai, Q., Liu, B., Qiu, K., Yang, X., Chen, D., Zheng, X., & Luo, C. (2026). From raw experience to skill consumption: A systematic study of model-generated agent skills [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2605.23899

License

MIT

Ver o original no GitHub

Bom para

Relacionados