Development
Plugin
oma
The hardcore multi-agent orchestrator for production-grade software. Not just another chat wrapper—oh-my-agent is a professional harness that gives your AI assistant an entire engineering team. Ever wished your AI assistant had coworkers?
Plugin Signal78/100Solid
maintained100
capable43
documented100
adopted66
Install on Claude Code
> /plugin marketplace add first-fluke/oh-my-agent> /plugin install oma@oh-my-agent
Stats
1,219
Stars
140
Forks
Active
Maintenance
TypeScript
Language
MIT
License
13h ago
Last commit
6mo ago
Created
Repo: first-fluke/oh-my-agent
What's inside
Hooks
4Badges
5
README
1oh-my-agent: Portable Multi-Agent Harness
한국어 | 中文 | Português | 日本語 | Français | Español | Nederlands | Polski | Русский | Deutsch | Tiếng Việt | ภาษาไทย
The hardcore multi-agent orchestrator for production-grade software. Not just another chat wrapper—oh-my-agent is a professional harness that gives your AI assistant an entire engineering team.
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: Antigravity, Claude Code, Codex, Cursor, Grok Build, Kimi Code, OpenCode, Pi, Qwen Code, and more.
Quick Start
Requires Node.js 26+. The install scripts below auto-install bun, uv, and serena if they're missing.
# 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 as an Agent Plugin
oma exports a portable Agent Plugins 1.0.0 package — the open packaging standard backed by AWS, Cursor, Microsoft, OpenAI, and Vercel:
oma emit --target agent-plugin # writes generated/agent-plugin/
Point any conformant client (Kiro, AWS Agent Toolkit, and more as clients roll out support) at that directory. Conformant clients load the skills and MCP servers; workflows, rules, and oma-config.yaml ride along under the com.firstfluke.oma extension namespace for oma-aware installs. Hooks and oma agent:spawn still need the full bunx oh-my-agent@latest install.
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
Agent Plugins is the package format; APM is an installer that 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:
| Preset | What You Get |
|---|---|
| All | Every agent and skill |
| Backend | architecture + backend + brainstorm + db + debug + dev-workflow + pm + qa + scm |
| Content | academic-writer + design + image + scm + translator + voice |
| DevOps | architecture + brainstorm + debug + dev-workflow + observability + pm + qa + scm + tf-infra |
| Frontend | architecture + brainstorm + debug + design + frontend + pm + qa + scm |
| Fullstack | architecture + backend + brainstorm + db + debug + design + dev-workflow + frontend + mobile + pm + qa + scm + tf-infra |
| Fullstack Mobile | architecture + backend + brainstorm + db + debug + design + dev-workflow + mobile + pm + qa + scm |
| Fullstack Web | architecture + backend + brainstorm + db + debug + design + dev-workflow + frontend + pm + qa + scm |
| Mobile | architecture + brainstorm + debug + mobile + pm + qa + scm |
| Research | academic-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
| Agent | What They Do |
|---|---|
| oma-academic-writer | Drafts, revises, and audits academic prose to publication quality. |
| oma-architecture | Weighs architecture tradeoffs and draws module boundaries, with ADR/ATAM/CBAM analysis. |
| oma-backend | Builds and secures your APIs in Python, Node.js, or Rust. |
| oma-brainstorm | Explores ideas with you before you commit to building. |
| oma-db | Designs your schema, migrations, indexes, and vector stores. |
| oma-debug | Finds the root cause, fixes the bug, and writes a regression test. |
| oma-deepsec | Scans your code for security holes and blocks risky pull requests. |
| oma-design | Builds design systems with tokens, accessibility, and responsive layouts. |
| oma-dev-workflow | Automates your CI/CD, releases, and monorepo tasks. |
| oma-docs | Checks your docs for broken references and flags ones a code change touched. |
| oma-explainer | Turns a diff, PR, or branch into a self-contained interactive HTML explainer with a quiz. |
| oma-frontend | Builds your UI with React/Next.js, TypeScript, Tailwind CSS v4, and shadcn/ui. |
| oma-hwp | Converts HWP, HWPX, and HWPML files to Markdown. |
| oma-image | Generates images through several AI providers at once. |
| oma-market | Researches your market from community signals and frames it with SWOT, 5F, and PESTEL. |
| oma-mobile | Builds cross-platform mobile apps with Flutter. |
| oma-observability | Routes observability work across metrics, logs, traces, SLOs, and incident forensics. |
| oma-orchestrator | Runs multiple agents in parallel from the CLI. |
| oma-pdf | Converts PDF files to Markdown. |
| oma-pm | Plans tasks, breaks down requirements, and defines API contracts. |
| oma-qa | Reviews your code for OWASP security, performance, and accessibility issues. |
| oma-recap | Recaps your conversation history into themed work summaries. |
| oma-refactor | Refactors code without changing its behavior, using hotspot targeting, characterization-test safety nets, and refactor-only commits. |
| oma-scholar | Searches academic literature and helps you run peer review. |
| oma-scm | Manages your branches, merges, worktrees, and Conventional Commits. |
| oma-search | Routes each query to the best source and scores how much you can trust the result. |
| oma-slide | Generates distinctive, animation-rich HTML presentation decks and exports to PDF/PNG/PPTX. |
| oma-tf-infra | Provisions multi-cloud infrastructure with Terraform. |
| oma-translator | Translates between languages so it reads like a native wrote it. |
| oma-video | Generates short-form, explainer, and demo videos through a key-optional Remotion pipeline. |
| oma-voice | Generates voiceovers and transcribes audio on-device, no cloud needed. |
| Agent | What They Do |
|---|---|
| oma-coordination | Guides manual step-by-step coordination of PM, frontend, backend, mobile, and QA agents. |
| oma-skill-creator | Writes and audits new OMA skills in the SSL-lite format. |
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:
| Step | Command | What It Does |
|---|---|---|
| 0 | /deepinit | Maps your existing codebase into AGENTS.md, ARCHITECTURE.md, and docs |
| 1 | /brainstorm | Explores ideas with you before you commit to building |
| 2 | /architecture | Weighs your design tradeoffs and draws clean module boundaries |
| 2 | /design | Builds your design system with tokens, accessibility, and responsive layouts |
| 2 | /plan | Breaks your feature down into prioritized tasks |
| 3 | /work | Builds your feature step by step across multiple agents |
| 3 | /orchestrate | Runs multiple agents in parallel to build your feature faster |
| 3 | /ultrawork | Builds your feature through five gated quality phases; every review runs in a fresh, isolated reviewer session (cross-context review) |
| 3 | /ralph | Repeats /ultrawork until an independent verifier passes every criterion |
| 4 | /review | Reviews your code for security, performance, and accessibility issues |
| 4 | /deepsec | Runs a deep security scan and blocks risky pull requests |
| 5 | /debug | Finds the root cause, fixes the bug, and writes a regression test |
| 5 | /docs | Checks your docs for broken references and patches the ones your code changes touched |
| 6 | /scm | Manages your branches, merges, and Conventional Commits |
| - | /schedule | Schedules an agent job to run on a recurring interval |
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. Detection accuracy is measured, not assumed: oma verify triggers scores the detector against a labeled 171-prompt corpus (currently 0% missed-fire, under 10% false-fire) and gates CI on it.
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 | kiro | mixed | qwen
# Optional per-agent overrides
agents:
backend: { model: openai/gpt-5.5, effort: high }
oma doctor --profile— prints the per-role resolved model matrix- Full guide:
web/docs/guide/per-agent-models.md
Why oh-my-agent?
- Portable —
.agents/travels with your project, not trapped in one IDE.oma emitprojects the same SSOT into open-standard artifacts — Agent Skills-conformant skill folders, a.claude-plugin/marketplace.json, andAGENTS.md— so oma skills work in any tool that reads the open spec, with a drift check in CI keeping the generated output honest - Role-based — Agents modeled like a real engineering team, not a pile of prompts
- Token-efficient — Two-layer skill design saves ~75% of tokens (how it works)
- 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 inoma-config.yaml;orchestrateStep 5 blocks the next spawn when exceededralphworkflow — independent JUDGE re-verifies every criterion each iteration to catch silent regressions; heavy-test caching for >30s suites- Exploration Loop — after 2 retries,
orchestratespawns hypothesis variants in parallel and keeps the highest-scoring result - Monorepo auto-routing —
detectWorkspacereads pnpm / nx / turbo / lerna and routes each agent to its workspace
- Multi-vendor — Mix Antigravity, Claude, Codex, Cursor, Kiro, 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
- Detailed Documentation — Full technical spec and architecture
- Supported Agents — Agent support matrix across IDEs
- Web Docs — Guides, tutorials, and CLI reference
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-agentTry our optimized starter template: fullstack-starter
🚀 Champion
🛸 Booster
☕ Contributor
See SPONSORS.md for a full list of supporters.
Star History
References
- Li, X., Liu, Y., Chen, W., You, B., Di, Z., He, Y., Zheng, S., Choe, K. W., Sun, J., Wang, S., Tao, C., Li, B., Zhao, X., Geng, H., Wu, X., Zhou, J., Chen, X., Xing, H., Li, Y., … Song, D. (2026). SkillsBench: Benchmarking how well agent skills work across diverse tasks (Version 4) [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2602.12670
- Yu, G., & Wang, X. (2026). Knows: Agent-native structured research representations (Version 1) [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2604.17309
- 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 (Version 2) [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
- Hong, D. B., Imani, A., & Ahmed, I. (2026). From anatomy to smells: An empirical study of SKILL.md in agent skills (Version 2) [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2607.01456
License
MIT
File tree
1570first-fluke/oh-my-agentView on GitHub
.agents/
agents/
architecture-reviewer.md
backend-engineer.md
db-engineer.md
debug-investigator.md
docs-curator.md
frontend-engineer.md
mobile-engineer.md
pm-planner.md
qa-reviewer.md
refactor-engineer.md
research-explorer.md
tf-infra-engineer.md
variants/
agent-variant.schema.json
claude.json
codex.json
commandcode.json
cursor.json
grok.json
kiro.json
opencode.json
config/
defaults.yaml
eval/
oma-docs/
escape-hatch.yaml
gitignored-target.yaml
hook-policy.yaml
sync-apply-policy.yaml
translation-routing.yaml
url-check-tool.yaml
oma-market/
_rollouts/
0e495563955c5929.json
coverage-annotation.yaml
framework-toggle.yaml
keyed-source-skip.yaml
output-path-contract.yaml
preflight-gate.yaml
trap-refuse-flow.yaml
oma-scm/
_rollouts/
8d4085aff4108372.json
coauthor-trailer.yaml
forcepush-flag.yaml
protected-branch-pr.yaml
secret-scanner.yaml
split-precedence.yaml
worktree-merge.yaml
hooks/
core/
agentmemory-client.ts
agy-input.ts
constants.ts
filter-test-output.sh
fs-utils.ts
grok-context.ts
hook-output.ts
hud.ts
inject-log.ts
keyword-detector.ts
persistent-mode.ts
prompt-input.ts
scm-guard.ts
serena-primer.ts
skill-injector.ts
state-boundary.ts
state-emit.ts
state-marker.ts
test-filter.ts
triggers.json
types.ts
vendor-detect.ts
vendor-renderer.ts
variants/
antigravity.json
claude.json
codex.json
commandcode.json
cursor.json
grok.json
hook-variant.schema.json
kimi.json
kiro.json
opencode/
oma.ts
pi/
index.ts
README.md
qwen.json
mcp_config.json
mcp.json
oma-config.yaml
results/
.gitkeep
rules/
backend.md
commit.md
database.md
debug.md
design.md
dev-workflow.md
frontend.md
i18n-arb.md
i18n-guide.md
infrastructure.md
market.md
mobile.md
quality.md
skills/
_shared/
conditional/
experiment-ledger.md
exploration-loop.md
quality-score.md
core/
api-contracts/
README.md
template.md
clarification-protocol.md
common-checklist.md
context-budget.md
context-loading.md
difficulty-guide.md
lessons-learned.md
prompt-structure.md
quality-principles.md
session-metrics.md
skill-routing.md
stack-verify.schema.json
test-approach.md
vendor-detection.md
README.md
runtime/
event-spec.md
execution-protocols/
antigravity.md
claude.md
codex.md
commandcode.md
grok.md
kimi.md
kiro.md
opencode.md
pi.md
qwen.md
memory-protocol.md
_version.json
oma-academic-writer/
resources/
academic-verb-tiers.md
anti-ai-checklist.md
hedging-guide.md
sentence-structure-reference.md
SKILL.md
oma-architecture/
resources/
api-evolution.md
checklist.md
execution-protocol.md
methodology-selection.md
migration-patterns.md
output-templates.md
stakeholder-synthesis.md
SKILL.md
oma-backend/
resources/
checklist.md
error-playbook.md
execution-protocol.md
orm-reference.md
SKILL.md
variants/
node/
api-template.ts
snippets.md
stack.yaml
tech-stack.md
python/
api-template.py
snippets.md
stack.yaml
tech-stack.md
rust/
api-template.rs
snippets.md
stack.yaml
tech-stack.md
stack.schema.json
oma-brainstorm/
resources/
triz-lite.md
SKILL.md
oma-coordination/
SKILL.md
oma-db/
resources/
anti-patterns.md
checklist.md
document-templates.md
error-playbook.md
examples.md
execution-protocol.md
iso-controls.md
migration-playbook.md
query-tuning.md
vector-db.md
SKILL.md
oma-debug/
resources/
bug-report-template.md
checklist.md
common-patterns.md
debugging-checklist.md
error-playbook.md
execution-protocol.md
SKILL.md
oma-deepsec/
resources/
config.md
matchers.md
pr-review.md
scanning.md
setup.md
triage.md
SKILL.md
oma-design/
reference/
accessibility.md
color-and-contrast.md
component-patterns.md
motion-design.md
responsive-design.md
shader-and-3d.md
spatial-design.md
typography.md
visual-hierarchy.md
resources/
anti-patterns.md
asset-strategy.md
checklist.md
design-md-spec.md
design-tokens.md
error-playbook.md
execution-protocol.md
getdesign-fetcher.md
prompt-enhancement.md
redesign-protocol.md
stitch-integration.md
SKILL.md
oma-dev-workflow/
resources/
api-workflows.md
database-patterns.md
i18n-patterns.md
release-coordination.md
troubleshooting.md
validation-pipeline.md
SKILL.md
oma-docs/
SKILL.md
oma-explainer/
resources/
document-structure.md
html-contract.md
SKILL.md
oma-frontend/
resources/
angular-rules.md
checklist.md
error-playbook.md
execution-protocol.md
snippets.md
tailwind-rules.md
tech-stack.md
SKILL.md
oma-hwp/
config/
hwp-config.yaml
resources/
balanced-tables.ts
bun.lock
execution-protocol.md
flatten-tables.ts
package.json
troubleshooting.md
tsconfig.json
turndown-plugin-gfm.d.ts
SKILL.md
oma-image/
config/
image-config.yaml
resources/
checklist.md
execution-protocol.md
prompt-tips.md
vendor-matrix.md
SKILL.md
oma-market/
resources/
checklist.md
error-playbook.md
examples.md
execution-protocol.md
frameworks/
pestel.md
porters-5f.md
swot.md
intent-rules.md
operator-packs/
competitor.md
discovery.md
pain.md
positive.md
output-laws.md
SKILL.md
oma-mobile/
resources/
checklist.md
error-playbook.md
execution-protocol.md
screen-template.dart
screen-template.swift
screen-template.tsx
tech-stack.md
SKILL.md
variants/
flutter/
api-template.dart
snippets.md
stack.yaml
tech-stack.md
react-native/
api-template.ts
snippets.md
stack.yaml
tech-stack.md
README.md
stack.schema.json
swift-ios/
api-template.swift
snippets.md
stack.yaml
tech-stack.md
oma-observability/
resources/
anti-patterns.md
boundaries/
cross-application.md
multi-tenant.md
release.md
slo.md
checklist.md
examples.md
execution-protocol.md
incident-forensics.md
intent-rules.md
layers/
L3-network.md
L4-transport.md
L7-application/
crash-analytics.md
mobile-rum.md
waf.md
web-rum.md
mesh.md
matrix.md
meta-observability.md
observability-as-code.md
signals/
audit.md
cost.md
logs.md
metrics.md
privacy.md
profiles.md
traces.md
standards.md
transport/
collector-topology.md
otlp-grpc-vs-http.md
sampling-recipes.md
udp-statsd-mtu.md
vendor-categories.md
SKILL.md
oma-orchestrator/
config/
cli-config.yaml
resources/
memory-schema.md
subagent-prompt-template.md
scripts/
parallel-run.sh
spawn-agent.sh
verify.sh
SKILL.md
templates/
backend-task.md
... 1600 moreShowing a partial view of a very large repo.
FAQ
oma is a Claude Code plugin with hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is oma?
- The hardcore multi-agent orchestrator for production-grade software. Not just another chat wrapper—oh-my-agent is a professional harness that gives your AI assistant an entire engineering team. Ever wished your AI assistant had coworkers?
- How do I install oma?
- Run these in Claude Code: /plugin marketplace add first-fluke/oh-my-agent then /plugin install oma@oh-my-agent. Then prompt normally.
- Does oma auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is oma free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.