> > **We're building a fully productized version of Sisyphus to define the future of frontier agents. <br />Join the waitlist [here](https://sisyphuslabs.ai).**
> | [<img alt="X link" src="https://img.shields.io/badge/Follow-%40justsisyphus-00CED1?style=flat-square&logo=x&labelColor=black" width="156px" />](https://x.com/justsisyphus) | News and updates for `oh-my-opencode` used to be posted on my X account. <br /> Since it was suspended mistakenly, [@justsisyphus](https://x.com/justsisyphus) now posts updates on my behalf. |
> "It made me cancel my Cursor subscription. Unbelievable things are happening in the open source community." - [Arthur Guiot](https://x.com/arthur_guiot/status/2008736347092382053?s=20)
> "If Claude Code does in 7 days what a human does in 3 months, Sisyphus does it in 1 hour. It just works until the task is done. It is a discipline agent." — B, Quant Researcher
> "Knocked out 8000 eslint warnings with Oh My Opencode, just in a day" — [Jacob Ferrari](https://x.com/jacobferrari_/status/2003258761952289061)
> "I converted a 45k line tauri app into a SaaS web app overnight using Ohmyopencode and ralph loop. Started with interview me prompt, asked it for ratings and recommendations on the questions. It was amazing to watch it work and to wake up this morning to a mostly working website!" - [James Hargis](https://x.com/hargabyte/status/2007299688261882202)
> "use oh-my-opencode, you will never go back" — [d0t3ch](https://x.com/d0t3ch/status/2001685618200580503)
> "I haven't really been able to articulate exactly what makes it so great yet, but the development experience has reached a completely different dimension." - [
> "You guys should pull this into core and recruit him. Seriously. It's really, really, really good." — Henning Kilset
> "Hire @yeon_gyu_kim if you can convince him, this dude has revolutionized opencode." — [mysticaltech](https://x.com/mysticaltech/status/2001858758608376079)
Hey please read this readme and tell me why it is different from other agent harness? why is this actually good? https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/refs/heads/dev/README.md
I still can't believe a human — not an agent — is reading this.
Just install it. Type `ultrawork` (or `ulw`). That's it.
Every feature below — this entire bible-length list of highlights — you don't need to know any of it. Sorry we have too many good features. It just works.
| ✅ | **Todo Enforcer** | Agent goes idle? System yanks it back. Your task gets done, period. |
| 💬 | **Comment Checker** | No AI slop in comments. Code reads like a senior wrote it. |
| 🖥️ | **Tmux Integration** | Full interactive terminal. REPLs, debuggers, TUIs — all live. |
| 🔌 | **Claude Code Compatible** | Your hooks, commands, skills, MCPs, and plugins? All work here. |
| 🎯 | **Skill-Embedded MCPs** | Skills carry their own MCP servers. No context bloat. |
| 📋 | **Prometheus Planner** | Interview-mode strategic planning before any execution. |
| 🔍 | **`/init-deep`** | Auto-generates hierarchical `AGENTS.md` files throughout your project. Great for both token efficiency and your agent's performance |
**Sisyphus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`** ) is your main orchestrator. He plans, delegates to specialists, and drives tasks to completion with aggressive parallel execution. He does not stop halfway.
**Hephaestus** (`gpt-5.3-codex`) is your autonomous deep worker. Give him a goal, not a recipe. He explores the codebase, researches patterns, and executes end-to-end without hand-holding. *The Legitimate Craftsman.*
**Prometheus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`** ) is your strategic planner. Interview mode: it questions, identifies scope, and builds a detailed plan before a single line of code is touched.
> Anthropic [blocked OpenCode because of us.](https://x.com/thdxr/status/2010149530486911014) That's why Hephaestus is called "The Legitimate Craftsman." Irony intended.
>
> Honestly, we run best on Opus — but the Kimi K2.5 + GPT-5.3 Codex combo already outperforms vanilla Claude Code. You don't need to configure anything.
Every hook, command, skill, MCP, and plugin you configured for Claude Code works here — without changes. The compatibility layer is complete, including plugin support.
The harness problem is real. Most agent failures aren't model failures — they're edit tool failures.
> *"None of these tools give the model a stable, verifiable identifier for the lines it wants to change... They all rely on the model reproducing content it already saw. When it can't — and it often can't — the user blames the model."*
>
> — [Can Bölük, The Harness Problem](https://blog.can.ac/2026/02/12/the-harness-problem/)
Inspired by [oh-my-pi](https://github.com/can1357/oh-my-pi), we implemented **Hashline** — every line the agent reads comes back tagged with a content hash:
The agent edits by referencing those tags. If the file changed since the last read, the hash won't match and the edit is rejected before corruption. No whitespace reproduction. No stale-line errors.
Agents auto-read the relevant ones when touching any file. Zero manual context management.
### Planning — Prometheus
Complex task? Don't just prompt and hope.
`/start-work` invokes Prometheus — it **interviews you like a real human programmer**, identifies scope and ambiguities, and produces a detailed verified plan before execution begins. The agent knows exactly what it's building before it starts.
### Skills
Skills are more than prompts. Each brings:
- Specialized system instructions tuned for the domain
- Embedded MCP servers that spin up on demand
- Scoped tool permissions — agents can't go out of bounds
Built-in: `playwright` (browser automation), `git-master` (atomic commits, rebase surgery, history archaeology), `frontend-ui-ux` (design-first UI development).
Load your own from `.opencode/skills/*/SKILL.md` or `~/.config/opencode/skills/*/SKILL.md`.
**Want the full feature breakdown?** See the **[Features Documentation](docs/features.md)** — agents, hooks, tools, MCPs, and everything else in detail.
---
> **Want the backstory?** Read the [mythology behind our agents](docs/agent-lore.md) — why Sisyphus rolls boulders, why Hephaestus is "The Legitimate Craftsman", and [why we chose OpenCode](docs/agent-lore.md#why-opencode).
>
> New to oh-my-opencode? Check the **[Agent-Model Matching Guide](docs/guide/agent-model-matching.md)** for model recommendations.
We have lots of features that you'll think should obviously exist, and once you experience them, you'll never be able to go back to how things were before.
See the full [Features Documentation](docs/features.md) for detailed information.
The answers to every problem I hit are baked into this plugin. Just install and go.
If OpenCode is Debian/Arch, Oh My OpenCode is Ubuntu/[Omarchy](https://omarchy.org/).
Heavily influenced by [AmpCode](https://ampcode.com) and [Claude Code](https://code.claude.com/docs/overview)—I've ported their features here, often improved. And I'm still building.
It's **Open**Code, after all.
Enjoy multi-model orchestration, stability, and rich features that other harnesses promise but can't deliver.
I'll keep testing and updating. I'm this project's most obsessive user.
99% of this project was built using OpenCode. I tested for functionality—I don't really know how to write proper TypeScript. **But I personally reviewed and largely rewrote this doc, so read with confidence.**
