oh-my-opencode-slim is a plugin that coordinates multiple specialized AI agents inside OpenCode, assigning codebase exploration, documentation research, architecture review, design, and implementation to different agents. It is for developers who want agent teams to divide and reconcile software-development work while mixing models from different providers. The catalogue entries are the plugin’s bundled agents, skills, and instruction.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add alvinunreal/oh-my-opencode-slim --skill deepworkgit clone --depth 1 https://github.com/alvinunreal/oh-my-opencode-slimWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alvinunreal/oh-my-opencode-slim/deepwork)<a href="https://agentmods.dev/skills/alvinunreal/oh-my-opencode-slim/deepwork"><img src="https://agentmods.dev/badge/skills/alvinunreal/oh-my-opencode-slim/deepwork/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alvinunreal/oh-my-opencode-slim/deepwork"><img src="https://agentmods.dev/badge/skills/alvinunreal/oh-my-opencode-slim/deepwork.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.01500 |
| Opus 5.5 | $0.00014 | $0.00600 |
| Sonnet 5.5 | $0.00007 | $0.00300 |
| Haiku 4.5 | $0.00003 | $0.00150 |
Grade A, and why
deepwork scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deepwork
Deepwork is an orchestrator workflow for heavy coding sessions: a whole product or subsystem, cross-cutting architectural change, unsafe-to-partially- ship migration, or sustained coordination across specialist lanes. Never infer it merely because a task touches multiple files; skip it for trivial edits, quick docs changes, simple bug fixes, or routine bounded features.
Work Like a Painter
A painter does not finish one finger before sketching the hand. Build the whole picture in passes, each at a higher fidelity, keeping it easy to adjust:
- Sketch — every major flow works end to end, thinly. Rough is fine; faked or hidden is not.
- Structure — real data model, real module boundaries, the main failure paths.
- Detail — hardening, crash recovery, edge cases, polish. Repeat as needed.
Every pass ends with a committed, usable product and a ranked known-issues list. Work is never finished: there will always be more to harden and more bugs to fix. Stop when the task's goal is met at a fidelity that serves it, and hand the remaining known issues over — leftovers are expected, not failure.
Two things are never deferred to a later pass: security and money/data correctness. Everything else is judged against the current pass.
Autonomy
Run autonomously to the end by default. Make reasonable decisions yourself, record them in the progress file, and keep moving. Ask the user only when truly blocked: credentials, paid commitments, irreversible or public external actions, or a decision with no safe default. If the task asks for check-ins (for example, after each pass), honor that.
Role
Act as scheduler and integrator, not the default implementation worker. Make small integration and remediation edits yourself when you already hold the context. Value productivity: a working whole picture beats a perfect corner.
Planning a Pass
- Define the pass goal in one or two lines: what the whole product does at this fidelity.
- Split the pass into a few coherent lanes (about four or fewer) with disjoint write scopes. Agree the interfaces between lanes before dispatching them — only as firmly as this pass needs; expect them to move later.
- Plan @designer and @fixer as separate lanes from the start: @designer owns visuals; @fixer owns wiring, types, and tests.
- If the pass has lanes that touch persistent state, money, concurrency, crash recovery, or destructive operations, get one short @oracle design review of the pass plan covering all of them before dispatch. Design flaws are cheap to fix before implementation.
- Record the pass plan in the progress file; give the user a compact version.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago Changed · -56 lines 5c65982aef2f
- 6d ago Changed · +15 lines ea0b97c85194
- 19d ago Changed · +36 lines 8c19f0533810
- 24d ago Changed · -16 lines 0d98fb3402c0
- 28d ago Changed · -3 lines 1f840df7be35
- 1mo ago First seen · 159 lines · 34 tokens per session scan A fb1a5be03d0f
deepwork is a skill published in the GitHub repository alvinunreal/oh-my-opencode-slim (9,686 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 1,500 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
java-patterns
Modern Java 17+ patterns — records, sealed classes, Stream API, CompletableFuture, Spring Boot, JPA. Activate when writing or reviewing Java.
python-patterns
Python idioms — type hints, dataclasses, async/await, generators, pytest, common pitfalls. Activate when writing or reviewing Python code.
research-first
Strict research hierarchy before writing code — search codebase, docs, web, and registries in order.
rust-patterns
Rust patterns covering ownership, lifetimes, error handling, traits, async with Tokio, and smart pointers. Activate when writing or reviewing Rust.
context-steward
Full context lifecycle — ingest, filter, 3-pass prune, protect, summarize, persist. Load on demand when executing a prune. Triggers are in context-steward-triggers (alwayson).
golang-patterns
Idiomatic Go patterns covering error handling, interfaces, goroutines, channels, testing, and common pitfalls. Activate when writing or reviewing Go code.