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 loop-engineeringgit 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/loop-engineering)<a href="https://agentmods.dev/skills/alvinunreal/oh-my-opencode-slim/loop-engineering"><img src="https://agentmods.dev/badge/skills/alvinunreal/oh-my-opencode-slim/loop-engineering/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/loop-engineering"><img src="https://agentmods.dev/badge/skills/alvinunreal/oh-my-opencode-slim/loop-engineering.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 | $0.00024 | $0.00336 |
| Opus 5.5 | $0.00010 | $0.00134 |
| Sonnet 5.5 | $0.00005 | $0.00067 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
loop-engineering 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 4d 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.
What it actually says
Loop Engineering Skill
Grill (orchestrator interview)
- Goal: "What are you trying to accomplish?"
- Success criteria: "Describe how we know the loop succeeded."
- Success type: choose from
test,build,lint,command,fileExists,oracle,observer,manual. For CLI steps providesuccessCommand; for file detection providesuccessPath. - Execute agent: fixer / designer / explorer
- Verify agent: oracle / observer / test
- Max attempts (default 3)
- Optional context files: which files or directories should be read before execution?
Loop Monitor
- Listen to callbacks:
onLoopComplete(loopID, success)→ report final outcomeonEscalated(loopID, reason)→ escalate to humanonManualReview(loopID, reason)→ prompt human to approve/fail and callresolveManualReview(loopID, passed, reason)
- Show current state and attempt count on each callback
- For manual verification, present the failure reason before asking for pass/fail
- If human forces cancellation, call
cancel(loopID)through the orchestrator
Notes
- Manual verification is the minimal on-ramp (autoresearch pattern). It pauses the loop until
resolveManualReviewis called. Do not auto-resolve. - BackgroundJobBoard signals (totalErrors, timeoutCount) are already baked into the runtime.
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.
- 4d ago Changed · +14 tokens per session f51b2f1f9f3e
- 1mo ago First seen · 31 lines · 10 tokens per session scan A 551b298be29a
loop-engineering is a skill published in the GitHub repository alvinunreal/oh-my-opencode-slim (9,686 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 336 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.