OpenAgents Control is a framework that adds plan-first, approval-based coding workflows to OpenCode, an AI coding framework. Developers and teams use it to make agents follow shared coding patterns, work across several programming languages, and validate changes through testing and review. The catalogue includes its agents, skills, commands, plugin, and hook.
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.
git clone --depth 1 https://github.com/darrenhinde/OpenAgentsControlWrote 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/plugins/darrenhinde/openagentscontrol/claude-code)<a href="https://agentmods.dev/plugins/darrenhinde/openagentscontrol/claude-code"><img src="https://agentmods.dev/badge/plugins/darrenhinde/openagentscontrol/claude-code/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/plugins/darrenhinde/openagentscontrol/claude-code"><img src="https://agentmods.dev/badge/plugins/darrenhinde/openagentscontrol/claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
oac 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 1mo 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
{
"name": "oac",
"description": "OpenAgentsControl — multi-agent orchestration for Claude Code. Context-aware development with skills, subagents, parallel execution, and automated code review.",
"version": "1.0.2",
"author": {
"name": "darrenhinde",
"url": "https://github.com/darrenhinde"
},
"license": "MIT",
"repository": "https://github.com/darrenhinde/OpenAgentsControl",
"homepage": "https://github.com/darrenhinde/OpenAgentsControl#readme",
"keywords": ["code-review", "tdd", "multi-agent", "context-aware", "task-management", "parallel-execution", "workflow"]
}
What it installs
The manifest is a name and a version. 12 skills, 6 commands, 7 agents, 1 hook travel with it, and installing the plugin installs all of them — 1,029 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill debugger A 19 tokens
- Skill using-oac A 42 tokens
- Skill code-execution A 27 tokens
- Skill code-review A 28 tokens
- Skill parallel-execution A 21 tokens
- Skill task-breakdown A 29 tokens
- Skill test-generation A 27 tokens
- Skill external-research A 24 tokens
- Skill oac-approach A 32 tokens
- Skill context-discovery A 23 tokens
- Skill context-setup C 40 tokens
- Skill verification-before-completion A 43 tokens
- Command oac-cleanup A 14 tokens
- Command oac-status A 16 tokens
- Command brainstorm A 17 tokens
- Command install-context A 0 tokens
- Command oac-help A 8 tokens
- Command debug A 18 tokens
- Agent context-scout A 175 tokens
- Agent external-scout A 24 tokens
- Agent task-manager A 22 tokens
- Agent code-reviewer A 167 tokens
- Agent coder-agent A 175 tokens
- Agent test-engineer A 19 tokens
- Agent context-manager C 19 tokens
- Hook SessionStart A not measured
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.
- 1mo ago First seen · 14 lines scan A 0a0803d7c21b
oac is a plugin published in the GitHub repository darrenhinde/OpenAgentsControl (4,910 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
axint
Compile TypeScript intent definitions into native Apple App Intents and MCP tool servers. Define once, ship to Siri, Shortcuts, and Spotlight.
transmuter
Transmute Framework — AI-driven pipeline that transforms a business plan into a fully deployed product through 25 stages (23 automated, 2 manual).
specialist-agent
Your AI development team. 36 agents and 32 skills for building, reviewing, debugging, and shipping production code. Supports Vue, React, Next.js, SvelteKit, Angular, Astro, and Nuxt.
scaffold
AI-powered software project scaffolding — CLI pipeline with auto-activated skills for Claude Code.
spec-first marketplace
Spec-first development: define a spec, implement it, and generate docs.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.