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/danieljhkim/orbitWrote 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/danieljhkim/orbit/plugin)<a href="https://agentmods.dev/plugins/danieljhkim/orbit/plugin"><img src="https://agentmods.dev/badge/plugins/danieljhkim/orbit/plugin/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/danieljhkim/orbit/plugin"><img src="https://agentmods.dev/badge/plugins/danieljhkim/orbit/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
orbit 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": "orbit",
"version": "0.18.0",
"description": "Task and activity orchestration for AI coding agents. Adds Orbit's MCP tool surface, skills, and orchestration subagents to Claude Code.",
"author": {
"name": "danieljhkim",
"url": "https://github.com/danieljhkim"
},
"homepage": "https://github.com/danieljhkim/orbit",
"repository": "https://github.com/danieljhkim/orbit",
"license": "MIT",
"keywords": [
"orbit",
"task-management",
"agent-orchestration",
"mcp"
]
}
What it installs
The manifest is a name and a version. 3 agents, 1 hook travel with it, and installing the plugin installs all of them — 141 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 Changed 6de9c90147c4
- 1mo ago Changed · -1 lines ccafa44248f1
- 1mo ago First seen · 20 lines scan A a6ec3497dde5
orbit is a plugin published in the GitHub repository danieljhkim/orbit (10 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 2026-08-31.
Other plugins, from other repositories
simplicio-loop
Autonomous looping orchestrator + satellite skills that drains a backlog end-to-end on any LLM/runtime: discover, implement, verify, review, merge, close. /simplicio-loop is the unified public entrypoint for core + hardened loop; /simplicio-tasks remains only a legacy alias. Its Claude lifecycle route is Mapper-only…
simplicio-prompt
Tuple-Space + Yool safe-speed runtime for Claude Code. A UserPromptSubmit hook makes it always-on (injects the runtime contract on every prompt unless the user stands down). Routes any user input through a Hilbert-indexed tuple graph with lazy batchspawn, LaneWorkerPool, receipt cache, jittered backoff, circuit breake.
simplicio
Verified Simplicio Runtime MCP bootstrap with mandatory Mapper-only Claude hooks and reusable project-map cache.
simplicio-hermes
Authenticated Mapper-only context and provider cache telemetry for Hermes.
better-fullstack
Let your AI assistant scaffold and extend Better Fullstack projects through the official MCP server and focused skills.
agentbridge
Bridge Claude Code and Codex with a shared daemon, push channel delivery, and bidirectional reply tooling.