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/MSApps-Mobile/claude-pluginsWrote 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/msapps-mobile/claude-plugins/sosa-orchestrator)<a href="https://agentmods.dev/plugins/msapps-mobile/claude-plugins/sosa-orchestrator"><img src="https://agentmods.dev/badge/plugins/msapps-mobile/claude-plugins/sosa-orchestrator/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/msapps-mobile/claude-plugins/sosa-orchestrator"><img src="https://agentmods.dev/badge/plugins/msapps-mobile/claude-plugins/sosa-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
sosa-orchestrator 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
{
"name": "sosa-orchestrator",
"version": "1.0.1",
"description": "SOSA Orchestrator — token-aware task prioritization and budget management for Claude sessions. Ranks tasks by importance vs. cost, tracks consumption in real time, and pauses work before budget boundaries are crossed.",
"author": {
"name": "MSApps Research",
"url": "https://msapps.mobi"
},
"repository": "https://github.com/MSApps-Mobile/claude-plugins",
"license": "MIT",
"privacy_policy": "https://opsagents.agency/privacy",
"terms_of_service": "https://opsagents.agency/terms",
"keywords": [
"sosa",
"orchestrator",
"token-budget",
"prioritization",
"task-management",
"governance"
],
"platforms": [
"claude-code",
"cowork"
],
"hooks": "./hooks/hooks.json",
"sosa": {
"compliant": true,
"level": 3,
"impact": "low",
"methodology": "https://github.com/MSApps-Mobile/claude-plugins/blob/main/docs/SOSA.md",
"pillars": {
"supervised": "Always pauses and asks user before stopping any task. Never auto-kills work.",
"orchestrated": "Maintains priority×cost matrix. Integrates with SOSA Governor budgets and Token Efficiency Audit patterns.",
"secured": "Read-only access to audit logs and budget configs. No credential handling. All decisions logged.",
"agents": "Role: Session resource manager. Tools: TodoList, scheduled-tasks, audit-log reader. Memory: session-ledger.json. Planning: Priority Score algorithm."
},
"dependencies": [
"sosa-governor",
"token-efficiency-audit"
]
}
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 192 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.
- 4d ago Changed 8bcd3135f77e
- 1mo ago First seen · 43 lines scan A e487e77db758
sosa-orchestrator is a plugin published in the GitHub repository MSApps-Mobile/claude-plugins (9 stars, last pushed today), 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 2026-09-13.
Other plugins, from other repositories
moai-coworker
A general-purpose AI coworker for business work and personal planning, with skills for areas such as branding, proposals, reports, negotiations, habits, travel, and events.
moai-officer
A collection of skills for producing Korean office documents and HTML reports or slides, including HWPX, DOCX, XLSX, PPTX, and PDF files. It also includes official-document parsing, Notion templates, and productivity routines.
agentic-os
Set up an agentic OS — inside an Obsidian vault (command-center dashboard + bundled plugins) or as a standalone Next.js web dashboard with live MCP integrations and optional Railway deploy. Includes /os-mcp to self-host the Relay MCP server.
ai-psychiatry
Semantic executive control for loopholes, underthinking, overthinking, evidence, recursion, context, memory, and reliable delivery.
attention-notify
Raise a local macOS banner for every PushNotification call and every attention-needed Notification event.
rad-google-workspace
Google Workspace integration — 44 service skills (Gmail, Calendar, Drive, Docs, Sheets, Slides, Chat, Meet, Tasks, Forms, Keep, Classroom, Model Armor, Apps Script), 41 workflow recipes, and 10 role-based personas. Requires the gws CLI binary.