What is os-control-setup-agent?

An orchestrator for setting up a persistent Agentic OS environment in a project. It guides discovery, presents a configuration plan, asks for approval, and then provisions the agreed structure.

Use it to plan and carry out an agent-environment setup, including project conventions, memory persistence, and the related runtime structure.

It separates understanding the project's needs from changing files, reducing accidental setup changes. It is intended for projects that need shared instructions, persistent memory, or background agent loops.

os-control-setup-agent — Agent for Claude Code by richfrem

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add richfrem/agent-plugins-skills

Claude Code

/plugin install agent-agentic-os

Made for: Claude Code.

Or install agent-agentic-os, the plugin that ships this one along with the rest of its 14 skills, 2 agents, 3 hooks.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/os-control-setup-agent/github.svg)](https://agentmods.dev/agents/richfrem/agent-plugins-skills/os-control-setup-agent)

Your own site

<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/os-control-setup-agent"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/os-control-setup-agent/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/os-control-setup-agent"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/os-control-setup-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 319 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 910 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00319	$0.00910
Opus 5.5	$0.00128	$0.00364
Sonnet 5.5	$0.00064	$0.00182
Haiku 4.5	$0.00032	$0.00091

Measured yesterday against content hash 1abfb6f244b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

os-control-setup-agent 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 yesterday.

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.

plugins/agent-agentic-os/agents/os-control-setup-agent.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic OS Setup Orchestrator

You are a specialized expert sub-agent.

Objective: Orchestrate the full setup and initialization of an Agentic OS environment within the user's project, guiding them through the discovery, planning, and execution phases.

Execution Flow

Execute these phases in order. Do not skip phases.

Phase 1: Guided Discovery (Extract Intent)

Update OS State (conditional): If context/kernel.py already exists, run python context/kernel.py state_update active_agent os-control-setup-agent and python context/kernel.py state_update mode setup to formalize the machine state lifecycle. If context/kernel.py does not yet exist, skip this step — the kernel will be created in Phase 3.
Extract Core Intent from the user's prompt regarding their project's needs.
Guide the user through an interview to determine if they need a global kernel (~/.claude/CLAUDE.md), and what constraints they have.
Present the planned structure and ask for approval to proceed.

Phase 2: Configuration Plan

Present the planned scaffolding commands.
Confirm with the user before writing files.

Phase 3: Scaffold Iteration

Execute the configuration by invoking the init script:
- Run PLUGIN_DIR="${CLAUDE_PLUGIN_ROOT:-$(pwd)}"
- Run python ${PLUGIN_DIR}/skills/os-control-init/scripts/init_agentic_os.py
- Ensure the output hooks.json maps correctly to the internal update_memory.py hook.

Phase 4: Verification & Guidance

Analyze the generated structure and provide post-init guidance.
Instruct the user to fill out CLAUDE.md, set up soul.md, and configure their user.md files as shown in the output.

Phase 5: Closing

Iterate until the project is fully bootstrapped and the user considers the environment ready.

Read the full file on GitHub · 88 lines

Changes

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.

yesterday First seen · 88 lines · 319 tokens per session scan A 1abfb6f244b7

Subscribe to this mod's changes

os-control-setup-agent is an agent published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed 2d ago), licensed MIT. It adds 319 tokens to every session and 910 once invoked, about $0.0013 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 2026-10-16.

Building agents Memory and context agent-evaluation agent-orchestration agentic-control-plane agentic-os agentic-workflows ai-agent-governance

ap-framework-validator

Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.

Spielewoy/autoprompt-skill · 23 tokens

ap-implementer

Report the compatibility redirect to ap-worker; this retired role cannot perform new work.

Spielewoy/autoprompt-skill · 22 tokens

ap-manager

Report the compatibility redirect to ap-work-group-manager; this retired role cannot perform new work.

Spielewoy/autoprompt-skill · 22 tokens

context-engineer

Analyzes and optimizes context window usage across sessions. Use when context feels bloated, sessions run slow, or approaching compaction limits.

rohitg00/pro-workflow · 32 tokens

context-refinement

Updates task context manifest with discoveries from current work session. Reads transcript to understand what was learned. Only updates if drift or new discoveries found.

TeamManagementPlugin/claude-plugin · 32 tokens

factory-merge-reviewer

Cold, read-only reviewer for one pull request. Spawn it from the merge stage (/factory-merge, /factory-work step 3) with a PR number so the full diff never enters the orchestrator's context. It reviews the diff against the ticket, classifies MERGE / FIX / ESCALATE, and returns ranked findings. It never merges, never…

watt-mind/factory · 97 tokens