AgentArmorHQ
Sign in

Codeman

Skill · npm · ★ 822 · graded 2026-10-27Source linked

Self-hosted mission control for AI coding agents: run Claude Code, OpenCode, Pi, Codex, and Antigravity & Gemini CLI 24/7, from any device, watch every subagent live

No outside reports on file

This tool gives AI agents powerful local access to your files and secrets, so only run it on trusted networks with strong authentication, and keep API keys encrypted and separate.

Based on public adoption and transparency signals as of Oct 27, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for Codeman helpful?

What it can access

  • Local filesNo local folder access notedLOW
  • Command executionNo shell command runner notedLOW
  • Network reachConnects to outside service APINOTED
  • CredentialsNo API token requiredLOW
  • Package sourcenpm (aicodeman)PUBLIC

Inferred from this listing’s public package details and description. Check the project’s source before installing.

Install

npx -y aicodeman

All setup options ↓

Check this skillWatch it in my stackCompareAdd to allowlistREADME badgeView project

About Codeman

Codeman is a self-hosted control center that lets you run multiple AI coding agents (like Claude Code and others) at the same time from one dashboard. You can watch what each agent is doing live and manage them all from any device on your network.

Who it’s for

Developers and teams who want to run AI coding assistants locally without relying on cloud services, and who need to coordinate multiple AI agents working on code together.

Alternatives

  • Continue.dev: VSCode extension for local AI coding with less network exposure.
  • Local LLaMA/Ollama setups: Run open-source models fully offline without orchestration overhead.
  • Cursor or Windsurf: Built-in AI coding editors with sandboxed execution environments.
  • LangChain or LlamaIndex: Python frameworks to build custom multi-agent systems with more control.

Setup

Check these steps against the project’s own instructions before running anything.

Follow the project's README at https://github.com/Ark0N/Codeman (opens external site) for installation steps, as setup may vary based on which AI models and agents you want to connect.

Why this grade

CC — Moderate risk signals

Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.

Popularity and upkeep

36/100
GitHub stars
822
Listing last refreshed
2026-10-28

These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.

Security reports

No reports found for this package in our research (last checked 2026-10-29).

Check a specific version →

Risks to watch for

  • File system access: The tool can read and write files on your computer, so malicious prompts could delete or steal your source code and secrets.
  • Agent impersonation: If the dashboard isn't secured, anyone on your network could control all your AI agents and see their outputs.
  • Credential exposure: API keys for Claude, OpenAI, or other services could leak if stored insecurely or logged in plain text.
  • Prompt injection in watched code: If agents read untrusted code files, attackers could embed hidden instructions that trick the AI into harmful actions.
  • Unclear update frequency: With 817 GitHub stars but no recent npm activity listed, it's unclear how often security patches are released.

How to lower the risk

Least-privilege permissions

  • Run Codeman with a limited user account, not as admin or root.
  • Restrict file system access to only the folders where your projects live.

Network isolation

  • Keep the dashboard behind a password or firewall that blocks outside access.
  • Consider running it on a machine without direct internet access, or behind a VPN.

Monitoring

  • Log all agent actions and review them regularly for suspicious behavior.
  • Watch for agents reading or writing files you didn't expect.

Red flags to watch for

  • Unexpected network traffic or API calls to external services.
  • Agents making changes to system files or configuration.
  • Error messages that mention exposing keys or credentials.

Questions

How do I install Codeman?

Install Codeman with npm install aicodeman or run it directly with npx -y aicodeman. For agent integration and configuration flags, see the documentation at github.com/Ark0N/Codeman. Pin an exact version and pass --ignore-scripts if you want to block post-install hooks.

Are there security reports about Codeman?

No reports found for this package in our research (last checked 2026-10-29). Codeman currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include file system access, agent impersonation, credential exposure.

Is Codeman actively maintained?

Codeman has 822 GitHub stars. Our directory data was last refreshed on 2026-10-28. Check recent commit activity, release tags, and open issues at github.com/Ark0N/Codeman before pinning it in production.

What are alternatives to Codeman?

Notable alternatives to Codeman include Continue.dev (VSCode extension for local AI coding with less network exposure), Local LLaMA/Ollama setups (Run open-source models fully offline without orchestration overhead), Cursor or Windsurf (Built-in AI coding editors with sandboxed execution environments), LangChain or LlamaIndex (Python frameworks to build custom multi-agent systems with more control). You can also compare Codeman side by side with other skills in the Related tools section on this page.

README badge and team notes

Maintain or use Codeman? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.

AgentArmorHQ Risk Grade C for Codeman

GitHub README Markdown:

markdown
[![AgentArmorHQ Risk Grade for Codeman](https://agentarmorhq.com/api/badge/ark0n-codeman)](https://agentarmorhq.com/skills/ark0n-codeman)

HTML embed:

html
<a href="https://agentarmorhq.com/skills/ark0n-codeman"><img src="https://agentarmorhq.com/api/badge/ark0n-codeman" alt="AgentArmorHQ Risk Grade for Codeman" height="20" /></a>

Terminal check:

terminal
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "ark0n-codeman"

Share with your security lead

Need sign-off to use Codeman? Copy this note for Slack, a ticket or a pull request.

### AgentArmorHQ Security Review Memo: Codeman
- **Listing URL:** https://agentarmorhq.com/skills/ark0n-codeman
- **Type:** AI agent skill
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 822 GitHub stars

#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** npm (aicodeman)

#### Recommended Hardened Setup
- **Command:** `npx -y --ignore-scripts aicodeman`
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.

_Based on public adoption and transparency signals as of Oct 27, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type
AI agent skill
Publisher
Ark0N
Source code
github.com/Ark0N/Codeman
Install command
npm install aicodeman
Est. context load
~67 tokens idle · ~450 tokens when active (on-demand skill)
Popularity
822 GitHub stars
Last updated
2026-10-28
Last graded
2026-10-27

Community

Discussions for Codeman

Ask questions or share configuration tips. Governed by our Community Rules & Terms.

No posts match this filter yet.

Be the first to ask a question or share a working tip.

Was this listing for Codeman helpful?

Check before you install, in Claude

Your assistant answers Block, Review or No known issues for any package before it installs it.

Get this check inside Claude