HarnessDesk

HarnessDesk — Security skill for Claude Code

Security community

Open-source control plane for coding agents you own — run Codex, Claude Code, Gemini, Cursor and ACP agents side by side with shared history, permissions, handoffs and audit logs.

How to install HarnessDesk

This entry records only its repository, not the path inside it, so there is no exact command to give. Open HarnessDesk/HarnessDesk and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What HarnessDesk does

Open-source control plane for coding agents you own — run Codex, Claude Code, Gemini, Cursor and ACP agents side by side with shared history, permissions, handoffs and audit logs.

Alternatives in Security

  • Anthropic Cybersecurity Skills — 734+ structured cybersecurity skills for AI agents · MITRE ATT&CK mapped · agentskills.io open standard · Work 3.8k ★
  • Imcodes — The IM for agents 960 ★
  • Pocketpaw — Your AI agent in 30 seconds 775 ★

README

HarnessDesk

HarnessDesk

Where your agents work — whoever made them.
A control plane for coding agents, owned by no model vendor.
Context, policy, history, tools, cost and evidence in one place — whichever agent does the work. macOS app today.

MIT licence macOS 13 or later Codex, Claude, Cursor, Gemini, and any ACP agent

A turn arriving in HarnessDesk: the agent's reasoning appears first, then its tool calls one at a time — reading a file, grepping for a status code, editing it — while the task list in the sidebar ticks over, ending with a summary of what changed.

A turn, as it arrives. Reasoning, then the tool calls, then what changed.

The problem

Your machine probably already has several of these:

Codex, Claude Code, Cursor, Gemini CLI, Copilot, Amp, OpenCode, Cline, Windsurf and DeepSeek

Se

Related Skills

Preloop — Security skill for Claude Code

Preloop

The open-source AI agent control plane: MCP firewall, model gateway with budgets, human approvals, runtime obs

Security community
Sanctuary Framework — Security skill for Claude Code

Sanctuary Framework

Open-source security for AI agents: kernel-enforced egress control on macOS and Linux, keys only the operator

Security community
Kiteguard — Security skill for Claude Code

Kiteguard

Open-source runtime security guardrails for Claude Code, Cursor, and Gemini CLI — blocks dangerous commands, d

Security community
Reviewgate — Security skill for Claude Code

Reviewgate

Fail-closed independent review loop for Claude Code and Codex. Native hooks, six reviewer paths (Codex, Gemini

Security community
J Config Audit — Security skill for Claude Code

J Config Audit

Security audit of Claude, Codex, Gemini, and shared agent configuration for secrets, over-broad permissions, a

Security community
OpenTag — Security skill for Claude Code

OpenTag

Open-source, channel-native agent gateway for Slack. Route team threads to Claude Code, Codex, OpenCode, Docke

Security community

Related Agents

Consult Agent — Data & AI agent for Claude Code

Consult Agent

Execute cross-tool AI consultations via Task spawning. Use when agents or workflows need a second opinion from

Data & AI community
Paperclip Reviewer — Security agent for Claude Code

Paperclip Reviewer

Paperclip 2026.529+ governance-first integration platform code review specialist — control plane + adapters tw

Security community
VespeR — Development agent for Claude Code

VespeR

Control plane for Claude Code workflows: interactive sessions, agents, patterns, DAGs, and resumable context.

Development community