Orca — Security skill for Claude Code
A local harness for the coding agents you already run: let Claude Code or Codex spawn and depend on subagents over MCP, with governed lanes, git-worktree isolation, an audit gate, and a private phone.
How to install Orca
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open alex2481kobe/orca and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Orca does
A local harness for the coding agents you already run: let Claude Code or Codex spawn and depend on subagents over MCP, with governed lanes, git-worktree isolation, an audit gate, and a private phone dashboard over Tailscale.
Alternatives in Security
- Deepsec — Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents 7.8k ★
- T3mp3st — autonomous red teaming platform; multi-agent offensive-security meta-harness 5.7k ★
- Security Health Check — Execute the security-health-inline skill for inline orchestration 172 ★
README
Orca
A local harness that lets the coding agents you already run spawn and depend on each other — and watch them from your phone.
Orca is a **local daemon**. It ships **no agent, no model, no API keys, and no chat UI**. You keep working in Claude Code, Codex, or any MCP-capable agent; Orca is the harness those agents register with so one of them can reliably **spawn a subagent, wait on it, and judge the result** — instead of you babysitting terminals.
[](LICENSE)
Status: in development, deliberately scaled back
Orca was built out **too aggressively before it was validated** — it grew a chat UI, an in-app composer, provider plumbing, and a pile of features that were never proven useful. So it was cut back on purpose.
What's left is the part that actually earns its place: **a harness around the CLI agents you already use.** Not a platform, not an agent, not another place to type prompts. If you want a different model or a different CLI, you change nothing here — Orca drives whatever you already run.
Expect rough edges and breaking changes. Validated on macOS with phone access. Windows/Linux are not validated yet.
What it does
You are already running coding agents. The hard part is making one agent lean on **another** — hand it a scoped task, wait for it to finish, and know whether the work is any good — without sitting in a terminal watching.
- Agent spawns agent. An orchestrator agent registers with Orca for its working directory, then spawns executor subagents — same CLI or a different one. Full MCP passes through, and the contract is enforced by the server, not by prompt text. The orchestrator can wait on a subagent a
Related Skills
AI Coding Orchestrator
A production-ready CLI & MCP orchestrator coordinating multi-agent AI │ coding (Codex, AGY, Claude, Gemini) wi
Guardskill
Read-only scanner for git settings that let a repository run code in coding agents (Claude Code, Codex, Cursor
Fit Audit
Audit the fit between an already-deployed Claude Code harness and the current state of the target project (tra
POC
Generate an executable proof-of-concept exploit for a confirmed High/Critical finding — detect the toolchain,
Find Wasted Effort
Run the find-wasted-effort audit — the process-per-outcome (ceremony) sibling of /token-waste-audit. Parses Fl
Claude Skill Suite
Claude Code skills for running models cost-effectively: security gates (secret scanner, commit-gate), model-qu
Related Agents
Ade
Agent sessions routinely outlast the machine that started them, and checking a Claude Code or Codex run from a
Clean Room Alternative
Generates a design alternative in isolation, without seeing the first design. Used by the design-it-twice skil
Team Coordinator
Orquestrador de equipes de agentes para GarraRUST. Analisa a estrutura do projeto, atribui papéis especializad
