Argos — Security skill for Claude Code
Offensive security research framework, MCP server, and agent plugin for Codex, OpenCode, and Claude Code.
How to install Argos
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open rafabd1/Argos and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Argos does
Offensive security research framework, MCP server, and agent plugin for Codex, OpenCode, and Claude Code.
Alternatives in Security
- T3mp3st — autonomous red teaming platform; multi-agent offensive-security meta-harness 5.7k ★
- Skills — Trail of Bits Claude Code skills for security research, vulnerability detection, and audit workflows 4k ★
- Anthropic Cybersecurity Skills — 734+ structured cybersecurity skills for AI agents · MITRE ATT&CK mapped · agentskills.io open standard · Work 3.8k ★
README
Argos
**An offensive security research framework for Codex, OpenCode, and Claude Code**
Argos is an agent plugin, MCP server, and CLI for offensive security research. It keeps a durable map of what a target does, how its parts relate, what has been tested, and which conclusions still depend on unproven assumptions. Each real item has one canonical Markdown note. Typed links connect components, sinks, data, authority, state, tests, evidence, and findings.
The map helps an agent recover more than matching text. It can follow nearby relations, find paths between sinks, flag partial test coverage, show knowledge age, and suggest missing links for review. Every structural change remains explicit.
| Canonical knowledge | Linked recovery | Blind-spot checks | Obsidian view |
|---|---|---|---|
| One current note per item. Replaced text is discarded. | Bounded subgraphs instead of full database dumps. | Partial path coverage, mixed evidence, old premises, and missing context. | Automatically refreshed Markdown notes, exact graph links, a compact index, and a Bases explorer. |
Install
Argos requires Node.js 24 or newer.
npm install -g https://codeload.github.com/rafabd1/Argos/tar.gz/refs/heads/main
argos --version
Install the Codex plugin marketplace:
cod
Related Skills
Hackz Huntkit
Offensive-security playbooks for AI coding agents — IDOR, 403 bypass, CORS, finding validation and dupe-checki
Secure Vibe
Open-source security skill for AI agents (opencode / Codex / Claude Code). Detects 97 secret/injection/deseria
OpenTag
Open-source, channel-native agent gateway for Slack. Route team threads to Claude Code, Codex, OpenCode, Docke
Reviewgate
Fail-closed independent review loop for Claude Code and Codex. Native hooks, six reviewer paths (Codex, Gemini
Buster Claw
A macOS desktop app that gives your own Claude Code, Codex or OpenCode agent hands: a browser it can drive, yo
Trail Of Bits Claude-code-config
Opinionated production defaults from a top security firm: sandboxing, permissions, hooks, skills, MCP server c
Related Agents
Codex Bridge
把指定工作外包給 gpt-5.5(codex)並忠實回傳其輸出。當需要 gpt-5.5 的批量實作或獨立第二審查視角時使用。這是 plugin 內第三種 codex 路徑:一次性 codex exec CLI 呼叫、輸出
Agent Of Empires
Claude Code, OpenCode, Mistral Vibe, Codex CLI, Gemini CLI Coding Agent Terminal Session manager via tmux and
Skills Manager (AI 技能管理器)
一款用于管理 AI 编程助手技能(Skills)的统一桌面应用。 无缝组织、同步和共享 Claude Code、Codex、Opencode 及其他 AI 工具的技能。 Version Platform