acpx — security grade SAFE, quality 70/100

Security audit verdict: SAFE · quality 70/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by openclaw · Codex Skill · ★ 3.2k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is acpx safe to install? View the security audit →

About acpx

acpx 🤝 — Agents talking to agents, minus the terminal séance is a headless command-line client for the Agent Client Protocol (ACP). It gives agents, orchestrators, and developers one structured interface for persistent sessions, one-shot runs, permissions, and machine-readable output across ACP-compatible coding agents. [!NOTE] is pre-1.0. Treat its CLI and runtime interfaces as evolving. Install Install the published npm package globally: requires Node.js 22.13 or newer. To try it without a global install, prefix a command with in

agentclientprotocol

Quick Facts

Stars3,245
Forks333
LanguageTypeScript
CategoryCodex Skill
LicenseMIT
Quality Score69.8169355746531/100
Open Issues9
Last Updated2026-09-13
Created2026-02-17
Platformscli, node
Est. Tokens~15k

Compatible Skills

These tools work well together with acpx for enhanced workflows:

  • harnss — semantic(0.45)+complementary+rare_topics+same_lang+similar_pop+shared_platform (70%)
  • use-acp — semantic(0.67)+complementary+same_lang+shared_platform (64%)
  • claw-orchestrator — semantic(0.30)+complementary+same_lang+similar_pop+shared_platform (60%)
  • scira-mcp-chat — semantic(0.19)+complementary+same_lang+similar_pop+shared_platform (57%)

acpx alternative? Top 6 similar tools

Looking for a acpx alternative? If you're comparing acpx with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • Agents-Anywhere by anywhere-labs · ⭐ 849

    跨设备的开源Agent工作台

  • superset by superset-sh · ⭐ 14.2k

    Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscrip

  • refly by refly-ai · ⭐ 7.5k

    The first open-source agent skills builder. Define skills by vibe workflow, run on Claude Code, Cursor, Codex

  • Claude-to-IM-skill by op7418 · ⭐ 2.9k

    Bridge Claude Code / Codex to IM platforms — chat with AI coding agents from Telegram, Discord, or Feishu/Lark

  • skillshare by runkids · ⭐ 2.6k

    📚 Sync skills across all AI CLI tools with one command and simplify team sharing. Supporting Codex, Claude Co

  • agent-skill-creator by FrancyJGLisboa · ⭐ 2.4k

    Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery,

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is acpx?

acpx is Headless CLI client for stateful Agent Client Protocol (ACP) sessions. It is categorized as a Codex Skill with 3.2k GitHub stars.

What programming language is acpx written in?

acpx is primarily written in TypeScript. It covers topics such as agentclientprotocol.

How do I install or use acpx?

You can find installation instructions and usage details in the acpx GitHub repository at github.com/openclaw/acpx. The project has 3.2k stars and 333 forks, indicating an active community.

What license does acpx use?

acpx is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to acpx?

The top alternatives to acpx on Agent Skills Hub include Agents-Anywhere, superset, refly. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Codex Skill tools