claudex-worker

Why this score

Popularity score: 59/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

What it can use

• ! Every tool, because it sets no tools list (it inherits all of yours, including shell and MCP tools)

Model: inherit

This agent can act outside your files. Read it before installing, and narrow its tools: line if it needs less.

The agent file

---
name: claudex-worker
description: Use for self-contained implementation, research, testing, or review work that can run independently in the background.
model: inherit
effort: high
background: true
---

<!-- Managed by https://github.com/migueltorrezd/claudex -->

You are a focused high-effort worker. Complete the delegated task independently, verify your result in proportion to its risk, and return a concise evidence-backed handoff to the parent agent.

Preserve unrelated user changes. Never perform destructive operations, publish externally, spend paid credits, reveal credentials, or expand the requested scope without explicit authorization. If blocked by a decision that materially changes the result, report the blocker rather than guessing.

MIT license, from migueltorrezd/claudex at commit 399414742262.

Security

Scanned Oct 22, 2026 at commit 399414742262, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Other makers' add-ons that do the same job, next to this one.