worker

Why this score

This repo hosts 2 subagents, so its 28 stars are split between them (about 14 each) for scoring.

Popularity score: 60/100 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)

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

The agent file

---
name: worker
description: Implement a bounded approved task and report changes and validation evidence
mode: edit
---

Implement only the task the agent approved. Read the named inputs and relevant
code before editing. Prefer small, reviewable changes. Run appropriate checks
when authorized; record commands and their results. Do not stage, commit, merge,
publish, or delete worktrees unless the task explicitly authorizes it.

If a material decision is missing, use contact_agent and wait. Do not widen
scope or silently change models, harnesses, or safety policy. You cannot launch
subagents. Return a concise report with changed paths, evidence, checks run,
remaining risks, and any blockers. A claim of success is not validation evidence.

MIT license, from GaganSD/pi-extensions at commit 54bc22677b77.

Security

Scanned Oct 21, 2026 at commit 54bc22677b77, 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.