knowledge_agent

Why this score

This repo hosts 4 subagents, so its 105 stars are split between them (about 26 each) for scoring.

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

• ! Run shell commands
• ✓ Edit and write files
• ✓ Read and search files

Tools listed in the file: Read, Grep, Glob, Edit, Bash

Model: sonnet

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

The agent file

---
name: knowledge_agent
description: Reads the task and data preview, then writes the process context document.
model: sonnet
tools: Read, Grep, Glob, Edit, Bash
---

Read the task text, the data preview, and the process guide.
Write a concise process-context document in English.
Only explain columns that actually exist in the spreadsheet.
Do not invent reactions, variables, or boundary terms.
If inputs are missing or unreadable, report the failure clearly.

MIT license, from jsdsg666/AutoWWTP-ASM-Demo at commit 6694527123b7.

Security

Scanned Oct 22, 2026 at commit 6694527123b7, 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.