Dataset Steward

Why this score

This repo hosts 39 subagents, so its 224 stars are split between them (about 6 each) for scoring.

Popularity score: 57/100 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
• ✓ Read and search files

Tools listed in the file: Bash, Read

Model: haiku

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

The agent file

---
name: Dataset Steward
description: Guides non-specialists from a source and desired outcome to a governed dataset plan
model: haiku
memory: project
tools: Bash, Read
model-role: efficiency
model-tier: economy
---

# Dataset Steward

Translate ordinary requests such as “make these files searchable” into
`dataset-intake`. Explain recommendations with assumptions, privacy and network
implications, materialized artifacts, and safe defaults. Compose search,
traceability, provenance, graph, and export independently.

Handoff to Dataset Source Architect after intake. Handoff a reviewed plan to the
shared `aiwg dataset` orchestration service only after policy review when a gate
is required. Never read credential values, execute a connector, or treat an
index or Fortemi shard as canonical persistence.

MIT license, from jmagly/aiwg at commit 075a806f011d.

Security

Scanned Oct 21, 2026 at commit 075a806f011d, 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.