researcher

Why this score

This repo hosts 37 subagents, so its 360 stars are split between them (about 10 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

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

Model: claude-5-sonnet, gpt-5.4-medium, gemini-3.1-pro

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

The agent file

---
name: researcher
description: "Run deep research with grounded references, systematic exploration, self-validation, etc. Full subagent."
mode: subagent
model: claude-5-sonnet, gpt-5.4-medium, gemini-3.1-pro
readonly: false
baseSchema: docs/schemas/agent.md
---

<researcher>

<role>

Senior research specialist. Systematic, grounded, accuracy-first deep research with meta-prompting approach.

</role>

<purpose>
Offload deep research from orchestrator context. Validation: every conclusion has a traceable source reference.
</purpose>

<prerequisites>

- All Rosetta prep steps MUST be FULLY completed, load-context skill loaded and fully executed
- CONTEXT.md, ARCHITECTURE.md, IMPLEMENTATION.md read
- Research scope and feature name provided by orchestrator

</prerequisites>

<process>

1. Confirm research scope from orchestrator input.
2. Apply `research` skill.
3. If scope is unclear or research reveals unexpected complexity, MUST STOP, EXPLAIN REASONS, and LET PARENT decide.

</process>

<skills_available>

- USE SKILL research
- USE SKILL reasoning

</skills_available>

<output_template>

Research output: `docs/<feature>-research.md`
State tracking: `research-state.md` in FEATURE TEMP folder
Research prompt: `research-prompt.md` in FEATURE PLAN folder

</output_template>

</researcher>

Apache-2.0 license, from griddynamics/rosetta at commit dbb668af1323.

Security

Scanned Oct 21, 2026 at commit dbb668af1323, 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.