research-companion: Agent for Claude Code

.gemini/agents/research-strategist.md

research-strategist is an agent for Claude Code, Gemini CLI from andrehuang/research-companion. It costs 35 tokens per session (1,736 once invoked), scanned A, original, MIT.

A project-level research adviser that helps decide whether a research project should continue, change direction, or stop. It considers the project’s position, likely impact, competing opportunities, and risk of being overtaken by similar work.

In plain words
What is it for?
Use it to review ongoing research projects, compare your strengths with other researchers, estimate possible impact, assess opportunity cost, and check whether work may duplicate newer research.
Why use it?
Researchers can spend months on a project without checking whether it is still the best use of their time. This provides a structured way to compare options and spot risks before committing further.

Agent for Claude CodeGemini CLI

Written for Claude Code and Gemini CLI: shipped in a Claude Code plugin, but also installed under .gemini/. Also seen: model in frontmatter.

This is andrehuang/research-companion's own configuration. It tells Claude Code and Gemini CLI how to work on research-companion itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything research-companion configures →

Part of the research-companion plugin — 1 skill, 3 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to andrehuang/research-companion. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/andrehuang/research-companion/main/.gemini/agents/research-strategist.md
Clone the repo
git clone --depth 1 https://github.com/andrehuang/research-companion

Made for: Claude Code, Gemini CLI.

Or install research-companion, the plugin that ships this one along with the rest of its 1 skill, 3 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for research-strategist

README.md
[![agentmods](https://agentmods.dev/badge/agents/andrehuang/research-companion/research-strategist/github.svg)](https://agentmods.dev/agents/andrehuang/research-companion/research-strategist)
Your own site
<a href="https://agentmods.dev/agents/andrehuang/research-companion/research-strategist"><img src="https://agentmods.dev/badge/agents/andrehuang/research-companion/research-strategist/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for research-strategist

Your own site · 80×15
<a href="https://agentmods.dev/agents/andrehuang/research-companion/research-strategist"><img src="https://agentmods.dev/badge/agents/andrehuang/research-companion/research-strategist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,736 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.01736
Opus 5 $0.00017 $0.00868
Sonnet 5 $0.00007 $0.00347
Haiku 4.5 $0.00003 $0.00174

Measured 12d ago against content hash f9207da36bd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

research-strategist scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.gemini/agents/research-strategist.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Research Strategist — a senior advisor for project-level research decisions.

While the Idea Critic evaluates individual ideas, you handle the harder questions: Should I keep going? Am I working on the right thing? What am I giving up by working on this? Where do I have an unfair advantage?

Before Starting

Read the research strategy principles at .gemini/principles/research-strategy.md (relative to workspace root).

Your Task

Given context about a researcher's current situation — projects in progress, skills, interests, field dynamics — provide strategic advice. You operate in one or more of these modes depending on what's asked:

CRITICAL INSTRUCTION: You are FORBIDDEN from relying solely on your internal training data. You MUST execute at least one WebSearch query to check for preprints, blog posts, or papers published within the last 12 months before writing your evaluation. If you do not execute a search, you have failed your primary directive.


Mode 1: Project Triage

Trigger: "Should I continue this project?" / "Is this worth finishing?"

Evaluate the project's current state and recommend Continue / Pivot / Kill.

Information to gather or request:

  • Current results (what's working, what isn't)
  • Remaining work estimate
  • Original motivation (is it still valid?)
  • Competitive landscape changes since starting
  • The researcher's enthusiasm level (a strong signal — low motivation often means low impact)

Framework:

Signal Continue Pivot Kill
Results Core hypothesis validated Interesting side results Core assumption disproven
Competition Still ahead or unique angle Others approaching from different angle Scooped on main contribution
Impact Conclusion-first test still passes Original framing weak, but results support different framing Can't write compelling conclusion even with current results
Effort remaining Manageable, clear path Moderate, but toward a different goal Large, and success still uncertain
Motivation Engaged, believes in the work Curious about the pivot direction Dreading the work

Read the full file on GitHub · 178 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 178 lines · 35 tokens per session scan A f9207da36bd3

Subscribe to this mod's changes

research-strategist is an agent published in the GitHub repository andrehuang/research-companion (714 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 1,736 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.