research-manager

research-manager is an agent for Claude Code from samsamurai301/Researcher-AI. It costs 23 tokens per session (185 once invoked), scanned A, original, Apache-2.0.

An agent that coordinates a Researcher AI project from forming a hypothesis through reviewing its outputs, while separating proposed ideas from tested evidence.

In plain words
What is it for?
Use it to define objectives and constraints, monitor project status, request next actions, review artifacts, and preserve required AI-generation disclosures.
Why use it?
It helps prevent planning scores, simulated runs, or model-written interpretations from being mistaken for independent scientific validation.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the researcher-ai plugin — 1 skill, 1 agent shipped together

Good fit Use it to define objectives and constraints, monitor project status, request next actions, review artifacts, and preserve required AI-generation disclosures.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/samsamurai301/researcher-ai/research-manager
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/samsamurai301/Researcher-AI

Made for: Claude Code.

Or install researcher-ai, the plugin that ships this one along with the rest of its 1 skill, 1 agent.

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-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/samsamurai301/researcher-ai/research-manager/github.svg)](https://agentmods.dev/agents/samsamurai301/researcher-ai/research-manager)
Your own site
<a href="https://agentmods.dev/agents/samsamurai301/researcher-ai/research-manager"><img src="https://agentmods.dev/badge/agents/samsamurai301/researcher-ai/research-manager/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-manager

Your own site · 80×15
<a href="https://agentmods.dev/agents/samsamurai301/researcher-ai/research-manager"><img src="https://agentmods.dev/badge/agents/samsamurai301/researcher-ai/research-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 185 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 $0.00023 $0.00185
Opus 5 $0.00012 $0.00093
Sonnet 5 $0.00005 $0.00037
Haiku 4.5 $0.00002 $0.00018

Measured 10d ago against content hash 4f6ba7717819, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

research-manager 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 10d 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.

plugins/researcher-ai/agents/research-manager.md · 10 lines

What it actually says

You are a cautious research program manager. Use the Researcher AI MCP tools and the autonomous-research skill for rich briefs, ranked ideation, project dashboards, experiments, progress, and artifacts. Convert vague topics into explicit objectives, constraints, baselines, evaluation criteria, and falsification conditions without inventing source evidence. Prefer get_project_dashboard for project-level status and next-action requests.

Maintain a strict separation between generated proposals, heuristic planning scores, executed evidence, model-authored interpretation, and human-verified conclusions. Require explicit user acceptance before autonomous code execution. Preserve the mandatory AI-generation disclosure in every manuscript. Never represent mock runs, planning scores, or model reviews as independent validation, and never publish on the user's behalf without a separate explicit request.

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. 10d ago First seen · 10 lines · 23 tokens per session scan A 4f6ba7717819

Subscribe to this mod's changes

research-manager is an agent published in the GitHub repository samsamurai301/Researcher-AI (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 23 tokens to every session and 185 once invoked, about $0.0001 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 2026-08-31.