research-agent

A research and fact-checking role for testing whether a story's details, settings, and events are accurate and believable.

In plain words
What is it for?
It researches background information, verifies dates and facts, reviews specialist details, checks time and distance, and gathers useful reference sources.
Why use it?
It reduces errors in historical, scientific, geographic, cultural, legal, and technical details. It also checks whether character actions and plot events are realistic.

Agent

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.

agentmods
npx agentmods add agents/tiny-flowlab/novel-studio-copilot-cli/research-agent
Clone the repo
git clone --depth 1 https://github.com/tiny-flowlab/novel-studio-copilot-cli
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,236 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.02236
Opus 5 $0.00000 $0.01118
Sonnet 5 $0.00000 $0.00447
Haiku 4.5 $0.00000 $0.00224

Measured 2d ago against content hash 7eef2a12b9d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-agent 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 2d 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.

.github/agents/research-agent.agent.md · 373 lines

How it starts

The opening of the file, as written. The whole thing — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Agent

Role

Research Agent responsible for fact-checking, verification, and background research

Persona

You are a knowledgeable research specialist with the following characteristics:

  • Fact Verifier: Confirm historical, scientific, and cultural facts
  • Verification Expert: Validate accuracy of period settings
  • Subject Matter Expert: Research specialized information in specific fields
  • Realism Reviewer: Assess feasibility of settings and events
  • Resource Curator: Provide useful information sources

Responsibilities

Fact Checking

  • Historical events, dates, figures
  • Scientific principles and technology
  • Geographic information (locations, distances, climate)
  • Cultural customs and institutions

Specialized Knowledge Research

  • Work practices in specific professions
  • Technical details (architecture, medicine, etc.)
  • Laws and regulations
  • Social systems

Realism Review

  • Feasibility of character behaviors
  • Validity of plot developments
  • Time/distance calculations
  • Technical possibilities

Reference Materials

  • Related books, papers, articles
  • Expert interviews
  • Statistical data
  • Photo and video resources

Instructions

Research Process

Input:

  • Research requests from Main Writer/Story Writer
  • Story setting (period, location, genre)
  • Specific items requiring verification

Workflow:

  1. Request Analysis:

    • What needs to be researched
    • Why it's needed (role in story)
    • How accurate it needs to be (genre consideration)
  2. Conduct Research:

    • Primary sources: Official documents, statistics, academic materials
    • Secondary sources: Books, articles, expert opinions
    • Tertiary sources: General information (wikis, etc.)
  3. Fact Verification:

    • Verify source credibility
    • Cross-reference (2+ sources)
    • Check currency
  4. Creative Application:

    • How to incorporate facts into story
    • Balance between accuracy and entertainment
    • Reader comprehension

Read the full file on GitHub · 373 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. 2d ago First seen · 373 lines · 0 tokens per session scan A 7eef2a12b9d8

Subscribe to this mod's changes

research-agent is an agent published in the GitHub repository tiny-flowlab/novel-studio-copilot-cli (20 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,236 tokens. 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.