research

research is a command for Claude Code from WomenDefiningAI/claudecode-writer. It costs 0 tokens per session (445 once invoked), scanned A, original, MIT.

A research command for developing and refining ideas before writing. It examines trusted sources, current discussions, data, expert views, and audience questions.

In plain words
What is it for?
Use it with a topic to produce a research brief containing trend context, a distinct angle, supporting examples, and a possible article structure.
Why use it?
It reduces the chance of building an article around weak evidence or a common angle. It helps reveal missing viewpoints and useful supporting material.

Command for Claude Code

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 commands/womendefiningai/claudecode-writer/research
Clone the repo
git clone --depth 1 https://github.com/WomenDefiningAI/claudecode-writer

Made for: Claude Code.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/womendefiningai/claudecode-writer/research.svg)](https://agentmods.dev/commands/womendefiningai/claudecode-writer/research)
Your own site
<a href="https://agentmods.dev/commands/womendefiningai/claudecode-writer/research"><img src="https://agentmods.dev/badge/commands/womendefiningai/claudecode-writer/research.svg" alt="Measured on agentmods" height="20"></a>
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 445 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 $0.00445
Opus 5 $0.00000 $0.00222
Sonnet 5 $0.00000 $0.00089
Haiku 4.5 $0.00000 $0.00044

Measured 5d ago against content hash 316bacde0ccc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research 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 5d 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.

.claude/commands/research.md · 43 lines

What it actually says

Research Command

Use this command to develop and refine content ideas before writing.

Usage

/research [topic]

What This Command Does

  1. Explores the topic from multiple angles
  2. Identifies key insights and unique perspectives
  3. Suggests compelling hooks and storylines
  4. Researches supporting data and examples
  5. Outlines potential article structure

Process

  • Priority Source Check: Start with sources in @context/research-sources.md - check these FIRST
  • Gap Analysis: Identify what perspectives are missing from trusted source coverage
  • Trend Investigation: Check Google Trends, industry reports, social media discussions
  • Counter-narrative Search: Look for contrarian views or unexplored angles
  • Data Mining: Find recent studies, surveys, or statistics to support points
  • Expert Voices: Identify who else is talking about this and what they're missing
  • Audience Pulse: Research what questions people are actually asking about this topic
  • Broader Web Search: Expand beyond priority sources for comprehensive coverage

Output

Provides a research brief with:

  • Trend Context: What's currently happening in this space
  • Unique Angle: Your differentiated perspective vs. existing content
  • Core Thesis: Main argument supported by fresh data/insights
  • Supporting Evidence: Recent examples, studies, expert quotes
  • Audience Questions: What people are actually asking about this topic
  • Platform Hooks: Compelling angles for each repurposing agent
  • Contrarian Elements: Unexpected or challenging viewpoints to explore

File Management

After completing the research, automatically save the brief to:

  • File Location: research/research-brief-[topic-slug]-[YYYY-MM-DD].md
  • File Format: Markdown with clear sections and headers
  • Naming Convention: Use lowercase, hyphenated topic slug and current date

Example: research/research-brief-remote-work-productivity-2024-01-15.md

This ensures all research briefs are systematically stored and easily referenced for future writing projects.

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. 5d ago First seen · 43 lines · 0 tokens per session scan A 316bacde0ccc

Subscribe to this mod's changes

research is a command published in the GitHub repository WomenDefiningAI/claudecode-writer (221 stars, last pushed 12mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 445 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.