A research workflow that searches the web, reads relevant sources, summarizes the findings, and saves them as a structured note in a knowledge workspace. For interactive pages, it can use a browser that supports clicks and other actions.

Use it to research a topic, create a summary with sources and action items, and link the result to related notes.

It keeps research, source links, key points, and follow-up tasks together instead of leaving them scattered across browser tabs and scratch notes.

How Railly/agent-brain configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Railly/agent-brain. 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/Railly/agent-brain/main/.agents/skills/research/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Railly/agent-brain

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/railly/agent-brain/research/github.svg)](https://agentmods.dev/skills/railly/agent-brain/research)

Your own site

<a href="https://agentmods.dev/skills/railly/agent-brain/research"><img src="https://agentmods.dev/badge/skills/railly/agent-brain/research/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/railly/agent-brain/research"><img src="https://agentmods.dev/badge/skills/railly/agent-brain/research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 271 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.

Model	Per session	Once invoked
Fable 5.1	$0.00010	$0.00271
Opus 5.5	$0.00004	$0.00108
Sonnet 5.5	$0.00002	$0.00054
Haiku 4.5	$0.00001	$0.00027

Measured 2mo ago against content hash 8cc5ef0999d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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.

.agents/skills/research/SKILL.md · 56 lines

What it actually says

Topic: $ARGUMENTS

Research Methods (choose based on need)

Static Content (default)

Use the runtime's web search capability to find relevant information
Use the runtime's page fetch capability to read key sources

Dynamic/Interactive Content (use agent-browser)

When pages require JavaScript, login, or interaction:

agent-browser open "https://example.com"
agent-browser snapshot -i
agent-browser click @e3  # if needed
agent-browser snapshot -i  # get updated content
agent-browser close

Process

Search and gather sources with the runtime's web tools or agent-browser
Synthesize findings into structured notes
Save to 05_Areas/research/$ARGUMENTS.md with:
- Summary
- Key points
- Sources
- Action items if applicable

Format:

# $ARGUMENTS

## Summary
Brief overview of the topic.

## Key Points
- Point 1
- Point 2

## Sources
- [Title](url)

## Action Items
- [ ] Next step

## Related
- [[Related Topic]]

Link to relevant existing notes if applicable.

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.

2mo ago First seen · 56 lines · 10 tokens per session scan A 8cc5ef0999d3

Subscribe to this mod's changes

research is a skill published in the GitHub repository Railly/agent-brain (22 stars, last pushed 3mo ago), licensed MIT. It adds 10 tokens to every session and 271 once invoked, about $0.0000 per session on Opus 5.5. 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.

Research

research next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
researchRailly/agent-brain	Skill	22	3mo ago	MIT	A	10	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	today	MIT	A	103	Claude Code

agent-brain: Skill for Claude Code