What is research-brief-builder?

A guided process for turning a broad research idea into a precise research brief. It asks challenging questions about the decision, scope, evidence, hypotheses, exclusions, and desired output.

Use it to define research questions for a deep-research agent, set time or geographic boundaries, record known context, state hypotheses, specify the final format, and acknowledge expected cost.

It prevents research from becoming vague, repetitive, or too broad to answer usefully. It makes clear what result would change the decision and what findings would not be useful.

research-brief-builder — Skill for Claude Code by Galbaz1

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.

Any agent

npx skills add Galbaz1/video-research-mcp --skill research-brief-builder

Clone the repo

git clone --depth 1 https://github.com/Galbaz1/video-research-mcp

Made for: Claude Code.

Or install gr, the plugin that ships this one along with the rest of its 12 skills, 17 commands, 7 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/galbaz1/video-research-mcp/research-brief-builder/github.svg)](https://agentmods.dev/skills/galbaz1/video-research-mcp/research-brief-builder)

Your own site

<a href="https://agentmods.dev/skills/galbaz1/video-research-mcp/research-brief-builder"><img src="https://agentmods.dev/badge/skills/galbaz1/video-research-mcp/research-brief-builder/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/galbaz1/video-research-mcp/research-brief-builder"><img src="https://agentmods.dev/badge/skills/galbaz1/video-research-mcp/research-brief-builder.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 471 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	$0.00471
Opus 5	$0.00005	$0.00235
Sonnet 5	$0.00002	$0.00094
Haiku 4.5	$0.00001	$0.00047

Measured 11d ago against content hash 7b68697f6533, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

research-brief-builder 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 11d 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.

skills/research-brief-builder/SKILL.md · 61 lines

What it actually says

Research Brief Builder

Last updated: 2026-03-05 14:58 CET

Knowledge pack for constructing high-quality research briefs for the Gemini Deep Research Agent.

Brief Quality Checklist

Question is falsifiable (can be proven wrong)
Scope has explicit boundaries (time, domain, geography)
At least 1 hypothesis to test
Known context documented (avoid rediscovery)
Output format specified (audience, structure)
Exclusions listed
Cost acknowledged ($2-5 per run)

Anti-patterns

"Research everything about X" -- Too broad, will get generic results
No hypotheses -- Research has no direction, agent wanders
No exclusions -- $5 spent rediscovering what user already knows
No format spec -- Get a wall of text instead of actionable output
Vague scope -- "recent" means different things to different people

Challenge Templates

"Your question assumes X -- is that actually true?"
"This could mean A or B -- which one matters for your decision?"
"You said you want 'comprehensive' but also 'quick' -- pick one."
"What would make this research WORTHLESS to you?"
"What's the actual decision this research needs to inform?"
"What finding would CHANGE your mind about this?"

Brief Template

RESEARCH BRIEF
==============
Question: <precise, falsifiable research question>
Scope: <time period, domains, geography, depth>
Hypotheses to test: <H1, H2, ...>
Known context: <what we already know>
Output format: <structure, audience, tone>
Exclusions: <what to skip>
Cost: $2-5 | Time: 10-20 min
==============

Evidence Tier Reference

When reviewing results, label claims:

CONFIRMED -- Multiple independent sources agree
STRONG INDICATOR -- Credible evidence with minor gaps
INFERENCE -- Reasonable conclusion from indirect evidence
SPECULATION -- Plausible but unverified
UNKNOWN -- Insufficient evidence

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.

11d ago First seen · 61 lines · 10 tokens per session scan A 7b68697f6533

Subscribe to this mod's changes

research-brief-builder is a skill published in the GitHub repository Galbaz1/video-research-mcp (23 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 471 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 2026-08-30.

Claude Code Planning Research ai-tools gemini mcp mcp-server

b123d-modeling

Use this skill when asked to model, build, or modify a 3D part or assembly with build123d — from a text description, a technical drawing (image or PDF), dimensions in a spec, or an existing STEP/STL file.

pzfreo/build123d-mcp · 0 tokens

b123d-edit

Use this skill when the task is to change an existing build123d model or script: "make this bracket 5 mm taller", "move the holes inward", "add a counterbore", "remove this rib", "make it fit this mating part", or "repair the code so the intended edit remains parametric".