research-architect-brainstorm

research-architect-brainstorm is a skill for Claude Code, Codex from mmTheBest/Research-Architect. It costs 44 tokens per session (563 once invoked), scanned A, original, MIT.

A research-planning skill that turns a broad topic, available sources, and project limits into several genuinely different research-question options.

In plain words
What is it for?
Use it to map the problem, compare possible research directions, filter out impractical ideas, and prepare a shortlist of research questions.
Why use it?
It helps avoid producing the same topic in slightly different wording and makes each option's evidence, contribution, and feasibility clear.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to map the problem, compare possible research directions, filter out impractical ideas, and prepare a shortlist of research questions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mmthebest/research-architect/research-architect-brainstorm
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 mmTheBest/Research-Architect --skill research-architect-brainstorm
Clone the repo
git clone --depth 1 https://github.com/mmTheBest/Research-Architect

Made for: Claude Code, Codex.

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-architect-brainstorm

README.md
[![agentmods](https://agentmods.dev/badge/skills/mmthebest/research-architect/research-architect-brainstorm/github.svg)](https://agentmods.dev/skills/mmthebest/research-architect/research-architect-brainstorm)
Your own site
<a href="https://agentmods.dev/skills/mmthebest/research-architect/research-architect-brainstorm"><img src="https://agentmods.dev/badge/skills/mmthebest/research-architect/research-architect-brainstorm/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-architect-brainstorm

Your own site · 80×15
<a href="https://agentmods.dev/skills/mmthebest/research-architect/research-architect-brainstorm"><img src="https://agentmods.dev/badge/skills/mmthebest/research-architect/research-architect-brainstorm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 563 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00044 $0.00563
Opus 5 $0.00022 $0.00282
Sonnet 5 $0.00009 $0.00113
Haiku 4.5 $0.00004 $0.00056

Measured 11d ago against content hash 18adcc9e3270, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

research-architect-brainstorm 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.

src/skills/research-architect-brainstorm/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Architect Brainstorm

Generate genuinely different research options, not topic paraphrases. A strong option changes the research logic, evidence path, contribution, or scope.

Inputs

Read when available:

paper_output/project_config.json
paper_output/source_map.md
paper_output/source_inventory.md
paper_output/terminology_ledger.md             # when present
paper_output/exemplar_logic_profile.md        # when accessible target references exist
paper_output/exemplar_adaptation_plan.md      # preliminary or approved version when available

Read ../research-architect/references/brainstorming-framework.md. Use ../research-architect/templates/idea_candidate_matrix.csv as the column contract and write paper_output/idea_candidate_matrix.md as a Markdown table.

Lenses and outputs

Generate 2–5 candidates using the reference-logic, adaptation, problem, material, inquiry, warrant, disconfirmation, and reader-value lenses. Create:

paper_output/problem_landscape.md
paper_output/idea_candidate_matrix.md
paper_output/research_question_options.md
paper_output/feasibility_filter.md

Each option states the problem/tension, research question, inherited reference function when applicable, required adaptation, independent contribution, needed and available evidence, provisional design family, claim boundary, feasibility, and first action.

Classify candidates as advance, needs_more_material, defer, or reject. A conceptually strong option may advance when it has explicit premises, warrants, counterarguments, and scope.

Standalone and degradation path

Accept a raw idea plus constraints even without intake artifacts. State the assumptions, create only the minimum candidate set, and route to intake before treating them as a full project record. Without an accessible target paper, do not invent its logic; develop independent options and let literature mapping identify useful exemplars later.

For guided depth, present the smallest useful 2–3 options and their feasibility filter. standard and deep add the full matrix and broader alternatives.

Read the full file on GitHub · 53 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 53 lines · 44 tokens per session scan A 18adcc9e3270

Subscribe to this mod's changes

research-architect-brainstorm is a skill published in the GitHub repository mmTheBest/Research-Architect (68 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 563 once invoked, about $0.0002 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.