agentmods.dev

scientific-brainstorming

scientific-brainstorming is a skill for Claude Code, Codex from CHENyiru3/AI-Skills-Collections. It costs 46 tokens per session (960 once invoked), scanned A, original, MIT.

A structured helper for generating and comparing possible scientific research directions. It separates ideas and predictions from evidence, decisions, and unresolved disagreement.

In plain words
What is it for?
Use it for research ideation or prioritization, including challenging candidate directions and identifying checks that could distinguish them. It does not validate hypotheses or authorize experiments.
Why use it?
Brainstormed ideas are not validated findings, and treating them as such can lead to unsupported conclusions or premature experiments. This keeps assumptions and evidence limits visible.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the core plugin — 5 skills shipped together

not rated 2repo 3d ago A scan 46 tokens original MIT

Good fit Use it for research ideation or prioritization, including challenging candidate directions and identifying checks that could distinguish them. It does not validate hypotheses or authorize experiments.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chenyiru3/ai-skills-collections/scientific-brainstorming
View source ↗ CHENyiru3/AI-Skills-Collections
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 CHENyiru3/AI-Skills-Collections --skill scientific-brainstorming
Clone the repo
git clone --depth 1 https://github.com/CHENyiru3/AI-Skills-Collections

Made for: Claude Code, Codex.

Or install core, the plugin that ships this one along with the rest of its 5 skills.

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 scientific-brainstorming

README.md
[![agentmods](https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/scientific-brainstorming/github.svg)](https://agentmods.dev/skills/chenyiru3/ai-skills-collections/scientific-brainstorming)
Your own site
<a href="https://agentmods.dev/skills/chenyiru3/ai-skills-collections/scientific-brainstorming"><img src="https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/scientific-brainstorming/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 scientific-brainstorming

Your own site · 80×15
<a href="https://agentmods.dev/skills/chenyiru3/ai-skills-collections/scientific-brainstorming"><img src="https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/scientific-brainstorming.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 960 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.00960
Opus 5.5 $0.00018 $0.00384
Sonnet 5.5 $0.00009 $0.00192
Haiku 4.5 $0.00005 $0.00096

Measured yesterday against content hash 5922ed5b2a99, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

scientific-brainstorming 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 yesterday.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/_common.py, scripts/evaluate_matrix.py, scripts/session_scaffold.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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-market/core/research/scientific-brainstorming/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scientific Brainstorming

Produce candidate directions, their assumptions, and discriminating next checks. Brainstorming supplies proposals, not validation or approval to execute them. Keep ideas, assumptions, predictions, located evidence, and actual decisions distinct. Preserve human ideas, negative evidence, and unresolved disagreement.

Scope and generate

Infer the focal question, constraints, and decision from the request and relevant project records. Ask only for missing information that changes the task. An ordinary chat brainstorm can be completed in the response without a workshop, JSON register, scoring system, or new project-management documents.

  • Direct AI-assisted session: generate candidates and then critique them. Disclose actual information exposure and missing expertise. Multiple model roles or samples are perspectives, not independent experts or replications.
  • Real human session: private initial generation, leader-last sharing, and independent ratings can reduce particular participation/anchoring problems. Do not invent participants, dissent, reviews, or approvals. This skill does not itself authorize contacting people or spawning agents.

Vary mechanisms and assumptions, not just wording. Include a plausible null, measurement explanation, or simpler alternative when relevant. Record what each retained idea predicts and what would make it wrong or uninformative. Analogies need explicit mappings and mismatches; they are proposals rather than evidence.

Challenge and compare

State relevant criteria and tradeoffs. Qualitative comparison is usually enough. For requested numeric scoring, expose scale anchors, directions, weights, raw ratings, uncertainty, and sensitivity. Scores support a decision; they do not establish truth, erase disagreement, or automatically select a winner.

Challenge shortlisted ideas with competing explanations, confounding, measurement failure, feasibility, and concrete harms. Identify an actual independent reviewer when one participated; otherwise label the self-critique.

Read the full file on GitHub · 92 lines

Files

What ships with it

12 files 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. yesterday First seen · 92 lines · 46 tokens per session scan A 5922ed5b2a99

Subscribe to this mod's changes

scientific-brainstorming is a skill published in the GitHub repository CHENyiru3/AI-Skills-Collections (2 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 960 once invoked, about $0.0002 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 2026-11-13.

ResearchScientific
Related

scientific-brainstorming compared with skills from other repositories

scientific-brainstorming next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
scientific-brainstormingCHENyiru3/AI-Skills-CollectionsSkill23d agoMITA46Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-pluginsSkill36kyesterdayApache-2.0A123Claude Code
matlabK-Dense-AI/scientific-agent-skillsSkill57k5d agoMITA44Claude Code
exploratory-data-analysisK-Dense-AI/scientific-agent-skillsSkill57k5d agoMITA83Claude Code
phylogeneticsK-Dense-AI/scientific-agent-skillsSkill57k5d agoMITA71Claude Code, Codex
research-engineerdavila7/claude-code-templatesSkill34ktodayMITA43Claude Code, Codex
mapping-to-snomedmaziyarpanahi/openmedSkill5.8kyesterdayApache-2.0A205Claude Code