agentmods.dev

research-design-helper

research-design-helper is a skill for Claude Code from WenyuChiou/research-hub. It costs 163 tokens per session (3,401 once invoked), scanned A, original, MIT.

A guided planning conversation for designing a research study or model. TDD here means test-driven development, but this tool is about research questions, mechanisms, identification, validation, and risks.

In plain words
What is it for?
Use it to sharpen a research question, state the expected mechanism, check whether the effect can be identified, plan validation, and record risks. It produces `.research/design_brief.md`.
Why use it?
It helps expose unclear assumptions before you spend time coding a model that cannot answer the intended question or be properly tested.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the research-workspace plugin — 13 skills, 1 MCP server shipped together

not rated 67repo +1 changed 1mo ago A scan SkillSpector: pass 163 tokens original MIT

Good fit Use it to sharpen a research question, state the expected mechanism, check whether the effect can be identified, plan validation, and record risks. It produces .research/design_brief.md.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wenyuchiou/research-hub/research-design-helper
View source ↗ WenyuChiou/research-hub pypi.org
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 WenyuChiou/research-hub --skill research-design-helper
Clone the repo
git clone --depth 1 https://github.com/WenyuChiou/research-hub

Made for: Claude Code.

Or install research-workspace, the plugin that ships this one along with the rest of its 13 skills, 1 MCP server.

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-design-helper

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/wenyuchiou/research-hub/research-design-helper"><img src="https://agentmods.dev/badge/skills/wenyuchiou/research-hub/research-design-helper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 163 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,401 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 $0.00163 $0.03401
Opus 5.5 $0.00065 $0.01360
Sonnet 5.5 $0.00033 $0.00680
Haiku 4.5 $0.00016 $0.00340

Measured 1mo ago against content hash c4713011ab08, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

research-design-helper 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 1mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/brief_to_docx.js), 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/research-design-helper/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

research-design-helper

Stage 3a (sharp problem framing) and front-of-Stage 4 (model design) helper. Part of the research-hub skill pack — works alongside Zotero, Obsidian, and NotebookLM workflows but does not require any of them. Domain-agnostic Socratic guide that walks a researcher through 5 short segments and saves the result as .research/design_brief.md.

The skill does not invent your research question or model design. Like research-context-compressor, it leaves blanks rather than guess. Its value is structured prompting: forcing you to articulate what you'd otherwise leave implicit, before you spend weeks coding.

When to use

Trigger phrases:

  • "Frame this research question."
  • "Design my study before I start coding."
  • "Help me think through what model to build."
  • "Sharpen my hypothesis."
  • "Walk me through the design."
  • "Build a design brief."

Not for:

  • Writing actual model code (that's the user's work, optionally with codex-delegate for boilerplate).
  • Project context manifests (that's research-context-compressor).
  • Literature comparison (that's literature-triage-matrix).
  • Manuscript writing (that's academic-writing-skills).

Inputs

In priority order:

  1. .research/project_manifest.yml if it exists — for project context (research_question may already be partially filled).
  2. .research/topic_dossier.gaps.yml if it exists — Stage 2 handoff from gap-to-topic (plugin v0.3.12+). Inspect candidate IDs/names/verdicts to identify eligible options; after the user's actual selection, read only that gaps[] entry plus top-level open_questions[], NOT the whole corpus. go and conditional-go are eligibility assessments, not proof of selection. Use a clear prior user choice without asking again; if absent or ambiguous, ask even when only one candidate is eligible. The workflow §0 then pre-fills segment 1 (RQ) from gaps[].statement and segment 5 (risks) from open_questions[] + gaps[].feasibility. If supplied, also read that selected candidate's optional .research/topic_dossier.direction-review.json record and applicable resource records as described below; its absence does not block the legacy dialogue.
  3. .research/design_brief.md if it exists — for refresh, not first-run.
  4. .research/literature_matrix.md if it exists — for prior-art context when discussing identifiability.
  5. The user's free-text answers during the conversation.

Read the full file on GitHub · 153 lines

Files

What ships with it

5 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. 1mo ago Changed · +5 lines c4713011ab08
  2. 1mo ago Changed · +1 lines 8a8ea84c5659
  3. 2mo ago First seen · 147 lines · 163 tokens per session scan A 3a7f8e1ae443

Subscribe to this mod's changes

research-design-helper is a skill published in the GitHub repository WenyuChiou/research-hub (67 stars, last pushed yesterday), licensed MIT. It adds 163 tokens to every session and 3,401 once invoked, about $0.0007 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.

PlanningResearchacademic-researchai-agentscitation-managementclaudecliknowledge-management
Related

research-design-helper compared with skills from other repositories

research-design-helper next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
research-design-helperWenyuChiou/research-hubSkill67yesterdayMITA163Claude Code
novel-writer-cliwpsnote/wpsnote-skillsSkill18410d agoMITA157Claude Code
novel-writerwpsnote/wpsnote-skillsSkill18410d agoMITA141Claude Code
wps-notewpsnote/wpsnote-skillsSkill18410d agoMITA109Claude Code
live-transcript-summarywpsnote/wpsnote-skillsSkill18410d agoMITA147Claude Code
xiaohongshu-note-creatorwpsnote/wpsnote-skillsSkill18410d agoMITA204Claude Code
content-digestwpsnote/wpsnote-skillsSkill18410d agoMITA254Claude Code