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.
npx skills add martinstofko219/agentic-design-toolkit --skill research-plangit clone --depth 1 https://github.com/martinstofko219/agentic-design-toolkitWrote 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.
[](https://agentmods.dev/skills/martinstofko219/agentic-design-toolkit/research-plan)<a href="https://agentmods.dev/skills/martinstofko219/agentic-design-toolkit/research-plan"><img src="https://agentmods.dev/badge/skills/martinstofko219/agentic-design-toolkit/research-plan.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00172 | $0.01902 |
| Opus 5 | $0.00086 | $0.00951 |
| Sonnet 5 | $0.00034 | $0.00380 |
| Haiku 4.5 | $0.00017 | $0.00190 |
Grade A, and why
research-plan 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
research-plan
A research session is an hour of a stranger's time and can't be re-run. The plan is what makes that hour count: sharp research questions, scenarios that surface behavior instead of polite opinions, and a session structure a moderator can run from directly. Draft it with the user, not for them — recommend themes and scenarios confidently, but treat every draft as a proposal: they know the product and its users; the skill knows how to turn that into a study.
Start from the decision, not the method
Establish what prompted the study and what decision its findings inform. A study run to "learn about users" produces a report nobody acts on; one run to decide "ship the new onboarding flow or rework it" produces answers.
From that decision, write 3–5 research questions with the user — specific, answerable within the study, and non-leading ("how do users currently decide what to reorder," not "do users love the reorder feature"). They are the plan's spine: every theme and scenario must trace back to one. The traceability pays off downstream — research-synthesis inherits the themes as candidates when transcripts come back.
Choose the method
Match the method to the questions, not the other way around:
- Discovery interviews — questions about the problem space: current workflows, motivations, unmet needs. No prototype required.
- Usability test — questions about whether a specific design works, and a prototype exists to put in front of people.
- Something else — if the questions point at surveys, card sorting, or A/B testing, read
secondary-methods.mdin this skill's folder before planning; it covers when each fits and how the plan's sections change. Don't load it otherwise.
A hybrid — interview-style context questions before usability tasks — is common; plan it as a usability test with a longer context phase.
Analyze the prototype (usability studies)
If the user wants to test a design but hasn't pointed at a prototype, ask whether one exists — scenarios have nothing to anchor to otherwise. If none exists, suggest wireframe-design or prototype-design first, or pivot to discovery interviews if the questions allow.
What ships with it
2 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.
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.
- 7d ago First seen · 126 lines · 172 tokens per session scan A d1112a22cb13
research-plan is a skill published in the GitHub repository martinstofko219/agentic-design-toolkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 172 tokens to every session and 1,902 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…