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 agentmods add skills/matthewdigiuseppe/mstack/research-questionnpx skills add matthewdigiuseppe/MStack --skill research-questiongit clone --depth 1 https://github.com/matthewdigiuseppe/MStackWrote 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/matthewdigiuseppe/mstack/research-question)<a href="https://agentmods.dev/skills/matthewdigiuseppe/mstack/research-question"><img src="https://agentmods.dev/badge/skills/matthewdigiuseppe/mstack/research-question.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 | $0.00068 | $0.00908 |
| Opus 5 | $0.00034 | $0.00454 |
| Sonnet 5 | $0.00014 | $0.00182 |
| Haiku 4.5 | $0.00007 | $0.00091 |
Grade A, and why
research-question 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 4d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mstack:research-question
Stage: ideate Voice: advisor
When to invoke
You have a candidate research idea and you're about to invest weeks. Before you do, this skill forces the questions that, if asked at month 6, become reasons to abandon the project.
This is an interrogation, not a brainstorm. Do not leap to encouragement.
Procedure
Ask each question and wait for the user's answer before moving on — one at a time in a live conversation. Offer upfront that the user may instead answer all six in a single message, and in an asynchronous context (web/mobile, or a user who is clearly batching), present all six together rather than forcing six round-trips. After all six answers, write them to .mstack/research-question.md with a verdict.
The six questions
-
Contribution in one sentence. "If this paper succeeds, what one sentence does it add to the literature that wasn't there before?" — Reject vague answers ("contributes to our understanding of X"). Push for a specific, falsifiable claim.
-
Audience and venue. "Who reads this paper, and what journal/community is it pitched to?" — If the answer is "it could go anywhere," that is a red flag. Papers that fit everywhere fit nowhere.
-
Identification strategy. "How do you separate your effect from the obvious confounders?" — If the design is observational and the answer is "control variables," press hard: name a placebo test, an instrument, a discontinuity, or a quasi-experiment. If the answer is "I'll figure it out," recommend deferring the project until the design is concrete.
-
Falsifiability. "What pattern in the data would make you abandon the hypothesis?" — If they can't name one, the hypothesis is unfalsifiable in their head and will be unfalsifiable on the page.
-
Feasibility. "What is the longest pole — data access, computation, fieldwork, IRB? How long? What's plan B if it fails?" — Ask for a concrete timeline.
-
Scoop risk. "Has someone else done this in the last 3 years? Is someone visibly working on it now (working papers, conference programs, NSF abstracts)?" — Push for evidence, not "I haven't seen it."
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.
- 4d ago First seen · 67 lines · 68 tokens per session scan A 549b91b8ba54
research-question is a skill published in the GitHub repository matthewdigiuseppe/MStack (14 stars, last pushed 7d ago), licensed MIT. It adds 68 tokens to every session and 908 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…