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/scope-challengenpx skills add matthewdigiuseppe/MStack --skill scope-challengegit clone --depth 1 https://github.com/matthewdigiuseppe/MStackWhat 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 | $0.00063 | $0.00649 |
| Opus 5 | $0.00032 | $0.00324 |
| Sonnet 5 | $0.00013 | $0.00130 |
| Haiku 4.5 | $0.00006 | $0.00065 |
Grade A, and why
scope-challenge 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 3d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mstack:scope-challenge
Stage: ideate Voice: adversarial-advisor
When to invoke
The project is growing. You have three figures that are each interesting and you can't tell which is the headline. You've added a new section every week for a month. You suspect this is two papers, or a book chapter, or an unfinishable thing.
Procedure
Read .mstack/research-question.md, .mstack/lit-map.md, and any draft sections that exist. Then run the four challenges, in order. Write the results to .mstack/scope-challenge-<YYYY-MM-DD>.md.
Challenge 1: One sentence
"State the paper's contribution in one sentence with no clauses." If the user can't, the scope is wrong. Push until they can.
Challenge 2: One table
"Which single table is the paper? Which figure is the cover?" Papers in IPE / political science journals are built around 1–2 tables and 1–2 figures. If the user names four "essential" tables, two of them belong in another paper or an appendix.
Challenge 3: Cleavage test
"If you had to split this into two papers, where would the cut go?" The exercise of finding the cut often reveals that one is a paper and one is a sketch. The sketch is for later.
Challenge 4: 3-month ship
"What would you cut if you had to submit in 3 months?" The list of cuts is usually a list of things that should already be cut. Build the minimum viable paper.
Verdict
Write a short summary:
- Tight — the project survives all four challenges. Continue as is.
- Sprawl — one or more challenges fail. Recommend a specific cut: a section, a table, an analysis branch.
- Multi-paper — the cleavage test reveals two distinct contributions. Recommend splitting and which half is paper one.
The verdict is opinionated by design. Soft verdicts produce sprawling papers.
Outputs
.mstack/scope-challenge-<date>.md— challenges, answers, verdict.- Summary block: verdict + the single most important cut.
Anti-patterns to refuse
- Affirming a 60-page draft. If the user describes a project that doesn't fit a journal article, say so.
- "Both papers are great." Pick one. The other is for next year.
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.
- 3d ago First seen · 59 lines · 63 tokens per session scan A 8108794f4f4a
scope-challenge is a skill published in the GitHub repository matthewdigiuseppe/MStack (14 stars, last pushed 6d ago), licensed MIT. It adds 63 tokens to every session and 649 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…