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/mstack-initnpx skills add matthewdigiuseppe/MStack --skill mstack-initgit 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 | $0.00077 | $0.00711 |
| Opus 5 | $0.00039 | $0.00356 |
| Sonnet 5 | $0.00015 | $0.00142 |
| Haiku 4.5 | $0.00008 | $0.00071 |
Grade A, and why
mstack-init 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 2d 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:mstack-init
Stage: setup Voice: scaffolder
When to invoke
Starting a new paper. Every other MStack skill assumes the folder layout this skill creates; run it once per paper, in the directory where the paper folder should live.
Argument
$ARGUMENTS — a short slug for the paper (e.g. tariffs-aid), optionally followed by --quarto for a Quarto main file instead of LaTeX. If no slug is given, ask for one (lowercase, hyphens, no spaces).
Procedure
-
Refuse to nest. If the current directory (or an ancestor) already contains
.mstack/, stop — a paper folder inside a paper folder breaks every path convention. Tell the user tocdout first. -
Run the bundled script. The plugin root is available as
${CLAUDE_PLUGIN_ROOT}:bash "${CLAUDE_PLUGIN_ROOT}/bin/mstack-init" <short-name> [--quarto] -
Fallback (script missing or no bash): replicate it manually —
- Copy
${CLAUDE_PLUGIN_ROOT}/templates/paper-folderto./<short-name>(preserve hidden files). - Stamp
short_name: "<short-name>"into.mstack/config.yaml. - If
--quarto: replacepaper/main.texwith amain.qmdthat{{< include >}}s the section files as.qmd, and setformat: "quarto"in config.
- Copy
-
Verify the tree exists (
.mstack/config.yaml,paper/,data/raw/,code/,output/). -
Hand off. Tell the user to fill in
.mstack/config.yaml(title, authors, target journals,voice.writing_styleif they have a style skill installed), then start with/mstack:research-questionor/mstack:idea-shotgun.
Outputs
./<short-name>/— the full paper scaffold.- Summary block: created path, format (latex/quarto), next steps.
Anti-patterns to refuse
- Scaffolding over an existing folder. If
./<short-name>exists, stop; never merge into it. - Skipping config. A scaffold with an empty config still works, but remind the user once — several skills read
target_journalsandvoice.*.
When to call other skills
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.
- 2d ago First seen · 59 lines · 77 tokens per session scan A 253772ba4d09
mstack-init is a skill published in the GitHub repository matthewdigiuseppe/MStack (14 stars, last pushed 5d ago), licensed MIT. It adds 77 tokens to every session and 711 once invoked, about $0.0004 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
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…