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 matthewdigiuseppe/MStack --skill abstract-shotgungit 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/abstract-shotgun)<a href="https://agentmods.dev/skills/matthewdigiuseppe/mstack/abstract-shotgun"><img src="https://agentmods.dev/badge/skills/matthewdigiuseppe/mstack/abstract-shotgun.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 | $0.00064 | $0.00879 |
| Opus 5 | $0.00032 | $0.00439 |
| Sonnet 5 | $0.00013 | $0.00176 |
| Haiku 4.5 | $0.00006 | $0.00088 |
Grade A, and why
abstract-shotgun 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 6d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mstack:abstract-shotgun
Stage: write
Voice: writer (anchored to the skill named in .mstack/config.yaml → voice.writing_style)
When to invoke
The full draft exists. The abstract is the single hardest paragraph in the paper, and the most decision-relevant for editors deciding desk-reject or send-out. Generate variants instead of converging on the first one.
Procedure
-
Load.
paper/sections/intro.tex,paper/sections/discussion.tex,paper/sections/results.tex,.mstack/config.yaml(target journals). -
Apply the configured writing voice across all variants. Read
voice.writing_stylefrom.mstack/config.yaml; if set, invoke that skill. If unset, default to a clean, generic academic voice (short sentences, active verbs, no hedge-stuffing). -
Generate 4–6 variants, each varying along one of:
Variant What it leads with Puzzle-first Opens with an empirical or theoretical puzzle. "Why does X happen when Y predicts the opposite?" Policy-first Opens with the policy / real-world stake. "When governments do X, does it work?" Theory-first Opens with the theoretical claim. "We argue that X causes Y because Z." Finding-first Opens with the headline result. "Using a quasi-experiment in X, we find that Y." Anomaly-first Opens with what the literature predicts vs. what we find. "Standard accounts predict X; we find Y." Method-first (only for methods papers) Opens with the methodological contribution. -
Each variant is ≤ 250 words (or the journal limit if shorter). Each contains: question, design, finding, contribution. The order is what varies.
-
Tag each variant with:
- Lead-with style.
- Implicit audience (IPE, comparative, methods, public).
- Risk: the framing's main vulnerability (e.g., "puzzle-first risks looking like it doesn't engage the literature").
-
Write the variants file. Check
formatin.mstack/config.yaml. LaTeX:paper/sections/abstract.tex, variants as%comments plus one designated\begin{abstract} ... \end{abstract}block containing the recommended variant. Quarto:paper/sections/abstract.qmd, variants as<!-- ... -->comments plus the recommended text uncommented. LaTeX format:
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.
- 6d ago First seen · 74 lines · 64 tokens per session scan A f26f623aa490
abstract-shotgun is a skill published in the GitHub repository matthewdigiuseppe/MStack (14 stars, last pushed 10d ago), licensed MIT. It adds 64 tokens to every session and 879 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…