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/results-auditnpx skills add matthewdigiuseppe/MStack --skill results-auditgit 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/results-audit)<a href="https://agentmods.dev/skills/matthewdigiuseppe/mstack/results-audit"><img src="https://agentmods.dev/badge/skills/matthewdigiuseppe/mstack/results-audit.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 | $0.00072 | $0.01080 |
| Opus 5 | $0.00036 | $0.00540 |
| Sonnet 5 | $0.00014 | $0.00216 |
| Haiku 4.5 | $0.00007 | $0.00108 |
Grade A, and why
results-audit 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mstack:results-audit
Stage: analyze (post-analysis, pre-writing) Voice: staff-statistician
When to invoke
After /mstack:analyze writes the primary table. Before /mstack:draft-section results. This skill is the one your future self wishes had run before the R2 reviewer found the same problem in three pages.
Procedure
-
Load.
code/01-clean.R,code/02-analyze.R,code/04-tables.R.data/codebook.mdfor variable definitions.output/tables/,output/models/,output/analyze-log.md.prereg/osf-prereg.mdif preregistered.
-
Run the audit checklist. For each item, either confirm pass or write the failure to the audit report.
Sample integrity
- N in the descriptive table matches N in the primary regression (or differs only by documented exclusions).
- N is consistent across primary + secondary tables (or differences are documented).
- No fully-dropped variable in the primary spec (e.g., a control with all NAs).
- If FE-included: effective sample for identification is reported (units with within-variation).
Specification integrity
- Primary spec matches prereg's "Primary analysis" word-for-word (variables, sample, SE).
- FE dimensions are justified (not just "everyone uses two-way FE").
- Clustering matches the dependence structure described in
/mstack:identification-review. - Standard errors are not naïve when the design has obvious dependence (panel, geographic, dyadic).
Inference integrity
- Multiple-comparison adjustment applied (or explicitly waived with justification) when ≥ 5 hypotheses are tested.
- Confidence intervals included (not just stars).
- Effect sizes reported in interpretable units (% change, SD of outcome, vs. baseline).
- No "marginally significant" or "approached significance" — give the number.
Forking-paths exposure
- Specification curve plot or table exists showing primary among reasonable alternatives.
- Outcome was preregistered or unambiguously defined upstream.
- Treatment / IV operationalization matches prereg (or deviation is logged).
- Sample restrictions match prereg.
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 · 85 lines · 72 tokens per session scan A bc2aac19f54a
results-audit is a skill published in the GitHub repository matthewdigiuseppe/MStack (14 stars, last pushed 9d ago), licensed MIT. It adds 72 tokens to every session and 1,080 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
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…