robustness

A research-analysis tool that reruns a main result using different samples, measurements, model settings, and statistical choices, then labels the result stable, sensitive, or fragile.

In plain words
What is it for?
Use it after the main results table is ready to run robustness checks and create a comparison table and specification curve.
Why use it?
It shows whether a headline finding holds under reasonable alternatives instead of depending on one set of analysis choices.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/matthewdigiuseppe/mstack/robustness
Any agent
npx skills add matthewdigiuseppe/MStack --skill robustness
Clone the repo
git clone --depth 1 https://github.com/matthewdigiuseppe/MStack

Made for: Claude Code, Codex.

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,007 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00065 $0.01007
Opus 5 $0.00032 $0.00504
Sonnet 5 $0.00013 $0.00201
Haiku 4.5 $0.00006 $0.00101

Measured 2d ago against content hash 1074870bf4e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

robustness 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.

skills/robustness/SKILL.md · 74 lines

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:robustness

Stage: analyze Voice: skeptical-analyst (anchored to r-coding-skills)

When to invoke

After /mstack:analyze produces a primary table and /mstack:results-audit passes. Robustness is not "more tables for the appendix" — it's the test of whether the headline is fragile.

Procedure

  1. Load. code/02-analyze.R, output/models/, prereg/osf-prereg.md (which lists pre-committed robustness checks), .mstack/identification-review-*.md.

  2. Enumerate the design choices in the primary spec. For each choice, list at least one defensible alternative:

    Choice in primary Alternative(s)
    Sample restriction Drop the most restrictive cut; add a stricter cut
    Outcome operationalization Alternative scaling, alternative scoring, dichotomized vs. continuous
    Treatment operationalization Continuous vs. binary, alternative threshold, lagged treatment
    Fixed-effects structure Drop a dimension, add a dimension, swap to interactive FE
    Standard-error clustering Alternative cluster level (more / less aggregated)
    Functional form Linear vs. log, polynomial, splines
    Sample composition With / without outliers, with / without specific subgroups
    Time window Earlier / later cutoffs
  3. Write code/05-robustness.R that:

    • Loads data/clean/analytic.rds (do not re-clean).
    • Defines the primary spec as a function or formula object.
    • Iterates over the alternatives, fitting each model.
    • Stores results in a long data frame: (spec_name, dimension, value, coef, se, ci_low, ci_high, n).
    • Saves the result as output/models/robustness.rds.
  4. Write code/06-robustness-table-and-curve.R. Copy the bundled helper — ${CLAUDE_PLUGIN_ROOT}/skills/robustness/assets/spec-curve.Rcode/spec-curve.R — and source() it for plot_spec_curve() and summarize_robustness(). The script:

    • Renders a robustness table at output/tables/table-robustness.tex showing each alternative against the primary.
    • Renders a specification curve at output/figures/specification-curve.pdf plotting all coefficients with CIs ranked by magnitude, with the primary spec marked.

Read the full file on GitHub · 74 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 2d ago First seen · 74 lines · 65 tokens per session scan A 1074870bf4e6

Subscribe to this mod's changes

robustness is a skill published in the GitHub repository matthewdigiuseppe/MStack (14 stars, last pushed 5d ago), licensed MIT. It adds 65 tokens to every session and 1,007 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens