identification-review

identification-review is a skill for Claude Code, Codex from matthewdigiuseppe/MStack. It costs 74 tokens per session (966 once invoked), scanned A, original, MIT.

A structured review of how a research study can support its main causal claim. It states the key assumption, checks common ways it could fail, and gives a pass or fail verdict.

In plain words
What is it for?
Use it to review the planned or actual analysis, identify plausible threats, and require tests that could disprove the explanation. It is intended for research papers using data to make causal claims.
Why use it?
It exposes weaknesses before the research design is fixed or a paper is submitted. This helps address reviewer concerns about selection, confounding, reverse causality, measurement, and related problems.

Skill for Claude CodeCodex

Part of the mstack plugin — 38 skills, 1 hook shipped together

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

Made for: Claude Code, Codex.

Or install mstack, the plugin that ships this one along with the rest of its 38 skills, 1 hook.

Wrote 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.

agentmods badge for identification-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/matthewdigiuseppe/mstack/identification-review.svg)](https://agentmods.dev/skills/matthewdigiuseppe/mstack/identification-review)
Your own site
<a href="https://agentmods.dev/skills/matthewdigiuseppe/mstack/identification-review"><img src="https://agentmods.dev/badge/skills/matthewdigiuseppe/mstack/identification-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 966 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 $0.00074 $0.00966
Opus 5 $0.00037 $0.00483
Sonnet 5 $0.00015 $0.00193
Haiku 4.5 $0.00007 $0.00097

Measured 5d ago against content hash 392d4c1803f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

identification-review 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 5d 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/identification-review/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:identification-review

Stage: map (before design lock-in) — re-run before submission Voice: methodologist

When to invoke

  • After /mstack:theory-build and before /mstack:design-research: lock down identification before committing to a design.
  • Before submission: re-run on the actual specification to catch what you missed.

Procedure

  1. Load context.

    • .mstack/research-question.md for the claim.
    • .mstack/lit-map.md for what the literature already disputes.
    • paper/sections/methods.tex (if it exists) for the current spec.
    • code/02-analyze.R (if it exists) for what is actually run.
  2. State the identifying assumption in one sentence. If the user can't, the review fails before it starts; surface that as the top finding.

  3. Run the prosecution checklist. For each item, name a concrete violation a reviewer could plausibly raise:

    • Selection. Who is in the sample? Who isn't? Is selection on the dependent variable?
    • Confounding. What is the most plausible omitted variable? Why does the design rule it out?
    • Reverse causality. Could Y cause X? What evidence rules it out?
    • Measurement. Is X measured pre-treatment? Is Y measured cleanly? What is the reliability?
    • SUTVA / spillovers. Are units independent? If not, what is the dependence structure?
    • Effective sample. What units actually contribute to identification (e.g., within-variation under FE)? Are they representative?
    • Standard errors. What is the level of clustering? What is the dependence structure that justifies it?
    • Multiple comparisons. How many tests? What is the family-wise error rate?
    • Specification curve. How many reasonable specifications exist? Have they been run? Where does the headline sit?
    • External validity. What is the population of generalization? Is the headline phrased to match?
  4. Falsification tests. Name at least two:

    • Placebo. A sample / time / outcome where the effect should be zero. Is it?
    • Pre-trend / pre-treatment outcome. Does the relationship exist before treatment?
    • Negative control. A predictor that should not predict the outcome — does it?

Read the full file on GitHub · 74 lines

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. 5d ago First seen · 74 lines · 74 tokens per session scan A 392d4c1803f5

Subscribe to this mod's changes

identification-review is a skill published in the GitHub repository matthewdigiuseppe/MStack (14 stars, last pushed 9d ago), licensed MIT. It adds 74 tokens to every session and 966 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.

Related

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…

anthropics/knowledge-work-plugins · 123 tokens

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…

K-Dense-AI/scientific-agent-skills · 83 tokens

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.

K-Dense-AI/scientific-agent-skills · 42 tokens

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.

K-Dense-AI/scientific-agent-skills · 68 tokens

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.

davila7/claude-code-templates · 43 tokens

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…

maziyarpanahi/openmed · 205 tokens