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/skillmedev/skills/causal-inferencenpx skills add SkillMedev/skills --skill causal-inferencegit clone --depth 1 https://github.com/SkillMedev/skillsWrote 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/skillmedev/skills/causal-inference)<a href="https://agentmods.dev/skills/skillmedev/skills/causal-inference"><img src="https://agentmods.dev/badge/skills/skillmedev/skills/causal-inference.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 | $0.00142 | $0.01968 |
| Opus 5 | $0.00071 | $0.00984 |
| Sonnet 5 | $0.00028 | $0.00394 |
| Haiku 4.5 | $0.00014 | $0.00197 |
Grade A, and why
Causal Inference 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Causal Inference
A confident effect estimate built on a broken identification strategy is worse than no estimate: it triggers real decisions with fake evidence. This skill forces the choice of design before any regression is run, states the assumptions each design buys, and requires falsification tests before an effect is reported as causal.
Inputs to collect
Gather these before choosing a design. If the user cannot supply one, propose a default and label it a guess.
- Treatment: the intervention, precisely defined (who received it, when, at what intensity).
- Outcome: the measured variable and its timing relative to treatment.
- Unit of analysis: person, account, store, region - and how many units exist on each side.
- Assignment mechanism: how units ended up treated - randomized, threshold rule, policy rollout, self-selection. This single fact determines which designs are available.
- Data availability: pre-treatment periods (how many), untreated comparison units, candidate instruments, covariates.
- Decision at stake: what action the estimate will drive, and how costly a wrong sign or 2x-off magnitude would be.
Operating procedure
Step 1: Frame the estimand and draw the DAG
Define treatment, outcome, unit, and the counterfactual in one sentence ("What would treated units' outcome have been absent treatment?"). Sketch a DAG listing confounders (cause both treatment and outcome), mediators (on the causal path), and colliders (caused by both). Never condition on a collider or any post-treatment variable; controlling for a mediator absorbs the effect you are trying to measure.
Run the confounder checklist - for each candidate variable ask:
- Does it plausibly influence who gets treated?
- Does it plausibly influence the outcome independent of treatment?
- Is it measured before treatment? (If measured after, it may be a mediator or collider - exclude it.)
- If it is unmeasured and answers yes to the first two, no amount of regression control fixes the problem - you need a design from higher in the ladder below.
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 · 124 lines · 142 tokens per session scan A 4990e91ad329
Causal Inference is a skill published in the GitHub repository SkillMedev/skills (11 stars, last pushed 2mo ago), licensed MIT. It adds 142 tokens to every session and 1,968 once invoked, about $0.0007 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 Review
Runs a PRISMA-compliant systematic review from PICO question and pre-registered protocol through search strings, two-stage screening, risk-of-bias appraisal, and GRADE-rated synthesis. Use when someone asks "run a systematic review", "build my search strategy and inclusion criteria", "screen these studies against a…
pkpd-modeling
Pharmacokinetic and pharmacodynamic modelling and simulation - non-compartmental analysis, compartmental and population PK, PK/PD and exposure-response, TMDD, PBPK orientation, bioequivalence, allometric scaling and first-in-human dose, drug interaction prediction, and Bayesian therapeutic drug monitoring. Use when…
statistical-analysis
Guided statistical analysis for research data - test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting. Use whenever a user wants to compare groups, test a hypothesis, analyze experimental or survey data, check statistical assumptions, compute required…
biopython
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use…
hypothesis-generation
Formulate evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready analysis plans. Use when turning observations or preliminary findings into transparent, testable research plans without treating…
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.