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 thuong-nc/perlytics-skill --skill causal-inference-checkgit clone --depth 1 https://github.com/thuong-nc/perlytics-skillWrote 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/thuong-nc/perlytics-skill/causal-inference-check)<a href="https://agentmods.dev/skills/thuong-nc/perlytics-skill/causal-inference-check"><img src="https://agentmods.dev/badge/skills/thuong-nc/perlytics-skill/causal-inference-check/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/thuong-nc/perlytics-skill/causal-inference-check"><img src="https://agentmods.dev/badge/skills/thuong-nc/perlytics-skill/causal-inference-check.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00035 | $0.01562 |
| Opus 5 | $0.00017 | $0.00781 |
| Sonnet 5 | $0.00007 | $0.00312 |
| Haiku 4.5 | $0.00003 | $0.00156 |
Grade A, and why
causal-inference-check 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 9d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Causal Inference Check
Purpose
Assess whether a causal claim is justified by the available evidence, identify what alternative explanations exist, and recommend what method or evidence is needed to support the claim rigorously.
When to use
Use this skill when:
- a team states or implies that X caused Y based on observational data ("we added feature X and retention went up")
- a
root-cause-analysisorhypothesis-treeinvestigation arrives at a confident-sounding conclusion that lacks experimental backing - a decision is being justified with a correlation rather than controlled evidence
- you need to evaluate whether non-experimental evidence is strong enough to act on
When not to use
Do not use this skill when:
- the causal claim is already supported by a well-designed randomized experiment (use
experiment-readoutinstead) - the task is descriptive - "what happened" rather than "what caused it"
Required thinking discipline
- Correlation is evidence, not proof. A correlation between X and Y is consistent with X causing Y, but also consistent with Y causing X, a common cause driving both, or coincidence.
- Always name the alternative explanation before accepting a causal claim. The job is not to disprove the claim, but to surface what else could explain the pattern.
- The counterfactual question is: what would have happened to Y if X had not occurred? If you cannot describe the counterfactual, you cannot assess the causal claim.
- Match the method to the question rigor required. Not every question needs an RCT - but every causal claim needs a credible counterfactual.
- Evidence constraint: Every conclusion must cite specific data — a number, a rate, a segment, or a timeframe. Do not speculate without evidential basis. If data is insufficient, state what is missing rather than asserting an unsupported inference.
Confounders to check by default
Before accepting any causal claim, ask whether these alternatives were ruled out:
- Selection bias: did the people who received X differ systematically from those who did not, in ways that also affect Y?
- Simultaneous change: did something else change at the same time as X that could explain the change in Y?
- Reverse causality: could Y be causing X rather than the other way around?
- Survivorship bias: is the comparison population systematically different because some entities dropped out?
- Regression to the mean: was X applied to a group precisely because Y was unusually bad, making a natural rebound likely regardless of X?
What ships with it
2 files 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.
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.
- 9d ago First seen · 118 lines · 35 tokens per session scan A 93dbc018f958
causal-inference-check is a skill published in the GitHub repository thuong-nc/perlytics-skill (5 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,562 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
sn-search-academic
An academic research tool for finding papers and encyclopedia entries, reading papers in full or by section, and tracing references and citations. It supports structured literature research.
scientific-slides
Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and…
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
paper-2-web
Use when converting academic papers into dissemination assets such as Paper2Web websites, Paper2Video video abstracts, or Paper2Poster conference posters from LaTeX or PDF sources.
get-available-resources
This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to…
plotly
Interactive scientific and statistical data visualization library for Python. Use when creating charts, plots, or visualizations including scatter plots, line charts, bar charts, heatmaps, 3D plots, geographic maps, statistical distributions, financial charts, and dashboards. Supports both quick visualizations (Plotly…