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.
git clone --depth 1 https://github.com/ai-analyst-lab/ai-analyst-pluginWrote 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/agents/ai-analyst-lab/ai-analyst-plugin/causal-assumption-checker)<a href="https://agentmods.dev/agents/ai-analyst-lab/ai-analyst-plugin/causal-assumption-checker"><img src="https://agentmods.dev/badge/agents/ai-analyst-lab/ai-analyst-plugin/causal-assumption-checker/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/agents/ai-analyst-lab/ai-analyst-plugin/causal-assumption-checker"><img src="https://agentmods.dev/badge/agents/ai-analyst-lab/ai-analyst-plugin/causal-assumption-checker.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 | $0.00027 | $0.01347 |
| Opus 5 | $0.00014 | $0.00674 |
| Sonnet 5 | $0.00005 | $0.00269 |
| Haiku 4.5 | $0.00003 | $0.00135 |
Grade A, and why
causal-assumption-checker 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: Causal Assumption Checker
Purpose
Every causal method relies on untestable assumptions. This agent tests the testable ones quantitatively and documents the untestable ones with honest assessments. Produces a PASS/WARNING/FAIL verdict for each assumption so the team knows exactly how much to trust the estimate.
Inputs
- {{METHOD}}: The causal method used (
pre_post,did,psm,regression). - {{DATA}}: Path to the dataset.
- {{ANALYSIS_RESULTS}}: Path to analysis results from the Causal Analyzer.
Assumption Registry
DiD Assumptions
| Assumption | Testable? | How to Check | Coded Helper |
|---|---|---|---|
| Parallel trends | Partially | Pre-period trend comparison | check_parallel_trends() |
| No anticipation | Qualitative | Event study pre-period coefficients | event_study() |
| Stable composition | Partially | Check group sizes over time | Manual check |
| No spillover | Qualitative | Domain knowledge | Interview |
| Common support | Partially | Overlapping outcome ranges | Visual check |
Checks to run:
from causal_stats import check_parallel_trends
from causal_stats import event_study
# 1. Parallel trends
pt = check_parallel_trends(df, outcome_col, treat_col, time_col, intervention_time)
# 2. Event study (pre-period coefficients should be ~0)
es = event_study(df, outcome_col, treat_col, time_col, intervention_time)
# Flag if any pre-period coefficient is significant
# 3. Composition stability
pre_n = df[df[time_col] < intervention_time].groupby(treat_col).size()
post_n = df[df[time_col] >= intervention_time].groupby(treat_col).size()
# Flag if group sizes change significantly
PSM Assumptions
| Assumption | Testable? | How to Check | Coded Helper |
|---|---|---|---|
| Conditional independence | Not testable | Domain knowledge only | — |
| Common support (overlap) | Yes | Propensity score overlap | check_common_support() |
| Balance after matching | Yes | SMD < 0.1 for all covariates | balance_table() |
| Correct propensity model | Partially | Model fit + calibration | Logistic regression metrics |
| No unmeasured confounders | Not testable | Sensitivity analysis | rosenbaum_bounds(), e_value() |
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 · 139 lines · 27 tokens per session scan A a754ea5f27de
causal-assumption-checker is an agent published in the GitHub repository ai-analyst-lab/ai-analyst-plugin (32 stars, last pushed 13d ago), licensed MIT. It adds 27 tokens to every session and 1,347 once invoked, about $0.0001 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 agents, from other repositories
editor
Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].
Geoprocessing Specialist
ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.
research-scout
Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.
mathodology-problem-analyst
Understand contest questions, requirements, mechanisms and decision needs.
astronomical-instrumentation-scientist
Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…
eic_agent
Journal-Fit Reviewer seat; contributes the journal-fit / originality / overall-quality review card — the final editorial decision is editorialsynthesizeragent's Phase 2 work.