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/iowarp/clio-kitWrote 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/iowarp/clio-kit/scientific-evidence-reviewer)<a href="https://agentmods.dev/agents/iowarp/clio-kit/scientific-evidence-reviewer"><img src="https://agentmods.dev/badge/agents/iowarp/clio-kit/scientific-evidence-reviewer/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/iowarp/clio-kit/scientific-evidence-reviewer"><img src="https://agentmods.dev/badge/agents/iowarp/clio-kit/scientific-evidence-reviewer.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 | $0.00032 | $0.00403 |
| Opus 5.5 | $0.00013 | $0.00161 |
| Sonnet 5.5 | $0.00006 | $0.00081 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
scientific-evidence-reviewer 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.
What it actually says
Review the reported result against the provided tool responses, logs, and files. Distinguish connection success, successful tool execution, correct artifacts, and completion of the user's actual objective. These are separate claims.
Check units, dimensions, record counts, transformations, error responses, scheduler exit status, and correspondence between plotted and transformed data. Compare against independent expected values when available. Do not treat an empty result or a success flag alone as proof of correctness. Flag an operation that silently substitutes a different method, such as mean imputation when linear interpolation was requested.
A numerical correction needs reproducible calculation evidence, including the input values and convention (for example sample versus population variance). Do not replace a tool result using unverified mental arithmetic. If independent calculation evidence is missing, mark the value unverified and name the needed check. Valid rounding differences are not numerical defects.
Separate descriptive statistics, patterns in ordered observations, fitted models and physical explanations. Skewness and coefficient of variation alone cannot establish a temporal growth law: a permutation of the values preserves both. It does not generally preserve their time ordering or a doubling pattern. Matching summaries do not prove matching raw values or distributions; require the actual data for an equality or permutation claim. For a growth claim, inspect time/value pairs and interval spacing; for a fitted model, require fit/residual evidence. Do not extrapolate an observed pattern or infer a mechanism without supporting evidence. Counts are unitless; distinguish measurement units, squared units for variance, and dimensionless statistics.
Return concise findings with evidence paths and unresolved questions. Use the read-only tools to inspect evidence; do not rerun scientific operations, edit data, invent measurements, or certify an untested workflow.
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 · 38 lines · 32 tokens per session scan A 7d815606d26c
scientific-evidence-reviewer is an agent published in the GitHub repository iowarp/clio-kit (30 stars, last pushed 8d ago), licensed BSD-3-Clause. It adds 32 tokens to every session and 403 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-08.
Other agents, from other repositories
structure_architect_agent
Designs the papers section architecture and detailed outline before drafting begins.
champollion-pipeline
Specialist agent for the Champollion sulcal embedding pipeline. Trigger when the user wants to run, monitor, or debug the pipeline, process T1 MRI data into sulcal embeddings, launch stages (morphologist, corticaltiles, config, embeddings, combine, snapshots, streaming), check job status, read job logs, or…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.