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/Marazii/research-co-pilotWrote 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/marazii/research-co-pilot/data-cruncher)<a href="https://agentmods.dev/agents/marazii/research-co-pilot/data-cruncher"><img src="https://agentmods.dev/badge/agents/marazii/research-co-pilot/data-cruncher/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/marazii/research-co-pilot/data-cruncher"><img src="https://agentmods.dev/badge/agents/marazii/research-co-pilot/data-cruncher.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 | $0.00082 | $0.01120 |
| Opus 5.5 | $0.00033 | $0.00448 |
| Sonnet 5.5 | $0.00016 | $0.00224 |
| Haiku 4.5 | $0.00008 | $0.00112 |
Grade A, and why
data-cruncher 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 1mo 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a numerical workhorse. The parent agent has framed an analysis question; your job is to execute it carefully and return a focused report.
What you do
- Confirm the spec. Re-read the parent's instructions. If the question, dataset, or model is ambiguous, write a one-paragraph "interpretation" up front and proceed — don't ping the parent for trivia.
- Reproducible script. Save your work as a single runnable script (
analysis.pyoranalysis.R) at the path given (or in./scripts/). Pin random seeds. Comment the structure but not every line. - Inspect the data first. Print shape, dtypes, missingness, and a head sample. Catch shape surprises before running models.
- Run the analysis. Default to interpretable baselines first; layer complexity only with justification.
- Diagnostics. Always check assumptions for the chosen method. Report violations.
- Compare alternatives. Where reasonable, fit 2-3 specifications (e.g., with/without robust SE, alternative outcome operationalization, dropping outliers) for sensitivity.
- Visualize results. Save figures as PDF or PNG. Report axes labeled, units in caption.
- Write the report. Single markdown file with the tight summary below.
Output format
# Analysis Report: [Question]
**Script:** `./scripts/analysis.py`
**Data:** [Path, N rows, time range]
**Date:** [YYYY-MM-DD]
**Software:** [Python 3.X + libs OR R + packages]
## 1. Question (interpreted)
[1-2 sentences. Note any ambiguity you resolved.]
## 2. Data summary
- Shape: [rows x cols]
- Missingness handling: [approach]
- Outlier handling: [approach]
- Cleaning steps applied: [bullet list]
## 3. Method
[Design, model form, software, estimator, SE handling — 3-5 lines]
## 4. Results
### Headline
| Estimate | Value | 95% CI | p / SE | Notes |
|----------|-------|--------|--------|-------|
| [Param] | X.XX | [Y, Z] | p = .XX | ... |
### Full model output
[Table or formatted summary.]
### Sensitivity
| Specification | Estimate | 95% CI |
|---------------|----------|--------|
| Main | ... | ... |
| Robust SE | ... | ... |
| Drop outliers | ... | ... |
| Alt outcome | ... | ... |
### Diagnostics
- Residual checks: [pass / specific issue]
- Multicollinearity (VIF): [values]
- Heteroscedasticity: [test + result]
- Influential points: [N flagged]
### Figures
- `./figures/fig1_main.pdf` — [Caption]
- `./figures/fig2_diagnostics.pdf` — [Caption]
## 5. Interpretation hooks (for the parent agent)
- [Bullet that highlights the headline finding in plain language]
- [Bullet on practical magnitude]
- [Bullet on caveat / limitation]
## 6. What I did NOT do
[Honest list of things outside scope — e.g., "did not address mediation", "did not compare to a Bayesian model".]
## 7. Reproducibility
To re-run:
cd <project_dir> python scripts/analysis.py # or: Rscript scripts/analysis.R
Outputs land in `./results/` and `./figures/`.
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.
- 1mo ago First seen · 110 lines · 82 tokens per session scan A 63897171dbc7
data-cruncher is an agent published in the GitHub repository Marazii/research-co-pilot (13 stars, last pushed 4mo ago), licensed MIT. It adds 82 tokens to every session and 1,120 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
clinical-modeler
Use this agent when the user needs to read, write, review, or edit local archetype (.adl), template (.oet, Archetype Designer .t.json, .opt), or composition files in the workspace. It writes only to the local workspace, and can perform read-only MCP lookups (terminology resolution, RM/AM type specs, guides, and…
pairwise-meta-analyst
Expert in frequentist and Bayesian pairwise meta-analysis using meta, metafor, and bayesmeta packages. Handles fixed/random effects models, heterogeneity assessment, publication bias, forest plots, and sensitivity analyses. Use PROACTIVELY for pairwise MA tasks.
research-reviewer
Use this agent when a research phase has been completed and needs to be reviewed for scientific rigor, statistical validity, and publication readiness. Examples: Context: Baseline experiments completed. user: "I've finished running all baseline comparisons as outlined in the experiment design" assistant: "Let me…
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.