rrdoctor-verify

rrdoctor-verify is a cursor rule for Cursor from Tom409114/research-repo-doctor. It costs 0 tokens per session (295 once invoked), scanned A, original, MIT.

A set of instructions for using rrdoctor, a fixed checker for research repositories, to assess whether work can be reproduced. Reproducibility means another person can run the project and obtain the expected results.

In plain words
What is it for?
Use it when cleaning up research code, notebooks, dependencies, data records, citations, or public releases.
Why use it?
It provides a repeatable review process for finding missing dependencies, local-only paths, stale notebook results, and incomplete records of data or citations.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Use it when cleaning up research code, notebooks, dependencies, data records, citations, or public releases.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/tom409114/research-repo-doctor/rrdoctor-verify
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Tom409114/research-repo-doctor

Made for: Cursor.

Wrote 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.

agentmods badge for rrdoctor-verify

README.md
[![agentmods](https://agentmods.dev/badge/rules/tom409114/research-repo-doctor/rrdoctor-verify/github.svg)](https://agentmods.dev/rules/tom409114/research-repo-doctor/rrdoctor-verify)
Your own site
<a href="https://agentmods.dev/rules/tom409114/research-repo-doctor/rrdoctor-verify"><img src="https://agentmods.dev/badge/rules/tom409114/research-repo-doctor/rrdoctor-verify/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.

agentmods 80×15 button for rrdoctor-verify

Your own site · 80×15
<a href="https://agentmods.dev/rules/tom409114/research-repo-doctor/rrdoctor-verify"><img src="https://agentmods.dev/badge/rules/tom409114/research-repo-doctor/rrdoctor-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 295 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00295
Opus 5 $0.00000 $0.00148
Sonnet 5 $0.00000 $0.00059
Haiku 4.5 $0.00000 $0.00030

Measured 11d ago against content hash cfda7ef2a32b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

rrdoctor-verify 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 11d 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.

integrations/cursor/rrdoctor-verify.mdc · 41 lines

What it actually says

rrdoctor Verify Loop

Use this rule when editing a research repository for reproducibility, Artifact Evaluation, public release, notebook cleanup, dependency documentation, data provenance, citation metadata, or coding-agent remediation.

rrdoctor is the grader. Cursor is the editor. Do not weaken rrdoctor checks to make a task pass.

Run the loop:

uvx rrdoctor scan . --format json --output baseline.json
uvx rrdoctor plan . --output plan.md
# Work through plan.md without weakening checks.
uvx rrdoctor scan . --baseline baseline.json --fail-on-new error

The final command is the definition of done. If it reports a new error, continue fixing from the finding and re-run the gate.

The default scan is static and safe for untrusted repositories: it does not install, import, build, or execute target code.

For trusted repositories only, use the dynamic gate:

uvx rrdoctor verify . --run --timeout 600 --fail-on error

Prioritize high-signal reproducibility blockers: missing run paths, unpinned or missing dependency metadata, local-only data paths, stale notebook outputs, missing citation/data/results provenance, and seed flags that do not actually seed randomness.

Changes

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.

  1. 11d ago First seen · 41 lines · 0 tokens per session scan A cfda7ef2a32b

Subscribe to this mod's changes

rrdoctor-verify is a cursor rule published in the GitHub repository Tom409114/research-repo-doctor (1 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 295 tokens. 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.