RuleStack

Configs

Stacks

Compare

Diff

RuleStack

Configs

Stacks

Compare

Diff

Read API

RuleStack

Configs

Stacks

Compare

Diff

Read API

Diff/aledon8-openleukemia-ml-claude ↔ aledon8-openleukemia-cursor-rules-project

Comparison

A · CLAUDE.md · Aledon8/OpenLeukemiaB · Cursor rules · Aledon8/OpenLeukemia
What each file covers, counted
DimensionSharedOnly in AOnly in BOverlap
Sections0230%
Commands0070%
Section tags22233%

What each file covers

Sections

0 shared · 2 only in A · 3 only in B
  • − ML Workspace Instructions
  • − Rules
  • + Cursor Project Rules
  • + Always Follow
  • + Checks

Commands

0 shared · 0 only in A · 7 only in B
  • + npm run lint:frontend
  • + npm run typecheck:frontend
  • + npm test --workspace frontend
  • + npm --workspace frontend run build
  • + python -m ruff check .
  • + python -m pytest
  • + python -m mypy app

Section tags

2 shared · 2 only in A · 2 only in B
  • − code-style
  • − monorepo
  • + test
  • + lint-format
  •   do-not
  •   agent-behaviour

Line diff

+24 added−9 removed4 unchanged14.3% identical
Aledon8/OpenLeukemia · ml/CLAUDE.md
@@ −1 @@
1# ML Workspace Instructions
 
 
 
 
 
2 
3This directory is for training pipelines, inference experiments, evaluations, and notebooks.
4 
5## Rules
6 
7- Keep structured ML workflows separate from LLM explanation workflows.
8- Prefer reproducible scripts and documented evaluation outputs over one-off notebook state.
9- Do not treat model output as diagnosis, urgent clinical judgment, or treatment recommendation.
10- Track assumptions about input data, labels, validation, and limitations close to the code or report that uses them.
11- Avoid committing patient-identifying or sensitive medical data.
12- Prefer measurable success criteria: metric, split, threshold, calibration, and known failure modes.
 
 
 
 
 
 
 
 
 
 
13 
Aledon8/OpenLeukemia · .cursor/rules/project.mdc
@@ +1 @@
1---
2description: OpenLeukemia project instructions
3globs:
4 - "**/*"
5alwaysApply: true
6---
7 
8# Cursor Project Rules
9 
10OpenLeukemia is a patient-centered leukemia data platform for organizing medical data, tracking changes over time, extracting structured information from documents, and explaining validated model outputs.
11 
12## Always Follow
13 
14- Patient data belongs to the patient.
15- Registration is not blanket consent.
16- Consent must be separate, explicit, auditable, and revocable.
17- AI may summarize, extract, and explain; it must not diagnose, recommend treatment, or make urgent clinical judgments.
18- Read nearby code and docs before editing.
19- Keep changes minimal and focused.
20- Follow existing React, TypeScript, Supabase, FastAPI, and Python patterns.
21- Run or recommend the relevant checks after changes.
22- Do not rewrite unrelated files or add dependencies without clear need.
23 
24## Checks
25 
26- Frontend: `npm run lint:frontend`, `npm run typecheck:frontend`, `npm test --workspace frontend`, `npm --workspace frontend run build`.
27- AI service from `ai-service/`: `python -m ruff check .`, `python -m pytest`, `python -m mypy app`.
28 
@@ −1 +1 @@
1−# ML Workspace Instructions
1+---
2+description: OpenLeukemia project instructions
3+globs:
4+ - "**/*"
5+alwaysApply: true
6+---
27  
3−This directory is for training pipelines, inference experiments, evaluations, and notebooks.
8+# Cursor Project Rules
49  
5−## Rules
10+OpenLeukemia is a patient-centered leukemia data platform for organizing medical data, tracking changes over time, extracting structured information from documents, and explaining validated model outputs.
611  
7−- Keep structured ML workflows separate from LLM explanation workflows.
8−- Prefer reproducible scripts and documented evaluation outputs over one-off notebook state.
9−- Do not treat model output as diagnosis, urgent clinical judgment, or treatment recommendation.
10−- Track assumptions about input data, labels, validation, and limitations close to the code or report that uses them.
11−- Avoid committing patient-identifying or sensitive medical data.
12−- Prefer measurable success criteria: metric, split, threshold, calibration, and known failure modes.
12+## Always Follow
13+ 
14+- Patient data belongs to the patient.
15+- Registration is not blanket consent.
16+- Consent must be separate, explicit, auditable, and revocable.
17+- AI may summarize, extract, and explain; it must not diagnose, recommend treatment, or make urgent clinical judgments.
18+- Read nearby code and docs before editing.
19+- Keep changes minimal and focused.
20+- Follow existing React, TypeScript, Supabase, FastAPI, and Python patterns.
21+- Run or recommend the relevant checks after changes.
22+- Do not rewrite unrelated files or add dependencies without clear need.
23+ 
24+## Checks
25+ 
26+- Frontend: `npm run lint:frontend`, `npm run typecheck:frontend`, `npm test --workspace frontend`, `npm --workspace frontend run build`.
27+- AI service from `ai-service/`: `python -m ruff check .`, `python -m pytest`, `python -m mypy app`.
1328  
RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack

RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack

RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack