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.
npx agentmods add rules/nedcodes-ok/cursor-doctor/mongodbgit clone --depth 1 https://github.com/nedcodes-ok/cursor-doctorWhat 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 | $0.00484 | $0.00484 |
| Opus 5 | $0.00242 | $0.00242 |
| Sonnet 5 | $0.00097 | $0.00097 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
mongodb 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 2d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MongoDB Cursor Rules
You are an expert MongoDB developer. Follow these rules:
Schema Design
- Design for access patterns: embed what you read together
- Embed when: 1:1 or 1:few, data is read together, child doesnt exist alone
- Reference when: 1:many (unbounded), data accessed independently, many:many
- Avoid unbounded arrays — they cause document growth and slow updates
- Use Mongoose schemas with strict mode for application-level validation
Indexing
- Index fields used in queries, sorts, and aggregation match stages
- Compound indexes: equality fields first, sort fields next, range last (ESR rule)
- Use explain() to verify queries use indexes — no collection scans in production
- Unique indexes for natural keys. Sparse indexes for optional fields
- TTL indexes for auto-expiring documents (sessions, logs)
- Text indexes for search, but Atlas Search for anything serious
Queries
- Projection: return only needed fields, not entire documents
- Use $match early in aggregation pipelines to reduce working set
- Avoid $where and $regex without index prefix — they scan everything
- Use bulkWrite for batch operations, not loops of single writes
- Cursor-based pagination (sort + range query) over skip/limit
Aggregation
- Pipeline stages ordered: $match → $project → $group → $sort
- $lookup for joins — use pipeline form for filtered joins
- $facet for multi-dimension results in a single query
- Use $merge or $out to materialize views for dashboards
Data Modeling
- _id: ObjectId by default, custom IDs only when migrating from another DB
- Timestamps: createdAt/updatedAt with Mongoose timestamps option
- Soft deletes with deletedAt field and partial index on active docs
- Store monetary values as integers (cents) — never floats
- Use change streams for real-time reactions, not polling
Operations
- Replica sets for production — never standalone
- Read preference: secondaryPreferred for analytics, primary for consistency
- Connection pooling: tune maxPoolSize based on load
- Monitor slow queries with profiler level 1
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.
- 2d ago First seen · 51 lines · 484 tokens per session scan A e578058ee1f1
mongodb is a cursor rule published in the GitHub repository nedcodes-ok/cursor-doctor (9 stars, last pushed 5mo ago), licensed MIT. It adds 484 tokens to every session, about $0.0024 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 2026-08-31.
Other cursor rules, from other repositories
java
Modern Java: records, sealed classes, streams, virtual threads.
javascript
Modern JavaScript: ES2023+, async patterns, common traps.
accessibility
Accessibility: semantic HTML, ARIA, keyboard navigation, testing.
cross-tool-config
Cross-tool AI config: what transfers between Cursor, Claude Code, Copilot, Windsurf, Gemini, and Codex.
angular
Angular: signals, standalone components, RxJS patterns.
django
Django: models, views, ORM best practices.