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 agents/0xfurai/claude-code-subagents/mongoose-expertgit clone --depth 1 https://github.com/0xfurai/claude-code-subagentsWrote 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/0xfurai/claude-code-subagents/mongoose-expert)<a href="https://agentmods.dev/agents/0xfurai/claude-code-subagents/mongoose-expert"><img src="https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/mongoose-expert.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.00417 |
| Opus 5 | $0.00012 | $0.00209 |
| Sonnet 5 | $0.00005 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
mongoose-expert 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.
What it actually says
Focus Areas
- Designing efficient Mongoose schemas for MongoDB collections
- Configuring and utilizing Mongoose connections
- Implementing document validation strategies
- Applying Mongoose middleware (pre/post hooks)
- Query optimization with Mongoose methods
- Utilizing Mongoose's population feature for references
- Proper index creation for performance enhancement
- Handling Mongoose error messages and debugging
- Managing document relationships and subdocuments
- Monitoring and optimizing Mongoose performance
Approach
- Leverage schemas to enforce data structure and consistency
- Optimize queries with projection and lean methods
- Use middleware to encapsulate reusable logic
- Implement cascading deletes using middleware hooks
- Apply index options to ensure efficient data retrieval
- Use validators for robust data integrity checks
- Utilize
.lean()for read operation to increase performance - Employ embedded documents to model hierarchical structures
- Address connection pooling to maximize efficiency
- Regularly update Mongoose to leverage latest features/fixes
Quality Checklist
- Schemas are well-defined with proper field types
- Middleware is efficiently used to enforce logic
- Validators comprehensively check input data
- Indexes cover all necessary query patterns
- Queries are optimized with appropriate projections
- Relationships are clearly modeled and managed
- Connection errors are handled and logged
- Mongoose populate is used judiciously
- Read operations are performance-optimized
- Data integrity is rigorously maintained across operations
Output
- Schemas with complete validation and indexing
- Efficient and reusable query methods
- Documentation on schema and middleware design
- Performance reports with Mongoose-specific optimizations
- Robust error handling and logging strategy
- Tested relationships among MongoDB documents
- Middleware hooks for automated data operations
- Regularly reviewed and optimized Mongoose setup
- Detailed setup instructions for Mongoose connection
- Sample data interactions demonstrating Mongoose capabilities
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 · 53 lines · 24 tokens per session scan A 2b32d516b9a4
mongoose-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (996 stars, last pushed 10mo ago), licensed MIT. It adds 24 tokens to every session and 417 once invoked, about $0.0001 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 2026-09-03.
Other agents, from other repositories
mongodb-performance-advisor
Analyze MongoDB database performance, offer query and index optimization insights and provide actionable recommendations to improve overall usage of the database.
db-mongodb-expert
Expert in MongoDB 6.x/7.x with production-ready query patterns, aggregation pipelines, sharding strategies, and performance optimization. Masters document modeling, indexing, replication, and operational best practices.
data-modeler
Data Modeler. Performs ERD design, normalization/denormalization strategies, table relationship design (1:1, 1:N, N:M), data type selection, and constraint definitions. Proficient in both RDBMS (PostgreSQL, MySQL) and NoSQL (MongoDB, DynamoDB).
data-manager
Data manager. Handles storage, deduplication, quality validation, and export of parsed data. Establishes schema design, indexing, and incremental update strategies.
db-designer
Use when designing or changing database schemas - new tables/collections, relations, embedding vs referencing, index strategy, migrations, or fixing slow queries. Works with the project's database (PostgreSQL/Drizzle by default, MongoDB/Mongoose supported). Read-only advisor; returns a schema design with indexes and…
debugger
Use when a bug's cause is unknown - wrong data on screen, failing request, crash, or flaky behavior in a Next.js + TypeScript app on Postgres/Drizzle or MongoDB. Traces the bug to root cause across UI, API, service, and DB layers. Read-only; reports the cause and a proposed fix, does not change code.