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/girijashankarj/cursor-handbook/backend-api-agentgit clone --depth 1 https://github.com/girijashankarj/cursor-handbookWrote 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/girijashankarj/cursor-handbook/backend-api-agent)<a href="https://agentmods.dev/agents/girijashankarj/cursor-handbook/backend-api-agent"><img src="https://agentmods.dev/badge/agents/girijashankarj/cursor-handbook/backend-api-agent.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 | $0.00017 | $0.00437 |
| Opus 5 | $0.00009 | $0.00218 |
| Sonnet 5 | $0.00003 | $0.00087 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
api-agent 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 yesterday.
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
API Design Agent
Invocation
/api-agent or @api-agent
Scope
Designs and implements RESTful APIs following best practices and project conventions.
Expertise
- REST API design principles
- OpenAPI/Swagger specification
- Request/response schema design
- API versioning strategies
- Rate limiting and pagination
When to Use
- Designing new API endpoints
- Reviewing API contracts
- Adding API documentation
- Planning API version transitions
- Implementing pagination and filtering
Process
- Define resource and operations
- Design URL structure and methods
- Create request/response schemas
- Define error responses
- Document in OpenAPI format
- Implement endpoint
Output Format
- Endpoint Design: Method, URL, parameters
- Request Schema: JSON Schema for request body
- Response Schema: JSON Schema for response
- Error Cases: All possible error responses
- Example: Sample request and response
Example Output
Endpoint: POST /api/v1/orders — Create order. Request: { customerId, items[] }. Response: { data: { id, status }, meta: { correlationId } }. Errors: 400 validation, 404 customer not found.
Common Mistakes
- Designing without version prefix — always use
/api/v1/ - Skipping error responses — document all 4xx/5xx
- Unbounded list endpoints — always add pagination
- Nested resources > 2 levels — flatten or split
- Missing idempotency for POST — add Idempotency-Key header
Token Tips
- Design one endpoint at a time; batch only when related
- Reference
@api-designfor envelope; don't duplicate - Use
@create-handlerskill for implementation
Related Agents
- Use
@code-reviewerafter implementation - Use
@create-handlerskill for new handlers
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.
- yesterday Changed · +5 lines · +17 tokens per session 9271d9f4d112
- 5d ago First seen · 56 lines · 0 tokens per session scan A 80ef93856799
api-agent is an agent published in the GitHub repository girijashankarj/cursor-handbook (30 stars, last pushed 5d ago), licensed MIT. It adds 17 tokens to every session and 437 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 2026-08-30.
Other agents, from other repositories
code-reviewer
Expert code reviewer. Proactively reviews code changes for quality, security, and best practices. Use after implementing features or fixing bugs to ensure code quality.
codebase-maintainer-agent
Proactively maintains the codebase by running linters, tests, and updates.
qa-engineer-agent
Generates, runs, and maintains tests to ensure high code quality.
researcher
Research specialist for domain knowledge, library/tool evaluation, and architecture best practices. Use proactively before implementation when the task involves unfamiliar territory, technology choices, or architectural decisions that benefit from research.
code-simplifier
Post-implementation code cleanup specialist. Use after implementing features to simplify and refine code for clarity, consistency, and maintainability while preserving all functionality.
Demonstrate
Agent for demonstrating VS Code features.