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.
git 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-performance-agent)<a href="https://agentmods.dev/agents/girijashankarj/cursor-handbook/backend-performance-agent"><img src="https://agentmods.dev/badge/agents/girijashankarj/cursor-handbook/backend-performance-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 5.1 | $0.00000 | $0.00277 |
| Opus 5 | $0.00000 | $0.00138 |
| Sonnet 5 | $0.00000 | $0.00055 |
| Haiku 4.5 | $0.00000 | $0.00028 |
Grade A, and why
backend-performance-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 4d 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
Performance Agent
Invocation
/performance-agent or @performance-agent
Scope
Identifies and resolves performance bottlenecks in backend services.
Expertise
- Database query optimization
- Caching strategies
- Memory and CPU profiling
- N+1 query detection
- Load testing and capacity planning
When to Use
- Slow API response times
- High database query times
- Memory leaks or high memory usage
- Preparing for traffic spikes
- Optimizing critical code paths
Process
- Identify the bottleneck (profiling, metrics)
- Analyze root cause
- Propose optimization options
- Implement with benchmarks
- Verify improvement with metrics
Optimization Checklist
- Database: Missing indexes, N+1 queries, unoptimized joins
- Caching: Cache-able data not cached, stale cache issues
- Memory: Unnecessary allocations, memory leaks, large payloads
- Network: Redundant API calls, missing connection pooling
- Compute: Expensive operations, unoptimized algorithms
Output Format
- Bottleneck: What's slow and why
- Impact: How much improvement expected
- Solution: Code changes with before/after benchmarks
- Trade-offs: Any downsides to the optimization
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.
- 4d ago First seen · 42 lines · 0 tokens per session scan A 4e0f91c445c3
backend-performance-agent is an agent published in the GitHub repository girijashankarj/cursor-handbook (30 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 277 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 2026-09-03.
Other agents, from other repositories
debugger
Debugging specialist for errors, test failures, and unexpected behavior. Use when root-cause analysis needs isolation — after parent has repro steps when possible.
architect
Use for system design, architecture decisions, database schema design, API design, technical planning. Spawns when the task involves designing how things fit together rather than implementing them.
maintainer-agent
Expert codebase maintainer. Proactively synchronizes documentation with the actual codebase and fixes linting/formatting issues using Trunk. Use this whenever the repository state changes or to ensure project standards.
engineer
Full-stack coding agent. Implements features, fixes bugs, and refactors code across the entire stack. Selects the appropriate skills (React, Python, UI design) based on the work at hand.
debugger
Debugging specialist for errors and test failures. Use when encountering issues.
debugger
Systematic debugging specialist. Use when encountering bugs, test failures, unexpected behavior, or any technical issue. Follows a 4-phase root cause analysis process before proposing fixes.