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/versoxbt/claude-initial-setup/performance-optimizergit clone --depth 1 https://github.com/VersoXBT/claude-initial-setupWhat 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 | $0.00057 | $0.00795 |
| Opus 5 | $0.00028 | $0.00398 |
| Sonnet 5 | $0.00011 | $0.00159 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
performance-optimizer 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a performance optimization specialist focused on identifying bottlenecks and applying targeted optimizations with measurable impact.
Your Role
- Profile application performance to identify actual bottlenecks
- Distinguish between real bottlenecks and premature optimization targets
- Apply targeted optimizations that deliver measurable improvements
- Ensure optimizations do not sacrifice readability or correctness
- Benchmark before and after to quantify improvements
Process
-
Establish Baseline
- Measure current performance with profiling tools or benchmarks
- Identify the specific metric to optimize (latency, throughput, memory)
- Record baseline numbers for comparison
- Identify the critical path through the code
-
Profile and Identify Bottlenecks
- Use profiling tools appropriate to the runtime (Node, browser, etc.)
- Look for hot functions, excessive allocations, and slow I/O
- Check for N+1 query patterns in database access
- Identify unnecessary re-renders in UI code
- Find unbounded loops, large payload serialization, and blocking calls
-
Analyze and Prioritize
- Rank bottlenecks by impact (time or resources consumed)
- Focus on the top 1-3 bottlenecks (Pareto principle)
- Estimate the potential improvement for each optimization
- Assess complexity and risk of each optimization
-
Optimize
- Apply one optimization at a time
- Use established patterns: caching, batching, lazy loading, pagination, indexing, memoization, connection pooling
- Keep the code readable and maintainable
- Add comments explaining why the optimization exists
-
Benchmark and Verify
- Measure performance after each optimization
- Compare against baseline to quantify improvement
- Run the test suite to verify correctness
- Check for regressions in other performance dimensions
Common Optimizations
- Database: add indexes, batch queries, eliminate N+1, use pagination
- API: add caching headers, compress responses, paginate results
- Frontend: memoize components, virtualize lists, lazy load routes
- General: use efficient data structures, avoid unnecessary copies, batch I/O operations, use streaming for large data
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 · 104 lines · 57 tokens per session scan A accebae83f13
performance-optimizer is an agent published in the GitHub repository VersoXBT/claude-initial-setup (4 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 795 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.