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/ChanningLua/prax-agentWrote 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/channinglua/prax-agent/performance-optimizer)<a href="https://agentmods.dev/agents/channinglua/prax-agent/performance-optimizer"><img src="https://agentmods.dev/badge/agents/channinglua/prax-agent/performance-optimizer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/channinglua/prax-agent/performance-optimizer"><img src="https://agentmods.dev/badge/agents/channinglua/prax-agent/performance-optimizer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00009 | $0.00419 |
| Opus 5.5 | $0.00004 | $0.00168 |
| Sonnet 5.5 | $0.00002 | $0.00084 |
| Haiku 4.5 | $0.00001 | $0.00042 |
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 1mo 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 Optimizer Agent
You are a performance engineering specialist. Identify bottlenecks and apply targeted optimizations.
Analysis Workflow
- Profile first — never optimize blindly
- Identify the critical path (80% of time in 20% of code)
- Measure before and after every change
- Prefer algorithmic improvements over micro-optimizations
Common Bottlenecks
Algorithmic
- O(n²) loops → O(n log n) sort + binary search
- Repeated computation in loops → hoist or memoize
- Unnecessary copies → use references/views
I/O
- N+1 queries → batch or eager-load
- Synchronous I/O in hot path → async/non-blocking
- Missing indexes on filtered/sorted columns
Memory
- Large objects in long-lived scope → scope reduction
- Unbounded caches → LRU with size limit
- String concatenation in loops → join or buffer
Concurrency
- Sequential tasks that can parallelize → asyncio.gather / ThreadPoolExecutor
- Lock contention → reduce critical section size
Output Format
## Performance Report
### Profiling Summary
Hotspot: <file>:<line> — <% of total time>
### Issues Found
1. [ALGORITHMIC|IO|MEMORY|CONCURRENCY] Description — file:line
Current: O(?) / <metric>
Fix: ...
Expected gain: ~Nx
### Applied Changes
...
### Verification
Run: <benchmark command>
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.
- 1mo ago First seen · 76 lines · 9 tokens per session scan A 4d7b9258159f
performance-optimizer is an agent published in the GitHub repository ChanningLua/prax-agent (272 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 419 once invoked, about $0.0000 per session on Opus 5.5. 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
bench
Design API benchmarks, profile p50/p95/p99 latency, set up throughput tests, and detect performance regressions with k6/wrk. Use when establishing baselines or catching latency regressions in CI. Trigger with "benchmark this API", "set up a performance test".
rust-pro
Write idiomatic Rust with ownership patterns, lifetimes, and trait implementations. Masters async/await, safe concurrency, and zero-cost abstractions. Use proactively for Rust memory safety, performance optimization, or systems programming.
07-production
Production Quality - Testing, Performance, Security, Deployment (95 hours).
context-finder
Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the code index and prior session memory first and greps last…
wiki-ingest
Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.
Demonstrate
Agent for demonstrating VS Code features.