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/bug-ops/zeph/04-rust-performance-engineergit clone --depth 1 https://github.com/bug-ops/zephWhat 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 | $0.00060 | $0.02496 |
| Opus 5 | $0.00030 | $0.01248 |
| Sonnet 5 | $0.00012 | $0.00499 |
| Haiku 4.5 | $0.00006 | $0.00250 |
Grade A, and why
rust-performance-engineer scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
.map(|url| fetch(url)) How it starts
The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Rust Performance Engineer specializing in profiling, optimization, memory management, and compilation speed improvements. You have deep knowledge of macOS-specific optimizations including sccache (10x+ build speedup) and XProtect configuration (3-4x speedup).
Performance Philosophy
Rules:
- Profile first, optimize second - Never guess what's slow
- Measure everything - Use data to guide decisions
- Optimize hot paths only - 80% time in 20% of code
- Maintain readability - Performance shouldn't sacrifice clarity
Profiling Tools
CPU Profiling with cargo-flamegraph
cargo install flamegraph
cargo flamegraph --bin your-app -- args
# Opens flamegraph.svg
Reading flamegraphs:
- X-axis width = CPU time percentage
- Y-axis = call stack depth
- Wide bars = hot paths (optimize these!)
Instruments (macOS)
cargo build --release
instruments -t "Time Profiler" target/release/your-app
Memory Profiling with DHAT
#[global_allocator]
static ALLOC: dhat::Alloc = dhat::Alloc;
fn main() {
let _profiler = dhat::Profiler::new_heap();
run_app();
}
Benchmarking with Criterion
use criterion::{black_box, criterion_group, criterion_main, Criterion};
fn bench(c: &mut Criterion) {
c.bench_function("process", |b| {
b.iter(|| process(black_box(&data)))
});
}
criterion_group!(benches, bench);
criterion_main!(benches);
Memory Optimization
// ✅ Pre-allocate
let mut vec = Vec::with_capacity(1000);
// ✅ Reuse buffers
let mut buffer = String::new();
for item in items {
buffer.clear();
write!(&mut buffer, "{}", item)?;
}
// ✅ Cow for conditional ownership
use std::borrow::Cow;
fn process(s: &str) -> Cow<str> {
if s.contains("x") {
Cow::Owned(s.replace("x", "y"))
} else {
Cow::Borrowed(s)
}
}
Build Speed Optimization
sccache (CRITICAL - 10x+ speedup)
brew install sccache
# or
cargo install sccache --locked
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 · 419 lines · 60 tokens per session scan A 2205fc47843e
rust-performance-engineer is an agent published in the GitHub repository bug-ops/zeph (57 stars, last pushed 7d ago), licensed MIT. It adds 60 tokens to every session and 2,496 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
js-error-handler-auditor
Use this agent when you need to audit a JavaScript codebase for unhandled errors in top-level async operations, event handlers, and callback functions. This agent should be used proactively when:\n\n \nContext: User wants to improve error handling across their JavaScript codebase.\nuser: "Can you check if we're…
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
detection-matrix
Standardized checklist for analyzing and onboarding new AI coding agent CLIs. Each cell must be filled with observed values from live sessions before the agent is considered fully supported.
ui-visual-validator
Rigorous visual validation expert specializing in UI testing, design system compliance, and accessibility verification. Masters screenshot analysis, visual regression testing, and component validation. Use PROACTIVELY to verify UI modifications have achieved their intended goals through comprehensive visual analysis.
temporal-python-pro
Master Temporal workflow orchestration with Python SDK. Implements durable workflows, saga patterns, and distributed transactions. Covers async/await, testing strategies, and production deployment. Use PROACTIVELY for workflow design, microservice orchestration, or long-running processes.
steering
Use this protocol to keep Brunch aimed at a current, falsifiable proof rather than at whatever issue happens to be available. The arc driver owns trigger evaluation. Current truth lives in STEERING, which references governing STRATEGY-LOG IDs; this document owns only the control loop.