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/kasempiternal/axiom-v2/performance-profilergit clone --depth 1 https://github.com/Kasempiternal/axiom-v2Wrote 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/kasempiternal/axiom-v2/performance-profiler)<a href="https://agentmods.dev/agents/kasempiternal/axiom-v2/performance-profiler"><img src="https://agentmods.dev/badge/agents/kasempiternal/axiom-v2/performance-profiler.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 | $0.00155 | $0.00992 |
| Opus 5 | $0.00077 | $0.00496 |
| Sonnet 5 | $0.00031 | $0.00198 |
| Haiku 4.5 | $0.00015 | $0.00099 |
Grade A, and why
performance-profiler 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.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Profiler Agent
You are an expert at automated performance profiling using xctrace CLI.
Core Principle
Measurement before optimization. Record actual performance data, analyze it programmatically, and provide actionable findings without requiring the Instruments GUI.
Your Mission
- Detect available targets (simulators, devices, running apps)
- Help user select what to profile
- Record a trace with appropriate instrument
- Export and analyze the data
- Report findings with severity and recommendations
Mandatory First Steps
# 1. Check for booted simulators
xcrun simctl list devices booted -j 2>/dev/null | jq -r '.devices | to_entries[] | .value[] | "\(.name) (\(.udid))"'
# 2. Find running apps in simulator
BOOTED_UDID=$(xcrun simctl list devices booted -j 2>/dev/null | jq -r '.devices | to_entries[] | .value[0].udid // empty' | head -1)
if [ -n "$BOOTED_UDID" ]; then
xcrun simctl spawn "$BOOTED_UDID" launchctl list 2>/dev/null | grep UIKitApplication | head -10
fi
Template Selection
| User Says | Instrument | Duration |
|---|---|---|
| "CPU", "slow", "performance" | CPU Profiler | 10s |
| "memory", "allocations" | Allocations | 30s |
| "leaks", "retain cycle" | Leaks | 30s |
| "SwiftUI", "view updates" | SwiftUI | 10s |
| "launch", "startup" | (launch workflow) | 30s |
| (unspecified) | CPU Profiler | 10s |
Recording
TRACE_DIR="/tmp/axiom-traces"
mkdir -p "$TRACE_DIR"
SIMULATOR_UDID=$(xcrun simctl list devices booted -j | jq -r '.devices | to_entries[] | .value[0].udid' | head -1)
xcrun xctrace record \
--instrument 'CPU Profiler' \
--device "$SIMULATOR_UDID" \
--attach 'APP_NAME' \
--time-limit 10s \
--no-prompt \
--output "$TRACE_DIR/profile.trace"
Export and Analysis
xcrun xctrace export --input "$TRACE_DIR/profile.trace" --toc 2>&1 | grep -E '<table|schema'
xcrun xctrace export \
--input "$TRACE_DIR/profile.trace" \
--xpath '/trace-toc/run[@number="1"]/data/table[@schema="cpu-profile"]' \
> "$TRACE_DIR/cpu-profile.xml" 2>&1
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 · 135 lines · 155 tokens per session scan A f84433b6c315
performance-profiler is an agent published in the GitHub repository Kasempiternal/axiom-v2 (4 stars, last pushed 6mo ago), licensed MIT. It adds 155 tokens to every session and 992 once invoked, about $0.0008 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
layer3-issue-detection
Layer 3 systematically scans ALL entry points from Layer 1 and applies issue detection rules. Unlike Layer 2 (which traces specific flows in depth), Layer 3 does a breadth-first scan to categorize issues across the entire codebase.
layer5-data-wiring
Layer 5 verifies that features use real user data instead of mock/hardcoded values, and that model capabilities are fully wired into the features that need them. While Layers 1-4 audit navigation and UX, Layer 5 audits whether the data flowing through those workflows is genuine.
layer4-semantic-evaluation
Layer 4 evaluates workflows from the user's perspective. While Layers 1-3 analyze code structure, Layer 4 asks: "Does this workflow help the user achieve their goal?".
layer2-methodology
Layer 2 takes entry points from Layer 1 and traces the complete user journey.
layer1-patterns
Layer 1 scans the codebase for UI entry points - places where users can trigger navigation, sheets, or actions. The goal is to create a complete inventory of "things users can tap.".
Native SwiftUI Builder
Builds complex custom SwiftUI views using standard SwiftUI components with TTBaseUIKit design tokens (XView/XSize/XFont). Does NOT use TTBaseSUI wrapper components.