compare-traces

compare-traces is a command for Claude Code from CharlesWiltgen/Axiom. It costs 15 tokens per session (730 once invoked), scanned A, original, MIT.

A performance-trace comparison tool for two Instruments recordings, which are Apple files containing app performance measurements. It uses xcprof to show function-level CPU-use changes, separate regressions from improvements, and return a failure status when thresholds are exceeded.

In plain words
What is it for?
It helps compare before-and-after performance, check whether a code change slowed a hot path, measure an optimisation, and gate CI merges on CPU regressions.
Why use it?
It replaces manual inspection of trace data and helps distinguish a real slowdown from a difference in the workload being recorded.

Command for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the axiom plugin — 27 skills, 17 commands, 42 agents, 5 hooks shipped together

Good fit It helps compare before-and-after performance, check whether a code change slowed a hot path, measure an optimisation, and gate CI merges on CPU regressions.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/charleswiltgen/axiom/compare-traces
About the project

Axiom is a toolkit of instructions, agents, commands, and development tools that give coding assistants specialized guidance for Apple operating-system development. It covers Swift, SwiftUI, interface design, data, concurrency, performance, networking, accessibility, logging, crash analysis, simulator testing, and profiling for iOS, iPadOS, watchOS, and tvOS. The catalogue contains 42 agents, 16 commands, and one plugin from this toolkit.

CharlesWiltgen/Axiom · 1,151 stars · on GitHub · charleswiltgen.github.io

Install

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.

Clone the repo
git clone --depth 1 https://github.com/CharlesWiltgen/Axiom

Made for: Claude Code.

Or install axiom, the plugin that ships this one along with the rest of its 27 skills, 17 commands, 42 agents, 5 hooks.

Wrote 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.

agentmods badge for compare-traces

README.md
[![agentmods](https://agentmods.dev/badge/commands/charleswiltgen/axiom/compare-traces/github.svg)](https://agentmods.dev/commands/charleswiltgen/axiom/compare-traces)
Your own site
<a href="https://agentmods.dev/commands/charleswiltgen/axiom/compare-traces"><img src="https://agentmods.dev/badge/commands/charleswiltgen/axiom/compare-traces/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.

agentmods 80×15 button for compare-traces

Your own site · 80×15
<a href="https://agentmods.dev/commands/charleswiltgen/axiom/compare-traces"><img src="https://agentmods.dev/badge/commands/charleswiltgen/axiom/compare-traces.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 730 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00015 $0.00730
Opus 5 $0.00008 $0.00365
Sonnet 5 $0.00003 $0.00146
Haiku 4.5 $0.00002 $0.00073

Measured 9d ago against content hash 1def14c87ad7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

compare-traces 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 9d 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.

.claude-plugin/plugins/axiom/commands/compare-traces.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compare Performance Traces

Diffs two Instruments .trace recordings with xcprof compare — function-level CPU-share deltas, regressions separated from improvements, and a non-zero exit code your CI can gate on. Replaces the old "export both traces and eyeball the XML" workflow.

When to Use

  • Verify a change didn't slow down a hot path ("did this PR regress CPU?").
  • Gate a merge on performance (fail when a function's CPU share jumps past a threshold).
  • Quantify an optimization (the improvement list shows what got faster).

Steps

  1. Verify the tool. command -v xcprof && xcprof doctor. If xcprof is missing, the Axiom install is stale — tell the user to update Axiom.

  2. Get two traces. Either the user already has baseline.trace + current.trace, or capture them. Both recordings MUST exercise the same workload (same UI flow / benchmark), or the deltas measure workload differences, not regressions:

    export XCPROF_TRACE_ROOT="$(mktemp -d)"
    # before-revision build, exercise the hot path:
    xcprof record --preset cpu --attach MyApp --time-limit 15s --no-prompt \
      --output "$XCPROF_TRACE_ROOT/baseline.trace"
    # after-revision build, exercise the SAME path:
    xcprof record --preset cpu --attach MyApp --time-limit 15s --no-prompt \
      --output "$XCPROF_TRACE_ROOT/current.trace"
    
  3. Compare. Default output is compact JSON; add --human to read it:

    xcprof compare baseline.trace current.trace --human
    

    For a CI gate, add --fail-on-regression (exit 3 when any function's inclusive CPU share rose ≥ --threshold-pct, default 5):

    xcprof compare baseline.trace current.trace --fail-on-regression --threshold-pct 5
    
  4. Interpret honestly. Report the regressions (sorted by severity = % delta × absolute time) and improvements. Note when frames were excluded for being unsymbolicated (pass --dsym for release builds). Deltas are percentage-points of CPU-cycle share — the only quantity comparable across two runs of different total work.

Read the full file on GitHub · 61 lines

Changes

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.

  1. 9d ago First seen · 61 lines · 15 tokens per session scan A 1def14c87ad7

Subscribe to this mod's changes

compare-traces is a command published in the GitHub repository CharlesWiltgen/Axiom (1,151 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 730 once invoked, about $0.0001 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 2026-08-30.