axiom-analyze-crash

axiom-analyze-crash is a command for Claude Code, Cursor from CharlesWiltgen/Axiom. It costs 22 tokens per session (440 once invoked), scanned A, original, MIT.

A crash-log analysis command for iOS and macOS. It accepts a crash file, crash-report bundle, or pasted report and uses symbol information to explain where and why the app failed.

In plain words
What is it for?
Use it to inspect an individual Apple-platform crash, identify the crashed thread, and produce a summary, standard, or full analysis.
Why use it?
Crash reports can contain low-level addresses and threads that are hard to read directly. This helps turn them into a more understandable failure pattern while handling the report safely.

Command for Claude CodeCursor

Written for Cursor and Claude Code: shipped in a Cursor plugin, but also a Claude Code command (commands/*.md).

Part of the axiom plugin — 17 commands shipped together

Good fit Use it to inspect an individual Apple-platform crash, identify the crashed thread, and produce a summary, standard, or full analysis.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/charleswiltgen/axiom/axiom-analyze-crash
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 · 1,155 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, Cursor.

Or install axiom, the plugin that ships this one along with the rest of its 17 commands.

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 axiom-analyze-crash

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/charleswiltgen/axiom/axiom-analyze-crash"><img src="https://agentmods.dev/badge/commands/charleswiltgen/axiom/axiom-analyze-crash.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 440 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 $0.00022 $0.00440
Opus 5 $0.00011 $0.00220
Sonnet 5 $0.00004 $0.00088
Haiku 4.5 $0.00002 $0.00044

Measured 6d ago against content hash d9137b4add08, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

axiom-analyze-crash 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 6d 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.

axiom-cursor/commands/axiom-analyze-crash.md · 19 lines

What it actually says

Analyze Crash Log

Use Axiom's structured MCP tools instead of invoking the xcsym helper binary.

  1. Accept either an existing crash-file path or pasted crash-report content. If neither is present or the input is ambiguous, ask the user for one crash report before continuing.
  2. For a file path, pass the verified readable file path directly in file. A readable .xccrashpoint bundle path is also valid. Never execute or rewrite a user-supplied path.
  3. For pasted content, create a task-scoped temporary directory with mode 0700 and a new file with mode 0600 outside the repository. Create the file exclusively with a fixed, non-user-derived name and an extension appropriate to JSON or text. Write the content with a filesystem write operation that does not interpolate it into a shell command. Do not include the crash content in a command line, log, diagnostic, or filename.
  4. Call axiom_xcsym_crash with the selected path in file and only summary, standard, or full in format. Use standard unless the user requests another output tier; pass only other schema-supported fields that the user supplied or the analysis requires.
  5. Interpret the returned pattern, crashed-thread frames, and dSYM completeness even when the tool reports a non-zero completeness status.
  6. For dSYM mismatches, call axiom_xcsym_verify with the same path in file, then call axiom_xcsym_find_dsym with the expected uuid when discovery is needed.
  7. After all MCP calls finish or fail, remove only the temporary file and directory created for this request. Never remove or modify a user-supplied crash path.
  8. Report the likely root cause, evidence, symbolication limits, and concrete next steps.

If a required MCP tool is unavailable, stop and report that the Axiom MCP integration is missing; do not fall back to a same-named executable.

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. 6d ago First seen · 19 lines · 22 tokens per session scan A d9137b4add08

Subscribe to this mod's changes

axiom-analyze-crash is a command published in the GitHub repository CharlesWiltgen/Axiom (1,155 stars, last pushed 3d ago), licensed MIT. It adds 22 tokens to every session and 440 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 2026-09-06.