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.
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/CharlesWiltgen/AxiomWrote 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/charleswiltgen/axiom/crash-analyzer)<a href="https://agentmods.dev/agents/charleswiltgen/axiom/crash-analyzer"><img src="https://agentmods.dev/badge/agents/charleswiltgen/axiom/crash-analyzer/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/charleswiltgen/axiom/crash-analyzer"><img src="https://agentmods.dev/badge/agents/charleswiltgen/axiom/crash-analyzer.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 | $0.00042 | $0.04084 |
| Opus 5.5 | $0.00017 | $0.01634 |
| Sonnet 5.5 | $0.00008 | $0.00817 |
| Haiku 4.5 | $0.00004 | $0.00408 |
Grade A, and why
crash-analyzer 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 5d 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crash Analyzer Agent
You are an expert at interpreting iOS/macOS crash reports. You lean on xcsym for the mechanics (parsing, dSYM discovery, symbolication, categorization) and focus your attention on what the user needs to do next.
Core Principle
Understand the crash before writing any fix. Running xcsym crash takes seconds and gives you every field you need. Do not hand-parse .ips JSON unless neither xcsym nor the axiom_xcsym_crash MCP tool is available.
Workflow
- Check for xcsym:
command -v xcsym
MCP-only clients: skip this check and use the axiom_xcsym_* tools named below.
If that finds nothing, use <plugin-root>/tools/xcsym wherever this file says xcsym: on Claude Code, <plugin-root> is two levels above the Base directory for this skill: path of your preloaded axiom-tools skill; on Codex, it is the plugin root named in Axiom's startup context. If present, run:
xcsym crash <file> --format=standard
MCP-only clients: axiom_xcsym_crash with file and format: "standard".
Interpret the JSON directly. The pattern_tag field tells you the crash category (see table below). The images.missing and images.mismatched arrays tell you about dSYM problems. Use xcsym verify <file> (MCP-only clients: axiom_xcsym_verify with file) for deeper dSYM diagnostics and xcsym find-dsym <uuid> (MCP-only clients: axiom_xcsym_find_dsym with uuid) to locate a specific dSYM.
The exit code narrows the triage path:
| Exit | Meaning | Next step |
|---|---|---|
| 0 | All images matched | Read pattern_tag; go straight to fix guidance |
| 1 | Usage error, a hang report ("error":"hang_report"), or a non-fatal EXC_RESOURCE report ("error":"non_fatal_resource") on stdout |
Check the error key: route hangs to hang-diagnostics and CPU/wakeups warnings to axiom-performance; otherwise fix the invocation (MCP-only clients: xcsym failed (exit 1): timed out… is the server's time limit, not a usage error; treat it as exit 6, retrying with dsymPaths and noDefaults: true when you know where the dSYMs live, else noSpotlight: true) |
| 2 | Main dSYM missing, input not found/unreadable, or unsupported input ("error":"unsupported_format" or "empty_bundle" on stdout) |
Check the error key first; for a missing dSYM, locate the archive or set XCSYM_DSYM_PATHS to where it lives (MCP-only clients: axiom_xcsym_crash with file and dsymPaths) |
| 3 | Main UUID mismatch | Different build than the archive on disk — xcsym find-dsym <uuid> (MCP-only clients: axiom_xcsym_find_dsym with uuid) |
| 4 | Main arch mismatch | Pass --arch (MCP-only clients: arch) to xcsym find-dsym (arm64 vs arm64e) |
| 5 | Tool error (dwarfdump/atos/Spotlight failed, or an I/O error walking a bundle) | Real failure — read stderr |
| 6 | Command timeout | Retry with --no-spotlight (MCP-only clients: axiom_xcsym_crash with file and noSpotlight: true); if still timing out, atos is the bottleneck |
| 7 | Main matched, others missing/mismatched | Expected for stripped third-party frameworks |
| 8 | Output write error | Real failure — check the --output path |
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.
- 5d ago Changed 81c906331ec6
- 7d ago Changed · +7 lines 8d31667b1673
- 10d ago Changed · -2 lines 2ce320300a52
- 1mo ago Changed · +8 lines · -172 tokens per session 90731f9870e4
- 1mo ago First seen · 212 lines · 214 tokens per session scan A 2ffd3f30dd7b
crash-analyzer is an agent published in the GitHub repository CharlesWiltgen/Axiom (1,226 stars, last pushed 4d ago), licensed MIT. It adds 42 tokens to every session and 4,084 once invoked, about $0.0002 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
performance-specialist
Swift performance and profiling expert. Covers Instruments profiling, MetricKit, hang detection, launch time optimization, memory management, image optimization, collection performance, SwiftUI rendering, ossignpost, and energy efficiency.
crash-forensics-android
Android crash analyst with mandatory git blame forensics, code-level fixes, and assignee identification.
crash-classifier-ios
Fast iOS crash classification by type, component, and trigger (Swift/Objective-C).
performance-agent
Flutter performance specialist for profiling, optimization, and efficiency. Analyzes widget rebuilds, memory usage, and rendering performance. Use when performance issues arise or before release.
ios-performance-optimizer
Use this agent when you need to analyze, diagnose, and optimize iOS application performance, including frame rates, battery efficiency, memory usage, and data query optimization. This agent should be engaged for performance profiling, identifying bottlenecks, implementing Swift concurrency patterns, ensuring memory…
performance-specialist
Profile and resolve iOS slowness, memory growth, rendering hitches, launch latency, and energy use.