ax-lldb

ax-lldb is a skill for Claude Code from Kasempiternal/axiom-v2. It costs 33 tokens per session (3,502 once invoked), scanned A, original, MIT.

A reference for LLDB, the debugger used with Xcode to inspect a running app and investigate crashes. It covers breakpoints, variables, thrown errors, asynchronous code, hangs, and evaluating code while paused.

In plain words
What is it for?
Use it to trace crashes to their source, inspect Swift values, stop when errors are thrown, diagnose stuck apps, debug async code, and test or change expressions during a debugging session.
Why use it?
It helps you see what the program was doing at the point of failure, including the relevant call stack and values, rather than relying only on crash messages.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the axiom plugin — 40 skills, 8 commands, 12 agents, 2 hooks shipped together

Good fit Use it to trace crashes to their source, inspect Swift values, stop when errors are thrown, diagnose stuck apps, debug async code, and test or change expressions during a debugging session.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kasempiternal/axiom-v2/ax-lldb
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.

Any agent
npx skills add Kasempiternal/axiom-v2 --skill ax-lldb
Clone the repo
git clone --depth 1 https://github.com/Kasempiternal/axiom-v2

Made for: Claude Code.

Or install axiom, the plugin that ships this one along with the rest of its 40 skills, 8 commands, 12 agents, 2 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 ax-lldb

README.md
[![agentmods](https://agentmods.dev/badge/skills/kasempiternal/axiom-v2/ax-lldb/github.svg)](https://agentmods.dev/skills/kasempiternal/axiom-v2/ax-lldb)
Your own site
<a href="https://agentmods.dev/skills/kasempiternal/axiom-v2/ax-lldb"><img src="https://agentmods.dev/badge/skills/kasempiternal/axiom-v2/ax-lldb/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 ax-lldb

Your own site · 80×15
<a href="https://agentmods.dev/skills/kasempiternal/axiom-v2/ax-lldb"><img src="https://agentmods.dev/badge/skills/kasempiternal/axiom-v2/ax-lldb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,502 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 $0.00033 $0.03502
Opus 5 $0.00016 $0.01751
Sonnet 5 $0.00007 $0.00700
Haiku 4.5 $0.00003 $0.00350

Measured 10d ago against content hash 0ce9ed59bb90, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ax-lldb 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 10d 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-plugin/skills/ax-lldb/SKILL.md · 410 lines

How it starts

The opening of the file, as written. The whole thing — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLDB

Quick Patterns

Crash Triage (When Debugger Stops)

(lldb) thread info              # What happened?
(lldb) bt                       # Where did it happen?
(lldb) frame select 3           # Jump to your code frame
(lldb) v                        # Inspect all variables
(lldb) v self.someProperty      # Inspect specific property

The Four Print Commands

Command Best For Reliability
v Swift structs, enums, locals, stored properties Most reliable (reads memory directly)
p Computed properties, function calls Compiles expression
po Classes with CustomDebugStringConvertible Calls debugDescription
expr Modifying state, calling methods Full expression evaluation

Default to v -- it never fails for stored properties. Use p when v can't reach it (computed properties, function calls). Use po only for class descriptions.

Exception Breakpoints (Set These Always)

(lldb) breakpoint set -E swift   # Break on all Swift errors
(lldb) breakpoint set -E objc    # Break on all ObjC exceptions

These catch errors at the throw site instead of the crash site.

Hang Diagnosis

(lldb) process interrupt         # Pause hung app
(lldb) bt all                    # All thread backtraces
(lldb) thread list               # Thread states (look for deadlocks)

Decision Tree

What do you need?
├─ App crashed, debugger stopped
│  ├─ Read stop reason -> thread info
│  ├─ Get backtrace -> bt
│  ├─ Find your frame -> frame select N
│  ├─ Inspect state -> v self, v localVar
│  └─ Classify: EXC_BAD_ACCESS? EXC_BREAKPOINT? SIGABRT?
├─ App is frozen/hung
│  ├─ Pause -> process interrupt
│  ├─ All backtraces -> bt all
│  ├─ Check main thread (Thread 0)
│  │  ├─ __psynch_mutexwait -> Blocked on mutex
│  │  ├─ _dispatch_sync_f_slow -> dispatch_sync deadlock
│  │  └─ Your code at top -> CPU-bound, move to background
│  └─ Check for deadlocks -> thread list (multiple threads waiting)
├─ Need to inspect a variable at runtime
│  └─ Set breakpoint -> v self.property
├─ po doesn't work / shows garbage
│  └─ Use v instead (see Swift Value Inspection)
├─ Need to test a fix without rebuilding
│  └─ expr self.property = newValue
├─ Want to break on specific condition
│  └─ breakpoint set -f File.swift -l 42 -c "value == nil"
└─ Need to log without stopping
   └─ Logpoint: breakpoint + command add + continue

Read the full file on GitHub · 410 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. 10d ago First seen · 410 lines · 33 tokens per session scan A 0ce9ed59bb90

Subscribe to this mod's changes

ax-lldb is a skill published in the GitHub repository Kasempiternal/axiom-v2 (4 stars, last pushed 6mo ago), licensed MIT. It adds 33 tokens to every session and 3,502 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

workflow-audit

Systematic UI workflow auditing for SwiftUI applications. Discovers entry points, traces user flows, detects dead ends and broken promises, audits data wiring, evaluates from user perspective. Triggers: "workflow audit", "audit flows", "find dead ends", "check navigation".

Terryc21/workflow-audit · 59 tokens

ttb-skill-bugfix

Systematic bug fixing workflow for TTBaseUIKit apps: root cause analysis, fix strategy, xcodebuild verify, zero regression.

tqtuan1201/TTBaseUIKit · 34 tokens

metrickit

Use when collecting or analyzing production iOS or iPadOS performance telemetry with MetricKit, including iOS 27 MetricManager async metric or diagnostic reports, hang or crash triage, custom signposts, extended launch measurement, durable export, or iOS 26 MXMetricManager compatibility.

thiennc-tesoglobal/ios-skills · 62 tokens

ios-memgraph-analysis

Captures or analyzes iOS memgraph files and persistent heap growth with Apple CLI evidence, ownership paths, raw artifacts, and matched-flow verification. Use for leaks or memory-growth investigations; route interactive Xcode Memory Graph, Instruments, or LLDB work to debugging-instruments.

thiennc-tesoglobal/ios-skills · 61 tokens

push-notifications

Implement or debug local and APNs notifications, permissions, payloads, categories, actions, silent pushes, and notification extensions. Use for alerts, badges, sounds, background delivery, rich content, registration, or delivery diagnosis; route Live Activity updates to activitykit.

thiennc-tesoglobal/ios-skills · 57 tokens

swiftui-performance

Profiles and fixes SwiftUI runtime performance with code review, Instruments, and repeatable measurement. Use for slow rendering, scrolling or animation hitches, excessive body updates, identity churn, layout spikes, broad Observation invalidation, CPU cost, or before/after verification.

thiennc-tesoglobal/ios-skills · 57 tokens