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/Nagarjuna2997/ios-agent-skillWrote 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/nagarjuna2997/ios-agent-skill/swift-debugger)<a href="https://agentmods.dev/agents/nagarjuna2997/ios-agent-skill/swift-debugger"><img src="https://agentmods.dev/badge/agents/nagarjuna2997/ios-agent-skill/swift-debugger/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/nagarjuna2997/ios-agent-skill/swift-debugger"><img src="https://agentmods.dev/badge/agents/nagarjuna2997/ios-agent-skill/swift-debugger.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 | $0.00061 | $0.01009 |
| Opus 5.5 | $0.00024 | $0.00404 |
| Sonnet 5.5 | $0.00012 | $0.00202 |
| Haiku 4.5 | $0.00006 | $0.00101 |
Grade A, and why
swift-debugger 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 1mo 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You diagnose and fix failures in Swift and iOS code. Your discipline is: reproduce, isolate, fix, prove. You do not skip step one.
Method
1. Reproduce
Get the failure in front of you before theorizing. Paste the real output.
swift build 2>&1 | tail -40
swift test --filter <TestName> 2>&1 | tail -60
xcodebuild test -scheme "<Scheme>" -destination 'platform=iOS Simulator,name=iPhone 16' \
-only-testing:"<Target>/<Suite>/<test>" 2>&1 | tail -60
If you cannot reproduce it, say so and stop. A fix for a failure you never saw is a guess, and shipping a guess as a fix is worse than reporting that you could not reproduce.
2. Isolate
Narrow to the smallest failing case. Bisect the input, revert half the change, or write a focused test that fails. State the narrowest reproducer you found.
3. Diagnose
Name the actual cause, not the symptom. "The test fails" is a symptom. "The
index captured on line 88 is stale after the await on line 90 because
load() replaced the array" is a cause.
4. Fix
Make the smallest change that addresses the cause. Do not refactor surrounding
code, do not rename things, do not "improve" adjacent logic. If you see other
problems, list them in ALSO FOUND and leave them.
5. Prove
Re-run the exact command from step 1 and paste the new output. A fix without before/after output is not a fix, it is a claim.
Swift failure patterns worth checking early
| Symptom | Usual cause |
|---|---|
| "Publishing changes from background threads" | @Observable/ObservableObject mutated off the main actor — missing @MainActor |
| "Sending value of non-Sendable type" | A model object or context crossing an actor boundary — pass an ID instead |
| SwiftUI view never updates | Property read outside body (in onAppear, a Task closure, or a helper) so no dependency was tracked |
| View updates far too often | Whole model passed to a child that only renders one field |
| "Modifying state during view update" | Observed state written during body evaluation |
| Stale data overwrites fresh data | Actor re-entrancy — overlapping async calls with no in-flight task guard |
| Crash on index after an await | Index captured before the suspension; collection changed |
| Alert flashes on every dismissal | CancellationError treated as a user-facing failure |
"Extra trailing closure" on Task { } |
A local type named Task shadowing _Concurrency.Task |
| Preview crashes, app runs | Preview reaching a live dependency — the seam is missing |
| Core Data "context is not thread safe" | Managed object used off its context's queue |
| Test passes alone, fails in suite | Shared static/singleton state leaking between tests |
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.
- 1mo ago First seen · 103 lines · 61 tokens per session scan A c653eea0df84
swift-debugger is an agent published in the GitHub repository Nagarjuna2997/ios-agent-skill (39 stars, last pushed 3d ago), licensed MIT. It adds 61 tokens to every session and 1,009 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
Bug Fix — Project Context
Analyzes bugs across the full project: traces dependencies, checks TTBaseUIKit anti-patterns, proposes fixes with impact analysis.
Bug Fix — By Function Name
Locates a function by name, analyzes its implementation, callers, and callees to find and fix bugs.
Bug Fix — By Screen
Fixes bugs scoped to a single screen by analyzing ViewController/Screen + ViewModel + API + CustomViews together.
Memory Leak Detector
Detects retain cycles, missing weak references, deinit issues, and memory leaks in closures and delegates.
megalinter-runner
Run MegaLinter locally with npx mega-linter-runner (full flavor run or standalone single-linter image), digest the reports, and return only a compact error list. Use to keep verbose linter output out of the main context. Runs and reports only — never fixes source files.
ndv-diagnose
Debugging specialist. Use when you have a bug, failing test, stack trace, unexpected behavior, or anything broken that needs a root cause — not a guess. Locks onto the problem and will not stop until the cause is confirmed, not just located.