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.
npx skills add ComeOnOliver/skillshub --skill axiom-background-processing-diaggit clone --depth 1 https://github.com/ComeOnOliver/skillshubWrote 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/skills/comeonoliver/skillshub/axiom-background-processing-diag)<a href="https://agentmods.dev/skills/comeonoliver/skillshub/axiom-background-processing-diag"><img src="https://agentmods.dev/badge/skills/comeonoliver/skillshub/axiom-background-processing-diag/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/skills/comeonoliver/skillshub/axiom-background-processing-diag"><img src="https://agentmods.dev/badge/skills/comeonoliver/skillshub/axiom-background-processing-diag.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 | $0.00048 | $0.03081 |
| Opus 5 | $0.00024 | $0.01541 |
| Sonnet 5 | $0.00010 | $0.00616 |
| Haiku 4.5 | $0.00005 | $0.00308 |
Grade A, and why
axiom-background-processing-diag 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.
How it starts
The opening of the file, as written. The whole thing — 443 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Background Processing Diagnostics
Symptom-based troubleshooting for background task issues.
Related skills: axiom-background-processing (patterns, checklists), axiom-background-processing-ref (API reference)
Symptom 1: Task Never Runs
Handler never called despite successful submit().
Quick Diagnosis (5 minutes)
Task never runs?
│
├─ Step 1: Check Info.plist (2 min)
│ ├─ BGTaskSchedulerPermittedIdentifiers contains EXACT identifier?
│ │ └─ NO → Add identifier, rebuild
│ ├─ UIBackgroundModes includes "fetch" or "processing"?
│ │ └─ NO → Add required mode
│ └─ Identifiers case-sensitive match code?
│ └─ NO → Fix typo, rebuild
│
├─ Step 2: Check registration timing (2 min)
│ ├─ Registered in didFinishLaunchingWithOptions?
│ │ └─ NO → Move registration before return true
│ └─ Registration before first submit()?
│ └─ NO → Ensure register() precedes submit()
│
└─ Step 3: Check app state (1 min)
├─ App swiped away from App Switcher?
│ └─ YES → No background until user opens app
└─ Background App Refresh disabled in Settings?
└─ YES → Enable or inform user
Time-Cost Analysis
| Approach | Time | Success Rate |
|---|---|---|
| Check Info.plist + registration | 5 min | 70% (catches most issues) |
| Add console logging | 15 min | 90% |
| LLDB simulate launch | 5 min | 95% (confirms handler works) |
| Random code changes | 2+ hours | Low |
LLDB Quick Test
Verify handler is correctly registered:
e -l objc -- (void)[[BGTaskScheduler sharedScheduler] _simulateLaunchForTaskWithIdentifier:@"com.yourapp.refresh"]
If breakpoint hits → Registration correct, issue is scheduling/system factors. If nothing happens → Registration broken.
Symptom 2: Task Terminates Unexpectedly
Handler called but work doesn't complete before termination.
Quick Diagnosis (5 minutes)
Task terminates early?
│
├─ Step 1: Check expiration handler (1 min)
│ ├─ Expiration handler set FIRST in handler?
│ │ └─ NO → Move to very first line
│ └─ Expiration handler actually cancels work?
│ └─ NO → Add cancellation logic
│
├─ Step 2: Check setTaskCompleted (2 min)
│ ├─ Called in success path?
│ ├─ Called in failure path?
│ ├─ Called after expiration?
│ └─ ANY path missing → Task never signals completion
│
├─ Step 3: Check work duration (2 min)
│ ├─ BGAppRefreshTask work > 30 seconds?
│ │ └─ YES → Chunk work or use BGProcessingTask
│ └─ BGProcessingTask work > system limit?
│ └─ YES → Save progress, resume on next launch
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.
- 9d ago First seen · 443 lines · 48 tokens per session scan A c6a60b820948
axiom-background-processing-diag is a skill published in the GitHub repository ComeOnOliver/skillshub (63 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 3,081 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 2026-09-03.
Other skills, from other repositories
cmd_flutter_build
Fix Dart analyzer errors and Flutter build failures incrementally. Invokes the dart-build-resolver agent for minimal, surgical fixes.
cmd_gradle_build
Fix Gradle build errors for Android and KMP projects.
agent-introspection-debugging
Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.
swift-protocol-di-testing
Protocol-based dependency injection for testable Swift code — mock file system, network, and external APIs using focused protocols and Swift Testing.
swift-actor-persistence
Thread-safe data persistence in Swift using actors — in-memory cache with file-backed storage, eliminating data races by design.
firebase-crashlytics
Use when implementing crash reporting, capturing fatal/non-fatal errors, recording isolate/async exceptions, customizing reports, or uploading obfuscated symbols.