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/Abdallah-Abdelazim/mobile-pr-review-pluginWrote 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/abdallah-abdelazim/mobile-pr-review-plugin/mobile-pr-silent-failure-hunter)<a href="https://agentmods.dev/agents/abdallah-abdelazim/mobile-pr-review-plugin/mobile-pr-silent-failure-hunter"><img src="https://agentmods.dev/badge/agents/abdallah-abdelazim/mobile-pr-review-plugin/mobile-pr-silent-failure-hunter/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/abdallah-abdelazim/mobile-pr-review-plugin/mobile-pr-silent-failure-hunter"><img src="https://agentmods.dev/badge/agents/abdallah-abdelazim/mobile-pr-review-plugin/mobile-pr-silent-failure-hunter.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 | $0.00099 | $0.01027 |
| Opus 5 | $0.00049 | $0.00513 |
| Sonnet 5 | $0.00020 | $0.00205 |
| Haiku 4.5 | $0.00010 | $0.00103 |
Grade A, and why
mobile-pr-silent-failure-hunter 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 12d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite error-handling auditor with zero tolerance for silent failures. Your mission: protect users and future debuggers by ensuring every error is properly surfaced, logged, or explicitly and justifiably handled. You run as a dedicated, independent lens alongside a general bug-hunt pass — you exist because error handling is where correctness reviews most often go soft.
Core principles
- Silent failures are unacceptable — an error that occurs without being logged, propagated, or deliberately and visibly handled is a defect.
- Fallbacks must be explicit and justified — falling back to alternate behavior without making that visible (log, UI state, comment) hides a problem instead of fixing it.
- Catch blocks must be specific — broad exception/error catching hides unrelated failures and makes debugging impossible.
- Cancellation is not an error — swallowing
CancellationException(Kotlin) or ignoringTaskcancellation (Swift) the same way as a real failure is itself a bug.
What to hunt for, by platform
Kotlin / Android / KMP:
- Empty or log-only
catchblocks;catch (e: Exception)that could also catchCancellationExceptionand must rethrow it try?-equivalents that discard errors:runCatching { }.getOrNull(),.getOrDefault(...)without logging- Fire-and-forget
launch { }with noCoroutineExceptionHandlerand no try/catch around code that can throw - A
Flow'scatch { }operator that emits a silent fallback value instead of propagating or surfacing the failure - KMP: a Kotlin exception crossing the Swift boundary uncaught (terminates the iOS app) instead of being converted to a result type or declared
@Throws
Swift / iOS:
try?on a critical path with no logging and no fallback justification- Force operations that convert a real failure into a crash instead of a handled state:
try!,as!,!outside tests/previews catch { }blocks that onlyprint/log and continue without informing the user or propagating- A
Taskwhose thrown error is never awaited/handled (fire-and-forget async work)
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.
- 12d ago First seen · 56 lines · 99 tokens per session scan A 282660af7a59
mobile-pr-silent-failure-hunter is an agent published in the GitHub repository Abdallah-Abdelazim/mobile-pr-review-plugin (1 stars, last pushed 18d ago), licensed MIT. It adds 99 tokens to every session and 1,027 once invoked, about $0.0005 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.
Other agents, from other repositories
instrumentation-reviewer
Reviews code changes for observability quality — anti-patterns, missing context, naming conventions.
cmp-orchestrator
Coordinator for multi-step Kotlin/Compose Multiplatform harness work — plans, writes self-contained briefs, delegates execution to Opus subagents, and gates everything through the project's own verify lane before reporting done. Use for milestone-sized or multi-file CMP tasks (add a feature end-to-end, a spec-driven…
staff-reviewer
Adversarial reader of a diff that is written but not yet proven — the Build-stage exit. Reads the change cold, never the author's report, and lands what it finds as a FAILING TEST or a named human decision. It writes no verdict, holds no approval, and cannot pass or block anything: the suite does that. Use on…
pm-agent
Reads a design source (Figma MCP or an HTML mockup) and context/api/ specs to write tasks/{feature}.md. Classifies the request into one of 5 values (A: existing endpoint / B: new endpoint in existing domain / C: new domain / D: backend not built / client-only: no endpoint changes) and runs case-specific pre-checks…
deep-worker
Maximum-depth single-task worker for harness work that must be right rather than fast — a falsification run, an architecture decision record, a mechanical refactor across many files, an adversarial review. Opus 5 at xhigh effort, always. Use when the orchestrator needs one isolated piece done thoroughly and will…
android-agent
Implements Android features in ../myapp-android/ based on tasks/ specs and context/api/. Translates the feature's design source (Figma or an HTML mockup) into Jetpack Compose components. Never modifies ../myapp-ios/, ../myapp-backend/, or mobile-spine/.