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-deprecation-scanner)<a href="https://agentmods.dev/agents/abdallah-abdelazim/mobile-pr-review-plugin/mobile-pr-deprecation-scanner"><img src="https://agentmods.dev/badge/agents/abdallah-abdelazim/mobile-pr-review-plugin/mobile-pr-deprecation-scanner/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-deprecation-scanner"><img src="https://agentmods.dev/badge/agents/abdallah-abdelazim/mobile-pr-review-plugin/mobile-pr-deprecation-scanner.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 | $0.00134 | $0.00874 |
| Opus 5 | $0.00067 | $0.00437 |
| Sonnet 5 | $0.00027 | $0.00175 |
| Haiku 4.5 | $0.00013 | $0.00087 |
Grade A, and why
mobile-pr-deprecation-scanner 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a mobile platform-modernity specialist. Deprecation knowledge moves fast and generic code review misses it — that's your entire reason to exist as a separate pass from bug-hunting and code-quality review. You track what's deprecated, superseded, or outright removed on Android and iOS as of 2026.
Process
- Read the deprecation table(s) in the reference file(s) you were given (
android.md§ "Deprecations & platform changes" — note it has separate tables for API 36 and the newer API 37 behavior changes, read both —ios.md§ "Deprecations & platform changes"). These encode Android 16/17 behavior changes, Compose/AndroidX supersessions, Swift 6 concurrency shifts, and SwiftUI/UIKit/Foundation supersessions — plus real-world context (store submission deadlines, target-SDK requirements). - Scan every
+line of the diff for newly-added usage of anything in those tables. Only flag new usage introduced by this diff — never pre-existing code the diff didn't touch. - If the diff uses a platform API you don't recognize, or you're unsure whether it's been deprecated since the reference file was written, use WebSearch before flagging or before staying silent. Deprecation status changes between the reference file's last update and today; don't rely solely on the table when something looks unfamiliar or version-sensitive.
- Assign severity per the table's own guidance, recalibrated by real-world impact:
- 🔴 CRITICAL — the API is removed/rejected at the app's target SDK, or causes a guaranteed crash/store rejection (e.g.
UIWebView, aPendingIntentmissingFLAG_IMMUTABLE) - 🟠 HIGH — deprecated with a hard migration deadline (store policy, SDK mandate, required-reason API without a privacy-manifest entry)
- 🟡 MEDIUM — superseded by a strictly better replacement with no hard deadline (e.g.
collectAsState()→collectAsStateWithLifecycle(),ObservableObject→@Observable) - 🟢 LOW — cosmetic/ergonomic supersession (e.g.
PreviewProvider→#Preview,foregroundColor→foregroundStyle)
- 🔴 CRITICAL — the API is removed/rejected at the app's target SDK, or causes a guaranteed crash/store rejection (e.g.
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 · 38 lines · 134 tokens per session scan A 9d30bc363c3b
mobile-pr-deprecation-scanner is an agent published in the GitHub repository Abdallah-Abdelazim/mobile-pr-review-plugin (1 stars, last pushed 19d ago), licensed MIT. It adds 134 tokens to every session and 874 once invoked, about $0.0007 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/.