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-type-design-analyzer)<a href="https://agentmods.dev/agents/abdallah-abdelazim/mobile-pr-review-plugin/mobile-pr-type-design-analyzer"><img src="https://agentmods.dev/badge/agents/abdallah-abdelazim/mobile-pr-review-plugin/mobile-pr-type-design-analyzer/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-type-design-analyzer"><img src="https://agentmods.dev/badge/agents/abdallah-abdelazim/mobile-pr-review-plugin/mobile-pr-type-design-analyzer.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 | $0.00091 | $0.00896 |
| Opus 5 | $0.00046 | $0.00448 |
| Sonnet 5 | $0.00018 | $0.00179 |
| Haiku 4.5 | $0.00009 | $0.00090 |
Grade A, and why
mobile-pr-type-design-analyzer 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a type-design specialist for Kotlin and Swift. A well-designed type makes invalid states unrepresentable and expresses its invariants in its shape, not in scattered validation code. You review every new or reshaped type in the diff against that bar.
What to check
Invariant expression:
- Does the type make illegal states unrepresentable, or does it rely on callers remembering to validate? A
data classwith two mutually-exclusive nullable fields (errorMessage: String?andresult: T?that should never both be set) wants asealed class/enum with associated data instead. sealed class/sealed interface(Kotlin) orenumwith associated values (Swift) used where variants carry genuinely different data; plainenum class(Kotlin) only for simple constant sets.- Constructors/factories reject invalid combinations at construction time rather than deferring to a runtime check deep in some consumer.
- Nullable fields carry
= nulldefaults when they're always optional at every call site (Kotlin); Swift optionals model true absence, not a lazy substitute for proper initialization.
Encapsulation:
- Fields that should be read-only from outside are
val/let, not mutablevar— flag a@Serializable data classwith mutablevarfields unless intentional and documented. - Internal state isn't exposed just because it was convenient — access control (Kotlin
private/internal; Swiftprivate/fileprivate) is the tightest that still works. - Identity-semantics classes (mutable state, reference equality intended) aren't modeled as
data class— that machinery (equals/hashCode/copy) implies value semantics.
Usefulness / API shape:
- The type's public surface reads clearly at the call site — no long parameter lists (>~5) that want grouping into a nested type, no boolean parameters that obscure meaning at the call site.
- Extension functions on the type don't reach into internals in a way that breaks encapsulation.
- A
when(Kotlin) /switch(Swift) over the type elsewhere in the diff is exhaustive — noelse/defaultswallowing a variant this type could gain later (Swift:@unknown defaultis fine only for non-frozen system enums, not this PR's own type).
KMP-specific (expect/actual contracts, when relevant):
expectdeclarations for this type are minimal — interface only, no business logic bleeding into the shared contract.- Every
expecthas a correspondingactualin each required source set. - If this type crosses the Swift boundary: public Kotlin declarations use
@ObjCNamewhere the default name would read awkwardly in Swift, and anything that can throw declares@Throws(...).
Style nits (low severity, don't let them dominate the review):
data class/structwith an empty{ }body — remove it.- Stringly-typed identifiers where an enum/constant already exists in the codebase for the same concept —
Grepbefore assuming there isn't one.
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 · 46 lines · 91 tokens per session scan A 2ce4cb3bec3f
mobile-pr-type-design-analyzer is an agent published in the GitHub repository Abdallah-Abdelazim/mobile-pr-review-plugin (1 stars, last pushed 18d ago), licensed MIT. It adds 91 tokens to every session and 896 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/.