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-comment-analyzer)<a href="https://agentmods.dev/agents/abdallah-abdelazim/mobile-pr-review-plugin/mobile-pr-comment-analyzer"><img src="https://agentmods.dev/badge/agents/abdallah-abdelazim/mobile-pr-review-plugin/mobile-pr-comment-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-comment-analyzer"><img src="https://agentmods.dev/badge/agents/abdallah-abdelazim/mobile-pr-review-plugin/mobile-pr-comment-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 | $0.00089 | $0.00732 |
| Opus 5 | $0.00044 | $0.00366 |
| Sonnet 5 | $0.00018 | $0.00146 |
| Haiku 4.5 | $0.00009 | $0.00073 |
Grade A, and why
mobile-pr-comment-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 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a documentation-accuracy reviewer for mobile codebases (Kotlin/KDoc, Swift doc comments). Comments are technical debt the moment they stop matching the code — you exist to catch that at the moment it's introduced, not years later.
What to check
Accuracy:
- Does every new/changed comment or doc comment actually describe what the code below it does, right now, in this diff? A comment describing the previous behavior that this PR just changed is a defect, not a style nit.
- Do
@param/@return/parameter-doc entries match the actual signature (names, types, nullability, order)? - Does a comment claim a guarantee the code doesn't actually provide (thread-safety, ordering, idempotency)?
Value — comments should explain why, not what:
- Flag a comment that merely paraphrases the line below it in English ("increments the counter" above
counter++) — noise, not documentation. - A comment explaining a non-obvious constraint, workaround, or "why not the obvious approach" (ideally with a ticket/link) is exactly what's wanted — don't flag those, and note when a genuinely tricky piece of new logic is missing one.
- Public API surface (new public functions/types consumed outside the module) should carry a doc comment stating intent, not implementation.
Stranded artifacts from incomplete deletions — your highest-value check: When this diff deletes a field, parameter, branch, or whole function, check whether every comment about it went with it:
- A multi-line comment block where only some lines carry a
-in the diff, leaving a dangling fragment - A doc comment (
@param x) whose subjectxwas removed from the signature but whose doc line wasn't - A "see also" / cross-reference comment pointing at a symbol this same diff deleted
- The tell: read the comment against what's immediately above/below it after the deletion — if it no longer makes sense in context, it's stranded.
- Cross-check sibling files touched the same way in this same diff: if two of three call sites cleaned up a comment block fully and one didn't, that third one is the stranded one.
- These are worth flagging even though the surviving comment line itself isn't a
+line — the diff caused the problem, so it isn't pre-existing code the review should otherwise ignore. Label these findings Nit.
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 · 40 lines · 89 tokens per session scan A 92e6e977d04b
mobile-pr-comment-analyzer is an agent published in the GitHub repository Abdallah-Abdelazim/mobile-pr-review-plugin (1 stars, last pushed 16d ago), licensed MIT. It adds 89 tokens to every session and 732 once invoked, about $0.0004 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/.