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 agentmods add skills/bcgov/bc-wallet-mobile/code-reviewnpx skills add bcgov/bc-wallet-mobile --skill code-reviewgit clone --depth 1 https://github.com/bcgov/bc-wallet-mobileWrote 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/bcgov/bc-wallet-mobile/code-review)<a href="https://agentmods.dev/skills/bcgov/bc-wallet-mobile/code-review"><img src="https://agentmods.dev/badge/skills/bcgov/bc-wallet-mobile/code-review.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.00598 |
| Opus 5 | $0.00015 | $0.00299 |
| Sonnet 5 | $0.00006 | $0.00120 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
code-review 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 2d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewing a pull request
This is a wallet holding people's real credentials. A defect that corrupts wallet state or leaks personal data costs a holder far more than a style nit costs the team. Review accordingly.
Procedure
-
Read What should the reviewer focus on first. It names where the author is least certain. Start there. If it says the change is trivial and the diff agrees, a short review is the correct review.
-
Check the blast radius. Credential create/store/delete, onboarding, PIN, biometrics, native modules, or IAS and mediator calls — read every changed line. Everything else is usually a skim.
-
Review by priority below, stopping when you have enough to be useful. Four real findings beat twenty observations.
-
Summarise by ordering the changed files by review risk, one line each. This is the most valuable part — it tells the human where to spend attention before they open the diff.
Priorities
- Wallet state — can this leave the wallet unrecoverable? Partial writes, no rollback on a failed exchange, assuming a credential survives an await.
- PII — personal data, tokens, credential attributes, and whole request/response bodies must not reach a log, an analytics event, or a user-visible error. Remote logging makes it permanent.
- iOS/Android divergence — behaviour changing on one platform only. Hides in native modules, permissions, camera, biometrics. Say which platform looks untested.
- Accessibility —
TouchableOpacity/PressableneedaccessibilityLabel,accessibilityRole,hitSlop,testID. Text must be localised, without layout\n. - Error handling — errors surface, never swallowed. API hooks throw; service
and UI hooks catch. Deleting something absent should succeed. Native errors go
through
throwNativeError/toNativeAppError. - Architecture — new work is MVVM; existing work follows the file it's in.
Leave alone
Formatting and import order (Prettier and ESLint own those), naming preferences, behaviour-preserving restructuring, coverage percentages, missing tests for code the PR didn't add, lockfiles and dependency bumps, and anything the author already flagged as known.
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.
- 2d ago First seen · 59 lines · 29 tokens per session scan A 40a4a365ef80
code-review is a skill published in the GitHub repository bcgov/bc-wallet-mobile (84 stars, last pushed yesterday), licensed Apache-2.0. It adds 29 tokens to every session and 598 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
orca-emulator-android
Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
winapp-maui
Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.
apple-search-ads
When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.