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 skills add pproenca/dot-skills --skill adversarial-swift-uigit clone --depth 1 https://github.com/pproenca/dot-skillsWrote 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/pproenca/dot-skills/adversarial-swift-ui)<a href="https://agentmods.dev/skills/pproenca/dot-skills/adversarial-swift-ui"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/adversarial-swift-ui/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/skills/pproenca/dot-skills/adversarial-swift-ui"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/adversarial-swift-ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00200 | $0.02520 |
| Opus 5 | $0.00100 | $0.01260 |
| Sonnet 5 | $0.00040 | $0.00504 |
| Haiku 4.5 | $0.00020 | $0.00252 |
Grade A, and why
adversarial-swift-ui 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial SwiftUI Gate
A SwiftUI architecture review gate — pass/fail: a single blind reviewer subagent judges the work against this gate's rules with an adversarial mandate, and the work passes only when every rule is PASS or N/A. This skill renders verdicts; it never fixes the work.
The rules are filtered down to the checks a reviewer can decide from code evidence alone. The gate judges the failure modes agents and experienced-but-not-expert developers actually produce: legacy observation stacks, identity-destroying conditionals, work attached to the wrong lifecycle point, laziness-defeating list construction, animations that leak across generic content, and controls that opt out of the system's accessibility semantics.
When to Apply
- A SwiftUI diff, feature, or PR is about to merge and needs an objective PASS/FAIL, not advisory feedback.
- An agent (Claude, Codex) authored the views and you want an independent check that it is not reproducing pre-Observation idioms (
ObservableObject/@StateObject,.onAppear { Task { ... } },AnyViewrows,GeometryReader-to-measure) or identity-resetting conditionals (applyIfhelpers, container-type switches). - UIKit-era screens are being ported to SwiftUI and the new surface needs auditing against the framework's update mechanics (subview boundaries, minimal dependencies, cached derivations, stable identity).
- Accessibility and platform-convention compliance must be verified, not assumed — icon-only buttons, tap gestures posing as controls, primitives rebuilt where a style protocol exists, silent Canvas controls, hardcoded fonts, fixed spacing around text.
Do not apply to targets with no SwiftUI surface — server-side Swift, CLI tools, non-UI packages (the reviewer prompt's precondition aborts with "GATE NOT APPLICABLE"). General Swift language quality (concurrency structure, API design, control flow) is the sibling adversarial-swift gate's job, not this one's. Rules whose remedy needs a newer toolchain or deployment target than the project's are N/A, not FAIL — the reviewer prompt carries the version-gate table.
What ships with it
36 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/templates/verdict.md 2.1 KB
- gotchas.md 6.8 KB
- metadata.json 951 B
- references/_sections.md 4.2 KB
- references/access-button-not-ontapgesture.md 2.2 KB
- references/access-button-title-and-icon.md 2.6 KB
- references/access-representation-for-custom-controls.md 3.3 KB
- references/access-scaledmetric-custom-spacing.md 3.9 KB
- references/access-semantic-fonts-and-colors.md 2.6 KB
- references/access-style-protocols-for-custom-controls.md 3.3 KB
- references/anim-body-scoped-animation-in-generic-containers.md 2.8 KB
- references/anim-builtin-effects-over-custom-animatable.md 2.4 KB
- references/identity-anylayout-over-container-branches.md 3.1 KB
- references/identity-branch-free-modifier-helpers.md 3.5 KB
- references/identity-branch-in-modifier-not-around-view.md 4.0 KB
- references/list-constant-foreach-view-count.md 3.4 KB
- references/list-no-anyview-rows.md 2.9 KB
- references/list-no-geometry-feedback-loop.md 2.8 KB
- references/list-ongeometrychange-over-georeader.md 2.8 KB
- references/list-visualeffect-for-render-transforms.md 3.7 KB
- references/reviewer-prompt.md 6.3 KB
- references/state-callasfunction-env-closures.md 3.0 KB
- references/state-guard-task-id-model-reinit.md 2.6 KB
- references/state-no-highfreq-environment-values.md 3.3 KB
- references/state-no-initialvalue-from-params.md 2.4 KB
- references/state-observable-not-observableobject.md 6.0 KB
- references/state-own-models-in-state.md 3.4 KB
- references/task-concurrent-offload-cpu-work.md 5.5 KB
- references/task-id-for-async-state-reactions.md 2.5 KB
- references/task-modifier-not-onappear-task.md 2.7 KB
- references/task-scalar-ids-for-onchange.md 2.8 KB
- references/update-cache-expensive-derivations.md 5.2 KB
- references/update-no-large-structs-on-rows.md 6.1 KB
- references/update-no-side-effects-in-view-init.md 3.4 KB
- references/update-pass-minimal-data.md 4.1 KB
- references/update-subview-structs-not-computed-vars.md 6.1 KB
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 · 76 lines · 200 tokens per session scan A 5d9a1bf13afb
adversarial-swift-ui is a skill published in the GitHub repository pproenca/dot-skills (205 stars, last pushed 24d ago), licensed MIT. It adds 200 tokens to every session and 2,520 once invoked, about $0.0010 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 2026-08-30.
Other skills, from other repositories
accessibility-cleanup
Finds common violations of the Android accessibility API in the Clank App Java code and attempts to address them (e.g. hardcoded state change announcements, missing events, focus moving, assertive live regions, etc).
app-store-review
Evaluates code against Apple's App Store Review Guidelines. Use this skill when reviewing iOS, macOS, tvOS, watchOS, or visionOS app code (Swift, Objective-C, React Native, or Expo) to identify potential App Store rejection issues before submission. Triggers on tasks involving app review preparation, compliance…
swift-concurrency-pro
Reviews Swift code for concurrency correctness, modern API usage, and common async/await pitfalls. Use when reading, writing, or reviewing Swift concurrency code.
swiftui-pro
Comprehensively reviews SwiftUI code for best practices on modern APIs, maintainability, and performance. Use when reading, writing, or reviewing SwiftUI projects.
axiom-audit-camera
Use this agent to scan Swift code for camera, video, and audio capture issues including deprecated APIs, missing interruption handlers, threading violations, and permission anti-patterns.
mobile-platform-offline-validate
Review a Lightning Web Component for mobile offline compatibility — the Komaci offline static analyzer that pre-primes the data graph for Salesforce Mobile App Plus and Field Service Mobile App. Produces a finding list with code-level fixes covering inline GraphQL queries in @wire configurations, modern lwc:if /…