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 OutlineDriven/odin-claude-plugin --skill ios-visual-reviewgit clone --depth 1 https://github.com/OutlineDriven/odin-claude-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/skills/outlinedriven/odin-claude-plugin/ios-visual-review)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/ios-visual-review"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/ios-visual-review/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/outlinedriven/odin-claude-plugin/ios-visual-review"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/ios-visual-review.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 | $0.00042 | $0.01171 |
| Opus 5 | $0.00021 | $0.00585 |
| Sonnet 5 | $0.00008 | $0.00234 |
| Haiku 4.5 | $0.00004 | $0.00117 |
Grade A, and why
ios-visual-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 3d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iOS visual review
Contract
| Field | Bound contract |
|---|---|
| Trigger | The user runs /ios-visual-review. |
| Authority | Reversible local: writes only the named review-report artifact; rollback is undo. No remote mutation. |
| Side effect | Local-write to iOS screen visual-review findings (one Markdown report file). |
| Done | An iOS visual-review report is produced. |
Inputs
- A running read-only iOS observation session against a real device or simulator, exposing screenshot capture and an accessibility-tree element query. Required; the skill does not start or mutate the session.
- The set of screens to review. Optional: if omitted, discover screens from the accessibility tree and confirm the discovered set before scoring.
- A project DESIGN.md or equivalent design-intent document. Optional: when present, evaluate against it in addition to Apple HIG; when absent, evaluate against HIG and general iOS design practice only.
Procedure
- Acquire read-only access to the observation session. Issue no mutating calls to the device or app.
- Determine the screen set. Use the user-supplied list when provided; otherwise, enumerate screens from the accessibility tree and confirm the set with the user before proceeding.
- For each screen in the set:
- Capture a screenshot.
- Query the accessibility tree for elements.
- Score each of the ten dimensions below 0-10 and state what would push the score to 10.
- Record concrete findings tied to the screenshot.
- Apply the ten-dimension rubric:
- Typography hierarchy. Display, body, and caption sizes follow the Apple HIG dynamic-type scale on SF Pro. Line-height matches font size. No undersized body text.
- Spacing rhythm. A 4pt or 8pt grid is applied consistently. No unexplained magic paddings. Safe-area insets are respected.
- Color hierarchy. The primary action carries the highest contrast; secondary actions are muted; destructive actions are visually distinct. Dark mode renders correctly. Body text meets WCAG AA 4.5:1 and large text 3:1.
- Touch targets. Every interactive element is at least 44x44pt. No tappable text smaller than 24pt.
- Loading, empty, and error states. Each is present and intentional. No blank screens during async work. Empty states tell the user what to do next.
- Accessibility. VoiceOver labels exist on every interactive element. Dynamic Type up to XXL does not break layouts. Reduce Motion is respected. The palette is checked against deuteranopia.
- Animation discipline. No more than two simultaneous animations. UI feedback durations land in 200-300ms. Spring damping matches the seriousness of the flow.
- iOS idiom alignment. Native components (NavigationStack, List, Form, system sheets) are used where appropriate. Navigation is not reinvented. No web-style hamburger menus on phone.
- Information density. Per-screen content fits without horizontal scroll. Long screens carry section anchors. Lists use real iOS list patterns (swipe actions, contextual menus).
- AI-slop check. No generic stock layouts, leftover placeholder data, cargo-culted Material Design imported from Android, or gradients that read as AI-generated.
- For every dimension scoring below 7 on any screen, surface the issue with a recommended fix and its tradeoff and let the user decide whether to address it. Do not auto-apply fixes.
- Write the report artifact described under Output. Done when: every reviewed screen has ten scores, concrete findings, and one highest-impact fix per dimension, while unscored screens carry their blocker.
What ships with it
1 file 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.
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.
- 3d ago First seen · 55 lines · 42 tokens per session scan A 7c540beb5231
ios-visual-review is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 42 tokens to every session and 1,171 once invoked, about $0.0002 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 2026-09-06.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…