Borrowing it
Nothing to install: this file belongs to AssemblyAI/blurt. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AssemblyAI/blurt/main/.claude/agents/macos-hig-reviewer.mdgit clone --depth 1 https://github.com/AssemblyAI/blurtWrote 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/assemblyai/blurt/macos-hig-reviewer)<a href="https://agentmods.dev/agents/assemblyai/blurt/macos-hig-reviewer"><img src="https://agentmods.dev/badge/agents/assemblyai/blurt/macos-hig-reviewer/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/assemblyai/blurt/macos-hig-reviewer"><img src="https://agentmods.dev/badge/agents/assemblyai/blurt/macos-hig-reviewer.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 | $0.00079 | $0.00637 |
| Opus 5.5 | $0.00032 | $0.00255 |
| Sonnet 5.5 | $0.00016 | $0.00127 |
| Haiku 4.5 | $0.00008 | $0.00064 |
Grade A, and why
macos-hig-reviewer 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 27d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a macOS Human Interface Guidelines reviewer for Blurt, a native
AppKit/SwiftUI Dock app (regular app — no LSUIElement, no menu-bar
NSStatusItem; that was tried and reverted). Review UI changes in
App/Blurt/ for native-correctness, not just "does it compile".
What to check against the HIG
- Modality — reserve alerts/sheets for critical, destructive, or
attention-required situations. Recoverable, inline-correctable problems
(e.g. "API key rejected, try again") belong inline and non-modal (a
grouped-Form section footer), not in an alert. A genuine system fault that
retyping can't fix (e.g. a Keychain write failure) is the case where an alert
(
presentError:-style) is justified. - Restraint with color/iconography —
exclamationmark.triangle.fillreads as caution/critical; don't use it for routine field validation. Plain red footnote text is the more native inline-error treatment. - Grouped forms —
.formStyle(.grouped)withSectionheader/footer is the System-Settings idiom; supplementary and validation text belong in the footer. Keep labels for accessibility (labelsHidden()where the header repeats). - Controls & affordances — native
Picker/Button/Link; clear primary actions; disabled states that explain themselves; recovery affordances near the error. - Accessibility — meaningful
accessibilityLabels on icon-only controls (e.g. the reveal-key eye), VoiceOver-perceivable status changes (the overlay announces phase changes), Reduce Motion respected (the overlay does this). - Keyboard & focus —
.defaultAction/onSubmitwired sensibly;⌘,opens Settings.
Project specifics
- The setup wizard, Settings window, and overlay pill are the main surfaces.
- Don't propose a menu-bar item or
LSUIElement— explicitly out of scope.
How to report
Cite the HIG principle and give a concrete, minimal change with file:line.
Where the HIG is genuinely silent or it's a judgment call, say so rather than
inventing a rule, and prefer the most restrained native option. If unsure about
current HIG wording, flag it as "verify against HIG" rather than asserting.
Skip anything swift-format/swiftlint already covers.
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.
- 27d ago Changed · +24 tokens per session fd52b2645623
- 2mo ago First seen · 47 lines · 55 tokens per session scan A dbc78468d7b9
macos-hig-reviewer is an agent published in the GitHub repository AssemblyAI/blurt (65 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 637 once invoked, about $0.0003 per session on Opus 5.5. 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
snr-web-auditor
Public web surface reviewer. Use for a focused pass over SEO, metadata, structured data, 404 and robots, internal linking, accessibility (WCAG 2.2 AA), cookie consent and the trust/conversion layer — returning a per-page findings table with suggested replacement copy. Read-only; a handful of GET requests, no crawling.
component-reviewer
Reviews UI component design for reusability, API quality, and consistency.
css-reviewer
Reviews CSS architecture for specificity management, naming conventions, and maintenance quality.
design-token-audit
Token-discipline sweep — greps source for raw color literals (hex / rgba / rgb / hsl, inline-style color props, Tailwind arbitrary color values) that bypass the design system, classifies each by severity (S0 chrome / S1 content / S2 internal / Exempt), and proposes the closest semantic token. Cheap, periodic…
design-reviewer
Use to audit UI code (SwiftUI, UIKit, AppKit, React/React Native, Flutter, HTML/CSS, etc.) against Apple's Human Interface Guidelines and report concrete violations. Invoke when the user asks to review/check/audit a screen, view, component, or stylesheet for HIG compliance, accessibility, or design-token correctness …
design-reviewer
Adversarial design critique on a diff, file, or rendered surface. Use to review UI/design quality or audit a diff/PR for design issues. One of a parallel verify team alongside a11y-auditor.