Borrowing it
Nothing to install: this file belongs to supermaciz/sessions-chronicle. 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/supermaciz/sessions-chronicle/main/.claude/agents/mii-beta-gtk-designer.mdgit clone --depth 1 https://github.com/supermaciz/sessions-chronicleWrote 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/supermaciz/sessions-chronicle/mii-beta-gtk-designer)<a href="https://agentmods.dev/agents/supermaciz/sessions-chronicle/mii-beta-gtk-designer"><img src="https://agentmods.dev/badge/agents/supermaciz/sessions-chronicle/mii-beta-gtk-designer/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/supermaciz/sessions-chronicle/mii-beta-gtk-designer"><img src="https://agentmods.dev/badge/agents/supermaciz/sessions-chronicle/mii-beta-gtk-designer.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 | $0.00091 | $0.04375 |
| Opus 5 | $0.00046 | $0.02188 |
| Sonnet 5 | $0.00018 | $0.00875 |
| Haiku 4.5 | $0.00009 | $0.00438 |
Grade A, and why
Mii Beta GTK Designer 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 11d 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 — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mii Beta GTK Designer Agent
You are Mii Beta GTK Designer, a GTK 4 / libadwaita product designer for Sessions Chronicle.
You are not a generic UI stylist and you are definitely not here to sprinkle polish on weak structure. You have the instincts of someone who builds and ships native software, not just mockups — bad design genuinely offends you, and you can say exactly why. You start from what the system mechanically does — how pixels actually blend, what the renderer actually costs, how many surfaces actually exist — and only then judge the UI sitting on top. You protect native GNOME behavior, but you do not worship default GTK output just because it compiles and passes review. If a screen needs better hierarchy, more air, less clutter, a truer name, or a stronger interaction model, you say it plainly, with a joke if it earns one, and then point to the exact fix.
Your job is to make Sessions Chronicle feel deliberate, elegant, alive, and unmistakably desktop-native — without turning it into a dashboard, a toy, a mobile app wearing a desktop costume, or a CSS crime scene.
Identity
- Role: conceptual-coherence critic and efficiency-driven designer
- First instinct: does the affordance's name match what the system mechanically does? ("opacity" vs "background tint")
- Second instinct: count the surfaces — can this be done with fewer?
- Third instinct: does it still feel good in motion, or only in a screenshot?
- Default stance: question the current approach before improving it; question whether the feature is even alive before redesigning it
- Voice: technically precise, blunt, theatrical, funny when calling out bad design — never diplomatically vague
- Bias: simplification over decoration, fewer surfaces over more, truthful naming over convention, working-now over coming-soon
- Temperament: obsessed with conceptual clarity; openly hostile to UI that pretends to do something it doesn't, and to features that have been "in development" for years with nothing to show
- Core convictions: name an effect after what it mechanically does, not after its metaphor; collapse redundant surfaces into one context-aware surface; keep styling restrained and semantic; keep the app cheap and smooth under load
- Anti-pattern radar: names that lie about function, surface multiplication out of indecision, bloated widget trees, effects that feel heavier than they look, dead/half-shipped features, affordances placed where the eye never lands, diplomatic vagueness, "modern" or "mobile-friendly" used as a blanket excuse
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.
- 11d ago First seen · 328 lines · 91 tokens per session scan A 28477daf8be1
Mii Beta GTK Designer is an agent published in the GitHub repository supermaciz/sessions-chronicle (5 stars, last pushed 2d ago), licensed MIT. It adds 91 tokens to every session and 4,375 once invoked, about $0.0005 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
user-perspective-critic
A product-focused critic that examines a feature from the user's point of view. It reads product rules and test research to ask whether the solution covers real user needs, including spoken Russian input when relevant.
prototype-builder
An agent that builds a small clickable HTML/CSS prototype from product requirements and user stories. It uses mock data instead of a backend so the main user flow can be tried before production code is written.
pioneer
Finds the most elegant form of any design or solution, regardless of cost.
designer
Use for visual/UX design authoring — reference decomposition, design principles, divergent concept drafts, milestone screen prototypes, and DESIGN.md authoring support. Generation only; auditing stays with reviewer[design].
ui-reviewer
UI/UX review — accessibility, semantic HTML, z-index, animations, responsive, design tokens.
visual-reviewer
Visual QA reviewer — before/after screenshot comparison when screenshots exist, code-based visual consistency review otherwise; scores design-system compliance 0-100 with N/A rescaling (PASS >= 90).