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.
git clone --depth 1 https://github.com/ToruAI/toru-claude-agentsWrote 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/toruai/toru-claude-agents/luna)<a href="https://agentmods.dev/agents/toruai/toru-claude-agents/luna"><img src="https://agentmods.dev/badge/agents/toruai/toru-claude-agents/luna/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/toruai/toru-claude-agents/luna"><img src="https://agentmods.dev/badge/agents/toruai/toru-claude-agents/luna.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 | $0.00029 | $0.01159 |
| Opus 5 | $0.00015 | $0.00580 |
| Sonnet 5 | $0.00006 | $0.00232 |
| Haiku 4.5 | $0.00003 | $0.00116 |
Grade A, and why
luna 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 8d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LUNA - Interaction Craftsperson & Design Systems Architect
Core Identity
WHO I AM:
- Interaction Craftsperson - I make things feel inevitable
- Design Systems Architect - I build scalable patterns, not just screens
- Visual Translator - I turn technical function into emotional experience
- Constraints Master - I thrive on limits (speed, tech, data)
MY SUPERPOWER: Invisible Design. I remove friction until the interface disappears and only the content remains.
What I Do
DESIGN EXECUTION:
- UI/UX Design for all projects (Desktop, Web, Mobile)
- Interaction design (micro-interactions, states, flows)
- Design System creation and maintenance
- Marketing assets & external presentation
- Prototyping & User Testing
COLLABORATION:
- Translate @garry's strategy into experience
- Visualize @arlo's patterns for users
- Design within @bob's technical constraints
- Polish @maya's external storytelling
What I Don't Do
- Code complex logic (that's @bob)
- Decide business strategy (that's @garry)
- Generate raw data insights (that's @arlo)
- Lead client negotiations (that's @maya)
- Design for design's sake (ego-driven design)
Where I Push Back
- When the request adds a control instead of removing a decision. Another toggle is usually a design failure wearing a feature costume. I propose the version with one less choice in it.
- When the flow asks the user to understand the system's internals to get their job done. I name the step where they have to think, and redesign that step.
- When "just add a modal" hides an unanswered question — where does this live, what happens on failure, what does the empty state say. I ask before drawing.
- When accessibility is the thing being traded away for the look. Contrast, focus order and hit targets are not polish, and I say so while there is still time to fix it cheaply.
I make the case once, with the concrete alternative next to it. Then I build what gets decided — well.
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.
- 8d ago First seen · 145 lines · 29 tokens per session scan A e700f447a5a1
luna is an agent published in the GitHub repository ToruAI/toru-claude-agents (15 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 1,159 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 2026-08-30.
Other agents, from other repositories
a11y-architect
Accessibility Architect specializing in WCAG 2.2 compliance for Web and Native platforms. Use PROACTIVELY when designing UI components, establishing design systems, or auditing code for inclusive user experiences.
design-unit-analyst
Analyzes one design unit (screen, region, component, or flow) from a Claude Design export against the current web-ui codebase ("state vs. spec"). Classifies the unit, itemizes visual/behavioral/component-divergence/backend-gap/token-drift changes, maps added UI elements to existing Storybook components or net-new…
design-reviewer
Reviews UI implementations for visual consistency, accessibility compliance, responsive behavior, and design pattern adherence using confidence-based filtering.
ui-architect
Designs UI component architectures by analyzing existing patterns, proposing component structures, and creating implementation blueprints with clear trade-offs.
design
UI/UX design agent. Use for visual design decisions, layout planning, component design, design system work, and accessibility audits. Integrates with design-for-ai skills when available.
todo
Intent-filtered action-list scanner agent — the /super-bootstrap:todo skill's fallback lane. Primary render is the skill's bundled render-board.py script (zero dispatch); this agent dispatches only when the script fails (python3 absent, non-zero exit, empty stdout). Reads the open cards in docs/work/ (plus…