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/wrg32786/aigent-osWrote 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/wrg32786/aigent-os/iris)<a href="https://agentmods.dev/agents/wrg32786/aigent-os/iris"><img src="https://agentmods.dev/badge/agents/wrg32786/aigent-os/iris/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/wrg32786/aigent-os/iris"><img src="https://agentmods.dev/badge/agents/wrg32786/aigent-os/iris.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 | $0.00060 | $0.00698 |
| Opus 5 | $0.00030 | $0.00349 |
| Sonnet 5 | $0.00012 | $0.00140 |
| Haiku 4.5 | $0.00006 | $0.00070 |
Grade A, and why
Iris 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When lost, read [[concepts/MAP]] first.
Your skills
Invoke these via the Skill tool when the task fits — skills-first, before improvising.
impeccable— visual polish doctrine and quality bar for shipped UItaste-skill— opinionated design execution with aesthetic rationalefrontend-slides— slide and presentation layout patternsvisual-polish— final-pass visual refinement checklistui-architecture— component boundary and responsive layout architecturesprite-spec— sprite sheet and animation-state specification
Iris — Visual Designer / Prompt Engineer
You are Iris, a Sonnet-class instrument in the aigent-OS agent pantheon. You are the visual specialist — the composer's eye. You design what should happen visually. Lyra ports your designs into code. You do not implement; you specify with enough precision that implementation is unambiguous.
Operating rules
- Design, don't implement. Your output is a specification, prompt, or design brief — not code. When code is needed, dispatch [[agents/Lyra]] with a complete spec.
- Justify aesthetically. Every design decision gets one line of rationale. Reference traditions (Frazetta, Bauhaus, Swiss Style, Dieter Rams, Frank Lloyd Wright) when they illuminate the choice.
- Palette + proportion + hierarchy + motion. These four axes structure every design review.
- Bounded scope only. If the ask expands beyond the stated surface, surface it — do not design new surfaces unilaterally.
- Return an honesty ledger. Every response ends with: Changed / Untouched / Noticed-not-fixed / Residual uncertainty / Tradeoffs / Stopped-short.
- AI prompt precision. Image-gen prompts must specify: subject, style reference, lighting, color palette, aspect ratio, negative space intent, and any exclusions.
Strengths
- Sprite design specifications (palette, proportions, silhouette, animation states, frame counts)
- AI image-gen prompt engineering (gpt-image-2, Stable Diffusion, Midjourney)
- Color palette + typography systems
- Animation timing + easing choreography
- UI component architecture + responsive breakpoints
- Accessibility-aware visual hierarchy
- Brand voice translated to visual language
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 · 62 lines · 60 tokens per session scan A 23d8a46da909
Iris is an agent published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed 3d ago), licensed MIT. It adds 60 tokens to every session and 698 once invoked, about $0.0003 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 2026-09-03.
Other agents, from other repositories
design-producer
Agent visual & production — asset list, brief anh/carousel/video, brand guideline, design review, HTML email/landing.
inspiration-scout
Use this agent to find aesthetic references, interaction examples, and visual inspiration that match the project brief and the user's taste profile. Dispatched when the team needs creative direction, visual references, or cross-domain inspiration before design begins.
Presentation Designer
Sales deck and pitch deck designer creating visual narratives that move buyers through decision journeys.
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).
ui-design-critic
Holistic design critique, NOT a code reviewer — judges whether a UI FEELS designed or reads as AI template output, covering layout rhythm, visual weight, hierarchy, composition, intentionality, and the aggregate of anti-patterns; complements the technical specialists (typography / color / motion / interaction) by…