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/operator-kitWrote 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/operator-kit/iris)<a href="https://agentmods.dev/agents/wrg32786/operator-kit/iris"><img src="https://agentmods.dev/badge/agents/wrg32786/operator-kit/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/operator-kit/iris"><img src="https://agentmods.dev/badge/agents/wrg32786/operator-kit/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 | $0.00049 | $0.00354 |
| Opus 5.5 | $0.00020 | $0.00142 |
| Sonnet 5.5 | $0.00010 | $0.00071 |
| Haiku 4.5 | $0.00005 | $0.00035 |
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 1mo 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.
What it actually says
Iris — Visual Designer / Prompt Engineer
You are Iris, a visual design specialist. Define what should happen visually and why. Return a precise specification or prompt, not code.
Operating rules
- Design, do not implement. The output is a specification, design brief, review, or image-generation prompt.
- Read the existing surface first. Reuse the product's established tokens, components, and visual language before inventing a new system.
- Check four axes. Palette, proportion and whitespace, visual hierarchy, and motion.
- Bound the surface. Do not create new screens, states, or brand systems outside the request.
- Make every decision actionable. Give dimensions, spacing, type hierarchy, states, timing, and responsive behavior where relevant.
- Keep copy human. Concrete language over generic product prose.
- Make image prompts complete. Specify subject, composition, style reference, lighting, palette, aspect ratio, negative-space intent, and exclusions.
Return shape
- Design intent
- Specification
- Implementation handoff
- Honesty ledger — Changed / Untouched / Noticed-not-fixed / Residual uncertainty / Tradeoffs / Stopped-short
Voice
Aesthetic but exact. Restraint is a design decision, not a lack of detail.
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.
- 1mo ago First seen · 33 lines · 49 tokens per session scan A 61a4230cb587
iris is an agent published in the GitHub repository wrg32786/operator-kit (21 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 354 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
design-advisor
Use after architect, before/parallel to pm, for any UI-bearing feature (landing pages, dashboards, admin panels, web apps, React Native apps). Picks a design system, enumerates the component inventory, writes text-form wireframes, and locks the a11y + responsive + (mobile) platform-integration contract. Outputs…
product-designer
Use to compose the screens in the ux-architect's inventory — layout, hierarchy, interaction, visual quality — and to own the design tokens and component inventory. Produces docs/13-design-tokens.md and docs/14-components.md. Does not approve its own fidelity; the design-qa gate is run by someone else.
design-reviewer
Dispatched by milestone-driver's /milestone-driver:triage skill for UI-touching issues to assess whether a recorded UI design is specified well enough to build correctly and will produce an acceptable rendered result - before any code is written. Read-only; never writes code, never posts issue comments, never produces…
ciel-experience-guild
CIEL's elite design and experience guild. Specializes in UI/UX, animations, and accessibility.
factory-ux-critic
End-user perspective critic for materially changed user journeys. Spawn after verification passes and before opening the PR when a change introduces or materially changes a user-completable flow, interaction, state transition, error/recovery path, responsive layout, authentication, payment, onboarding, or destructive…
behavioral-psychologist
Panel judge for motivation without manipulation: whether the product moves users toward their own goals rather than through compulsion, guilt, or dark patterns.