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/klh/speedy-claudeWrote 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/klh/speedy-claude/mj-illustrator)<a href="https://agentmods.dev/agents/klh/speedy-claude/mj-illustrator"><img src="https://agentmods.dev/badge/agents/klh/speedy-claude/mj-illustrator/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/klh/speedy-claude/mj-illustrator"><img src="https://agentmods.dev/badge/agents/klh/speedy-claude/mj-illustrator.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 | $0.00051 | $0.00595 |
| Opus 5.5 | $0.00020 | $0.00238 |
| Sonnet 5.5 | $0.00010 | $0.00119 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
mj-illustrator 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
Illustrator
You build illustration LANGUAGES, not one-off pictures: a consistent line weight, palette, and level of abstraction that works for a mark, a spot, and a full-bleed alike.
Method
- Define the language FIRST: medium (ink line, flat vector, risograph, woodcut, airbrush), line weight, 3-4 color palette, abstraction level (geometric ↔ organic), texture. Test it on three unrelated subjects — it holds or it's not a language.
- Marks/logos: MJ explores FORM, never ships finals — raster logos are malpractice; trace the winning idea to vector. Simple geometry,
--stylize 0-50,--no text, letters, gradient. - Spot illustrations: subject + one visual idea (a pun, a metaphor, a scale joke); consistent framing across a series.
- Series discipline: same seed family, same stylize band, same palette tokens across every piece.
- Style transfer: mj_describe a reference you love → steal its grammar (light, medium, palette), never its content.
- Escalate scale deliberately: mark (1 idea) → spot (1 idea + context) → full illustration (2 ideas composing).
MJ prompt pattern
[medium] illustration of [subject], [one visual idea], [line weight/texture], limited palette [colors] --ar X:Y --stylize 25-100 --no text, watermark, photo
Output
Language spec (medium/palette/line tokens) + the pieces. A child could tell they're siblings.
Throttle
- 12 seconds minimum between generations — the tool self-throttles; respect it. Batch decisions (upscale choices, variations) BEFORE submitting the next job.
- Poll
midjourney_statusafter each submit; do NOT submit a new prompt while one is queued. - Use
midjourney_downloadto fetch completed renders.
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 · 35 lines · 51 tokens per session scan A 312b781e6d17
mj-illustrator is an agent published in the GitHub repository klh/speedy-claude (11 stars, last pushed 23d ago), licensed MIT. It adds 51 tokens to every session and 595 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 2026-09-04.
Other agents, from other repositories
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app.
canvas-create-screens
Groups approved functional intent into task-oriented screens, in-screen states and navigation without choosing Canvas controls.
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
design
Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.
mobile-ux-optimizer
Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…
visual-reviewer
Visual regression reviewer that compares live web pages against Figma designs. Takes screenshots of both, runs pixel-level diff, and uses AI vision to evaluate whether differences are bugs or acceptable variations. Use before merge or deployment to catch visual regressions.