Kiro Crew is a persistent development workspace where agents continue multi-step software work across sessions, schedules, and connected interfaces. Developers use it locally or remotely through a desktop app, web dashboard, CLI, Slack, or Discord, with unattended tasks and recurring jobs. The catalogue contains skills and instructions for working with this workspace.
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.
npx skills add kirodotdev/KiroCrew --skill image-authoringgit clone --depth 1 https://github.com/kirodotdev/KiroCrewWrote 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/skills/kirodotdev/kirocrew/image-authoring)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/image-authoring"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/image-authoring/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/skills/kirodotdev/kirocrew/image-authoring"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/image-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00045 | $0.01823 |
| Opus 5.5 | $0.00018 | $0.00729 |
| Sonnet 5.5 | $0.00009 | $0.00365 |
| Haiku 4.5 | $0.00005 | $0.00182 |
Grade A, and why
image-authoring 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 12d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Authoring
Create images by authoring them as code — there is no text-to-image model or image-generation tool in this environment. Use when the user says "generate/create/make an image", "draw", "illustrate", "picture of", "logo", "icon", "poster", "banner", "mascot", "sprite", "texture", "wallpaper", or asks to change/tune an image you made earlier.
HARD RULES
- Never look for an image-generation tool. None exists. You ARE the artist — author the image as code and save the file.
- Never present this as AI text-to-image generation. It is authored graphics. For photorealism requests, explain the output is stylized (vector / procedural art) and offer the closest achievable style.
- Never recreate from scratch when the user gives feedback. Update the brief, then make targeted edits to the existing source.
- Always keep the editable source. SVG is its own source; for raster output keep the generating script/HTML next to the image so it can be edited and re-run.
Workflow
1. Brief — summarize the context
Before authoring, compose a short brief from EVERYTHING relevant in the conversation (earlier descriptions, project context, corrections), not just the last message: subject, style, palette, mood, 2–3 signature details, size/aspect, output format. Echo it in one line — "Authoring: " — so the user can correct course before you draw.
2. Choose the technique
| Request | Technique |
|---|---|
| Illustration, character, logo, icon, scene, stylized art | SVG authoring (primary) |
| Poster, banner, card, meme, text-heavy composition | HTML/CSS → Playwright screenshot |
| Texture, gradient art, pixel art, noise, filters, compositing | Python + Pillow (raster) |
| Raster copy of an SVG (user needs .png) | Convert: rsvg-convert → inkscape → magick → Playwright screenshot |
| Flowchart, architecture, data chart | Prefer mermaid / widgets; else SVG or Pillow |
| Hand-drawn / whiteboard-style diagram, sketch aesthetic | Excalidraw scene — see below |
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.
- 12d ago Changed · +1 lines ebeac1533cfd
- 22d ago Changed · -1 lines f01acbaa33af
- 1mo ago Changed · +2 lines 07f36406460f
- 1mo ago Changed · +9 lines fb2ff168726b
- 1mo ago First seen · 129 lines · 45 tokens per session scan A 11fa3f86f903
image-authoring is a skill published in the GitHub repository kirodotdev/KiroCrew (4,496 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 1,823 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 skills, from other repositories
architecture-diagram
Dark-themed SVG architecture/cloud/infra diagrams as HTML.
concept-diagrams
Minimal SVG diagrams as standalone HTML files.
frontend-design
Create distinctive, production-grade frontend interfaces.
emil-design-eng
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
cliptalk-graphics-packager
Adds task-local graphic text layers such as title cards, top labels, product tags, price or parameter callouts, watermarks, and CTA overlays to an existing timeline.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.