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 agentmods add skills/kirodotdev/kirocrew/theme-pack-authoringnpx skills add kirodotdev/KiroCrew --skill theme-pack-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/theme-pack-authoring)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/theme-pack-authoring"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/theme-pack-authoring.svg" alt="Measured on agentmods" 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 | $0.00064 | $0.01672 |
| Opus 5 | $0.00032 | $0.00836 |
| Sonnet 5 | $0.00013 | $0.00334 |
| Haiku 4.5 | $0.00006 | $0.00167 |
Grade A, and why
theme-pack-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 2d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kiro Crew theme-pack authoring
House rules for building theme packs. The authoritative contract is
website/docs/theming-contract.md;
this skill is the self-contained task-oriented digest, plus the traps that cost
real debugging time.
Pack anatomy
my-theme/
├── theme.json # manifest: slug, name, emoji, level, formatVersion, fonts[]
├── variables.json # dark + light palettes (54 allowlisted CSS vars)
├── readme.md # optional; attribution and notes
├── styles/
│ ├── overrides.css # optional; scoped structural CSS (see allowlist below)
│ └── fonts/ # .woff2 / .ttf files, max 6 faces, 512 KB each
└── LICENSE.txt # validates as meta, is NOT copied into the install
Levels: 0 = colors only. 1 = + fonts, branding, overrides.css. 2 = + overlays/topbar/audio/persona. Declare the lowest level that covers the payload — a level-0 pack shipping a font is refused.
theme.json — complete working example
{
"slug": "my-theme",
"name": "My Theme",
"emoji": "🎨",
"level": 1,
"formatVersion": 1,
"fonts": [
{ "family": "My Sans", "file": "my-sans-400.woff2", "weight": 400, "role": "sans" },
{ "family": "My Sans", "file": "my-sans-500.woff2", "weight": 500, "role": "sans" },
{ "family": "My Sans", "file": "my-sans-600.woff2", "weight": 600, "role": "sans" },
{ "family": "My Mono", "file": "my-mono-400.woff2", "weight": 400, "role": "mono" }
]
}
Fonts — the role system (the ONLY supported route)
- Each face carries
role: "sans"or"mono". Absent role =sans. sansfaces feed the Sans Font Family option;monofaces feed Mono AND code surfaces (code blocks, inline code, diffs) under every option.- System always stays the OS font — a pack cannot reach it. Unfilled roles fall back to Kiro Crew's own stacks.
- Max 6 faces across both roles; pick weights deliberately. The UI uses
400/500/600/700; with 3 sans slots ship 400/500/600 (
font-boldresolves to 600, acceptable; 400/500/700 makes the many semibold elements render heavy). - CJK/Devanagari/Bengali fallbacks are wired automatically — the generated stacks carry the script-fallback aliases. Latin-only faces are fine.
- Never set fonts in overrides.css.
--font-body,--mono, the--theme-font-*tokens, orfont/font-familyonbody/html/*/:rootare rejected at install and dropped at runtime (CSS-escape evasions included). Afont-familyon ONE allowlisted surface (e.g..topbar) is fine. - Ship the font's license file in the pack source (OFL/Apache/MIT).
- Only
"sans"and"mono"are valid; a wrong role string (e.g. the CSS keyword"monospace") is rejected at install with an error naming the font and the bad value. An already-installed pack whose role predates this check keeps loading — the coercion-to-sansbehavior only remains on that read path, never on a fresh install.
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.
- 2d ago Changed e8a6169d49ab
- 5d ago First seen · 126 lines · 64 tokens per session scan A 4aee5a87bf3d
theme-pack-authoring is a skill published in the GitHub repository kirodotdev/KiroCrew (3,532 stars, last pushed 2d ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,672 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 2026-08-30.
Other skills, from other repositories
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
brandkit
Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional…
html-artifacts
Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for saveplan, outputiframe, or slackattachhtml.
minimalist-ui
Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.
skin-creator
Create and apply a two-asset LobsterAI visual skin from the user's style description. Use only when the AI Skin Designer kit supplies the structured skinpack workflow marker; do not use for ordinary theme or image requests.