Kilo Code is an open-source AI coding agent that works inside VS Code and JetBrains, from the command line, or through cloud services. Developers use it to build software with AI models, switch between providers, and run cloud agents or automated code reviews. The catalogue includes eleven skills, eight agents, and one instruction for Kilo Code.
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 Kilo-Org/kilocode --skill icon-jetbrainsgit clone --depth 1 https://github.com/Kilo-Org/kilocodeWrote 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/kilo-org/kilocode/icon-jetbrains)<a href="https://agentmods.dev/skills/kilo-org/kilocode/icon-jetbrains"><img src="https://agentmods.dev/badge/skills/kilo-org/kilocode/icon-jetbrains/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/kilo-org/kilocode/icon-jetbrains"><img src="https://agentmods.dev/badge/skills/kilo-org/kilocode/icon-jetbrains.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- 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 | $0.00023 | $0.03572 |
| Opus 5 | $0.00012 | $0.01786 |
| Sonnet 5 | $0.00005 | $0.00714 |
| Haiku 4.5 | $0.00002 | $0.00357 |
Grade A, and why
icon-jetbrains 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 9d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IntelliJ Platform New UI Icons
Guidance for authoring SVG icons for the JetBrains plugin. This skill is the single source of truth for icon sizing, palette, dark variants, composition rules, and placement. Other docs (including packages/kilo-jetbrains/AGENTS.md) defer here for SVG authoring details.
Icons follow IntelliJ New UI conventions: a fixed canvas per role, a strict light/dark palette, and explicit per-shape colors (the IntelliJ SVG loader recolors by matching literal hex values, so currentColor and CSS do not work). The plugin loads icons directly from its resource folder — see Where the SVGs live.
Golden rules
- Always ship two SVGs — one for the light theme (e.g.
add-file.svg) and one for the dark theme with the_darksuffix (add-file_dark.svg). Geometry must be identical between them; only the palette swaps.- Tool-window icons ship as a quartet, not a pair. When a tool window has both a 16×16 base (
name.svg/name_dark.svg) and a 20×20 stripe variant ([email protected]/name@20x20_dark.svg), they must share the same metaphor. The stripe is only one surface — the 16×16 base also appears in Search Everywhere, Find Action, context menus, the Services tool window, recent locations, and the View ▸ Tool Windows menu. Changing only the @20x20 leaves users seeing two different icons for the same tool window depending on where they encounter it. Always update all four files together (this repo's tool-window quartet iskilo.svg/kilo_dark.svg+[email protected]/kilo@20x20_dark.svg).
- Tool-window icons ship as a quartet, not a pair. When a tool window has both a 16×16 base (
- Only use colors from the canonical palette. See palette.md. Picking a one-off color breaks theming and contrast.
- One canvas size per icon role. See Icon roles. Do not invent new sizes or pad with empty space — IntelliJ scales the canvas as a single unit.
- No raster, no gradients, no filters, no embedded fonts. Path geometry only (
<path>,<rect>,<circle>,<line>,<polyline>,<polygon>). Text must be converted to outlines. - Use
fill="none"on the root<svg>and setfill/strokeexplicitly per shape — never rely on CSS orcurrentColor. - Strokes use
stroke-width="1",stroke-linecap="round",stroke-linejoin="round"(orstroke-miterlimit="10"for hard joins). Heavier strokes are reserved for hero glyphs inside a circle badge (e.g. status checkmarks) and usestroke-width="1.5"or"2". The1applies to the primary glyph stroke — do not force every stroke to 1. Hairline/decorative strokes (e.g. a thin stroke used to fatten a filled dot) and strokes whose width is coupled to geometry (e.g. a badge ring meant to sit flush with a fill edge) must keep their intended weight (scale with the artwork), or they fatten and misalign. - Pixel-grid align: keep stroke axes on half-pixel centers (
x.5) and fills on whole pixels so the icon stays crisp at 1× rendering. Getting the base grid right also keeps it crisp on HiDPI/Retina; fine sub-pixel detail blurs at fractional scales (125%/150%), so keep geometry simple rather than chasing detail that won't survive scaling. SVGs are resolution-independent — ship one vector per theme, never@2xraster variants. - File names use kebab-case and stay ASCII-only (e.g.
arrow-down-to-line.svg,book-open-check.svg,[email protected]), matching every existing icon inpackages/kilo-jetbrains/frontend/src/main/resources/icons/.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 138 lines · 23 tokens per session scan A a1f378e73fda
icon-jetbrains is a skill published in the GitHub repository Kilo-Org/kilocode (27,218 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 3,572 once invoked, about $0.0001 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
theme-factory
Create new AiderDesk UI themes by defining SCSS color variables, registering theme types, and adding i18n display names. Use when adding a theme, creating a color scheme, customizing appearance, or implementing dark mode and light mode variants.
data-viz
Act as a Senior Data Visualization Designer for dashboards, analytics pages, and chart-driven UI built in Recharts / visx / D3 / Plotly — chart-type decision tree, dashboard layout heuristics, color-blind safe palettes, empty/loading/error states, library trade-offs. For a one-off chart or plot, prefer a…
motion-designer
Act as a Senior Motion Designer to specify and ship purposeful UI animation — micro-interactions, transitions, scroll-driven sequences, page transitions, loading states. Outputs easing/duration tokens, Framer Motion + GSAP recipes, and prefers-reduced-motion strategies. For implementing with the Motion/Framer Motion…
a11y-auditor
Act as a Senior Accessibility Engineer to audit a page, component, or design against WCAG 2.2 AA. Produces a triaged finding list (critical/serious/moderate), focus-order map, contrast report, ARIA decision tree, and a screen-reader test plan. Use when shipping new UI, hardening an existing flow, or preparing for…
enterprise-design
Produce a comprehensive technical blueprint for a web product or SaaS, suitable for implementation in Figma Make, engineering sprints, and cloud deployment.
figma-translator
Translate any technical specification into five precise, self-contained Figma Make prompts ready to paste and generate. Use when you have an enterprise-design, visual-system-architect, or copywriting output and need to convert it into Figma Make–compatible prompts covering hero, features, social proof, CTA, and mobile…