Instructions for sending design-focused software tasks to the local Kimi Code command-line tool. It is intended for interface design, frontend work, repository exploration, review, and analysis of images or videos.

Use it for UI and UX critique, visual direction, design-system decisions, polished frontend implementation, repository work, and media-aware analysis.

It helps route visually demanding work to an agent suited to layout, typography, design systems, and frontend polish. The instructions also define how to provide files and inspect the agent's result.

kimi — Skill for Claude Code and Codex by oil-oil

Install

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.

Any agent

npx skills add oil-oil/kimi --skill kimi

Clone the repo

git clone --depth 1 https://github.com/oil-oil/kimi

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/oil-oil/kimi/kimi/github.svg)](https://agentmods.dev/skills/oil-oil/kimi/kimi)

Your own site

<a href="https://agentmods.dev/skills/oil-oil/kimi/kimi"><img src="https://agentmods.dev/badge/skills/oil-oil/kimi/kimi/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/oil-oil/kimi/kimi"><img src="https://agentmods.dev/badge/skills/oil-oil/kimi/kimi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,379 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00154	$0.01379
Opus 5	$0.00077	$0.00690
Sonnet 5	$0.00031	$0.00276
Haiku 4.5	$0.00015	$0.00138

Measured 9d ago against content hash 73ac85f599b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

kimi 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.

SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kimi

Core rules

Use scripts/ask_kimi.sh instead of invoking kimi -p directly. The wrapper captures Kimi's JSONL, streams compact progress, records the session ID, and writes a Markdown result.
Run the wrapper once per task. After success, read the reported output_path and inspect the workspace before deciding whether a follow-up is needed.
Give Kimi the goal, completion criteria, constraints, and non-obvious context. Keep delegated prompts focused, normally under 500 words.
Pass 1-4 useful entry points with --file; Kimi can discover the rest. File hints may point to code, images, or videos that Kimi can inspect with its local tools.
Treat Kimi as a design-strong coding Agent. Prefer it for UI/UX critique, visual direction, layout and typography decisions, design-system work, and polished frontend implementation.
Do not ask Kimi to generate or edit image assets. It can analyze screenshots, images, and videos and then express its design decisions as specifications or frontend code, but it cannot create the image itself. Use an image-generation or image-editing tool when the requested deliverable is an image.
Quote paths containing spaces, brackets, or shell metacharacters.
Do not mention this Skill or its wrapper implementation in the delegated prompt.

Host compatibility

Use this Skill from any Agent that can load SKILL.md instructions and execute a local shell command. The wrapper is host-agnostic: it communicates with Kimi Code through its CLI and does not call a host-specific API. agents/openai.yaml is optional metadata for OpenAI hosts; other Agents may ignore it.

Safety boundary

Kimi's non-interactive prompt mode uses its automatic permission policy and may edit files or run commands. Use it only in a trusted workspace and only when the user's request authorizes those changes.

kimi -p cannot be combined with Kimi's --plan flag and provides no filesystem sandbox for non-interactive prompt mode. Therefore, this wrapper intentionally has no --read-only option. For enforced no-write exploration, use interactive kimi --plan in the user's terminal or another sandboxed mechanism; do not describe a prompt-only instruction as a read-only guarantee.

Read the full file on GitHub · 123 lines

Changes

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 · 123 lines · 154 tokens per session scan A 73ac85f599b3

Subscribe to this mod's changes

kimi is a skill published in the GitHub repository oil-oil/kimi (23 stars, last pushed 1mo ago), licensed MIT. It adds 154 tokens to every session and 1,379 once invoked, about $0.0008 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.

Building agents Design and UX

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

kimi