A writing tool for creating articles for Brunch, a Korean publishing platform. It follows Brunch's language, style, length, and formatting rules for technical blog posts.

Use it to draft Korean technical articles from a project brief, links, screenshots, metrics, code examples, or launch details.

It helps turn technical material into a draft that fits Brunch without having to learn the platform's publishing conventions yourself.

brunch — Skill for Claude Code and Codex by kakutixyz-ai

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 kakutixyz-ai/agent-publishing-skills --skill brunch

Clone the repo

git clone --depth 1 https://github.com/kakutixyz-ai/agent-publishing-skills

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/kakutixyz-ai/agent-publishing-skills/brunch/github.svg)](https://agentmods.dev/skills/kakutixyz-ai/agent-publishing-skills/brunch)

Your own site

<a href="https://agentmods.dev/skills/kakutixyz-ai/agent-publishing-skills/brunch"><img src="https://agentmods.dev/badge/skills/kakutixyz-ai/agent-publishing-skills/brunch/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/kakutixyz-ai/agent-publishing-skills/brunch"><img src="https://agentmods.dev/badge/skills/kakutixyz-ai/agent-publishing-skills/brunch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 655 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 83% copy Near-identical to another mod 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	$0.00000	$0.00655
Opus 5.5	$0.00000	$0.00262
Sonnet 5.5	$0.00000	$0.00131
Haiku 4.5	$0.00000	$0.00065

Measured 2mo ago against content hash 8ff91e7fdd32, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

brunch 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 2mo 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.

Origin

This is a copy

83% identical to a-list-apart — 34 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/platform-writers/brunch/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

name: writer-platform-brunch description: Write platform-specific drafts for Brunch (https://brunch.co.kr) using its dedicated language, length, tone, format, and community rules.

Brunch (https://brunch.co.kr) Writer

Use this skill when the target platform is brunch / Brunch (https://brunch.co.kr). This is the platform-specific writing capability for that website, not a generic adapter.

Knowledge To Load

knowledge/platforms/brunch.md
skills/adapter-technical-blog/SKILL.md
knowledge/styles/technical-blog.md
templates/base/article.md
templates/platforms/brunch/ when a platform override template exists
knowledge/rules/anti-spam.md
knowledge/rules/no-auto-publish.md
knowledge/rules/disclosure.md
knowledge/rules/factual-accuracy.md

Inputs

Project brief matching schemas/project-brief.schema.json, or a base draft matching schemas/platform-draft.schema.json.
Any user-provided assets, links, screenshots, metrics, code snippets, or launch details.

Platform Binding

Platform slug: brunch
Recommended adapter: adapter-technical-blog
Primary language code: ko
Categories: technical-blog
Target audience: developers

Writing Contract

Load knowledge/platforms/brunch.md first and treat it as the source of truth for this website.
Extract the site's required language, regional spelling, expected length, tone, accepted content shapes, formatting conventions, required assets, and banned patterns.
Use adapter-technical-blog only as a helper pattern. If the generic adapter conflicts with brunch, the platform profile wins.
Match the site's expected content length. Short-post platforms must stay short; long-form editorial or tutorial platforms must provide enough depth, evidence, and structure.
Match the site's voice. Preserve literary, technical, formal, skeptical, educational, founder-led, visual, or community-native tone when the profile asks for it.
Use only facts from the brief, base draft, loaded knowledge, templates, and user-provided materials. Do not invent URLs, metrics, version numbers, names, screenshots, testimonials, or claims.
Include required placeholders only when a platform field is mandatory but the fact is missing, and set status to needs_review.
Remove content types listed as poor fit for this platform. If the project is fundamentally unsuitable, return a needs_review draft explaining the fit problem instead of forcing a post.
Do not publish or imply that publication has happened.

Read the full file on GitHub · 56 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.

2mo ago First seen · 56 lines · 0 tokens per session scan A 8ff91e7fdd32

Subscribe to this mod's changes

brunch is a skill published in the GitHub repository kakutixyz-ai/agent-publishing-skills (2 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 655 tokens. A static security scan graded it A with 0 findings. It is 83% identical to a-list-apart, differing in 34 lines, and is treated as a copy.

Writing and docs

brunch next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
brunchkakutixyz-ai/agent-publishing-skills	Skill	2	5mo ago	MIT	A	0	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	4d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex