kimchi

A guided product-planning skill that turns a raw idea into detailed documents ready for implementation. It uses expert personas to question decisions, define each major feature, and review the resulting plan before coding starts.

In plain words
What is it for?
Use it to investigate a product idea, define APIs and feature priorities, create one plan for each epic, prepare a build handoff, and audit the documents.
Why use it?
It exposes unclear requirements and contradictions early, when they are cheaper to fix than during development.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/chitransh-cj/kimchi/plugin
Any agent
npx skills add chitransh-cj/kimchi --skill plugin
Clone the repo
git clone --depth 1 https://github.com/chitransh-cj/kimchi

Made for: Claude Code, Codex.

Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,030 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00122 $0.02030
Opus 5 $0.00061 $0.01015
Sonnet 5 $0.00024 $0.00406
Haiku 4.5 $0.00012 $0.00203

Measured 2d ago against content hash 9309ba386869, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kimchi 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.

plugin/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

kimchi

Run a product from idea → build-ready docs by grilling the user, not flattering them. The user summons expert personas one at a time. Each persona interrogates the user in their domain until the idea is airtight, records what it learned, then hands off to the next. When the picture is complete, the personas jointly emit one build-ready EPIC doc per epic. An Auditor reviews the docs before any code is written (and again after the build) to catch flawed or contradictory decisions early.

The point is friction — a product that survives eleven experts trying to break it is worth building, and it's cheap to find out here.

Invoking this skill authorizes dispatching personas as subagents where the roster below marks them research-mode or cross-consulting calls for one; no further permission is needed.

How to invoke

/kimchi <persona> — summon one persona. Accepts full name, kebab-case, or acronym. Case-insensitive. Examples: product head, product-head, PH.

/kimchi — no argument. Print the how-to below, then walk the user through the lifecycle, summoning personas in order.

/kimchi generate — after enough personas have weighed in, produce the EPIC build docs (see "Generating the docs").

/kimchi audit — run the Auditor over the completed decisions.

Persona roster

Acronym Persona Role Mode
CF co-founder Ideation & brainstorming partner for high-level direction interactive
PH product-head World-class product lead; owns EPIC→STORY→TASK breakdown interactive
FB finance-bro All the numbers: market research + market size (global/US/India), share, cost, revenue research
ARCH architect Senior tech architect; key architectural decisions, complexity interactive
DG design-girl Head of design; theme, UX, design direction interactive
SM security-master Cybersecurity expert; threat model, security posture interactive
DO devops Scalability & deployment expert; deployment architecture for current scope interactive
LB legal-bro Head of legal; flags legal boundaries, gives sound compliant advice + risks interactive
TB tech-bro Lazy staff engineer; minimum code, locked project structure interactive
COO coo Chief of operations; splits product into cohorts and owns their execution interactive
AUD auditor Meta-reviewer; re-summons every persona to review final decisions interactive

Read the full file on GitHub · 159 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.

  1. 2d ago First seen · 159 lines · 122 tokens per session scan A 9309ba386869

Subscribe to this mod's changes

kimchi is a skill published in the GitHub repository chitransh-cj/kimchi (44 stars, last pushed 1mo ago), licensed MIT. It adds 122 tokens to every session and 2,030 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

agent-collaboration

Initialize and wait for VibeAround subagents in a multi-agent coding turn. Use when the user's message starts with "subagent=", especially "subagent=parallel".

jazzenchen/VibeAround · 39 tokens

va-preview

Start a live preview so the user can see your work in their browser or phone. Use after starting a dev server or creating HTML files. Only available when the VibeAround MCP server is connected.

jazzenchen/VibeAround · 43 tokens

va-md-preview

Preview a markdown file with beautiful GitHub-style rendering. Use after creating or updating markdown documents like README, docs, or reports. Only available when the VibeAround MCP server is connected.

jazzenchen/VibeAround · 42 tokens

vibearound

Hand over your current coding session so the user can continue the conversation on their phone or another device via any IM channel connected to VibeAround. Use when the user says "/vibearound handover", "hand over this session", "continue on my phone", or similar session transfer requests.

jazzenchen/VibeAround · 65 tokens

va-session

Resolve your current session ID for use with other VibeAround tools. Called by other skills that need session context (e.g. va-preview, vibearound handover).

jazzenchen/VibeAround · 38 tokens

hue

Meta-skill that generates new design language skills. Works on Claude Code and Codex. Use when the user says 'create a design skill', 'generate design language', 'new design system skill', 'design skill inspired by X', 'design skill from this screenshot', '/hue', or 'use hue'. Also triggers for 'remix my design skill'…

dominikmartn/hue · 84 tokens