mk:party

mk:party is a skill for Claude Code from ngocsangyem/MeowKit. It costs 48 tokens per session (2,632 once invoked), scanned A, original, MIT.

A multi-agent discussion workflow for architecture decisions and trade-off analysis. It brings different specialist perspectives, such as development, security, testing, and design, into one structured conversation.

In plain words
What is it for?
Discussing architecture options, weighing security and user-experience trade-offs, reviewing large refactors, and brainstorming with several technical viewpoints.
Why use it?
It helps expose design flaws and competing concerns before code is written. This is useful when choosing between approaches or reviewing a change that affects many parts of a system.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

Good fit Discussing architecture options, weighing security and user-experience trade-offs, reviewing large refactors, and brainstorming with several technical viewpoints.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ngocsangyem/meowkit/party
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 ngocsangyem/MeowKit --skill party
Clone the repo
git clone --depth 1 https://github.com/ngocsangyem/MeowKit

Made for: Claude Code.

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.

agentmods badge for mk:party

README.md
[![agentmods](https://agentmods.dev/badge/skills/ngocsangyem/meowkit/party/github.svg)](https://agentmods.dev/skills/ngocsangyem/meowkit/party)
Your own site
<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/party"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/party/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.

agentmods 80×15 button for mk:party

Your own site · 80×15
<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/party"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/party.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,632 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.02632
Opus 5 $0.00024 $0.01316
Sonnet 5 $0.00010 $0.00526
Haiku 4.5 $0.00005 $0.00263

Measured 9d ago against content hash 439f7940cfd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mk:party 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.

.claude/skills/party/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Party Mode — Multi-Agent Collaboration

Bring multiple agent perspectives into one room. Agents debate, challenge, and build on each other's ideas to catch design flaws before code exists.

Required Agents

This skill orchestrates discussion among existing agent definitions. The following must exist under .claude/agents/ (per agent-routing.md):

architect, developer, security, tester, reviewer, ui-ux-designer, analyst, planner, researcher

If a referenced agent is missing, fall back to the Default row in "1. Agent Selection". Never silently skip a topic-mapped agent without falling back — the discussion loses its challenge dimension.

When to Use

  • Architecture trade-offs ("REST vs GraphQL?", "monolith vs microservices?")
  • Security vs UX trade-offs ("session timeout: 5min or 24hr?")
  • Large refactors that touch many files (risk assessment)
  • Brainstorming with domain expertise

For dedicated retrospectives, use mk:retro. mk:party is for architectural trade-off deliberation.

Protocol

Execution model: Agents are simulated personas in the single orchestrator session — NOT real subagent spawns via the Agent tool. The per-round token caps (150 / 175 / 100) are enforced by the orchestrator generating each response in-context. For real parallel multi-session work (separate context windows, worktree isolation), see mk:team-config.

1. Agent Selection

Based on topic keywords, select 2-4 agents:

Topic Signals Agents Selected
architecture, design, system, scale architect + developer + planner
security, auth, token, session, encrypt security + developer + planner
UI, UX, design, responsive, accessible ui-ux-designer + developer + planner
test, coverage, TDD, quality tester + developer + reviewer
performance, latency, optimize, cache architect + developer + analyst
refactor, migration, breaking change architect + developer + reviewer
sprint, retro, what went wrong planner + developer + tester + reviewer
Default (no keyword match) planner + architect + developer

Read the full file on GitHub · 188 lines

Files

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.

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. 9d ago First seen · 188 lines · 48 tokens per session scan A 439f7940cfd0

Subscribe to this mod's changes

mk:party is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 2,632 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories