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 ngocsangyem/MeowKit --skill partygit clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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/ngocsangyem/meowkit/party)<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.
<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>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 | $0.00048 | $0.02632 |
| Opus 5 | $0.00024 | $0.01316 |
| Sonnet 5 | $0.00010 | $0.00526 |
| Haiku 4.5 | $0.00005 | $0.00263 |
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.
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:partyis for architectural trade-off deliberation.
Protocol
Execution model: Agents are simulated personas in the single orchestrator session — NOT real subagent spawns via the
Agenttool. 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), seemk: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 |
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 · 188 lines · 48 tokens per session scan A 439f7940cfd0
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.
Other skills, from other repositories
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
session-deep-dive
Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.
brainstorm
Brainstorm Elixir/Phoenix features — explore ideas, compare approaches, gather requirements. Use when vague idea, not sure how to approach, or want to discuss before plan.
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
plugin-dev-workflow
Guide plugin development workflow — editing skills, agents, hooks, or eval framework in this repo. Use when modifying files in plugins/elixir-phoenix/, lab/eval/, or lab/autoresearch/. Ensures changes pass eval, lint, and tests before committing.