party

party is a skill for Claude Code, Codex from 1gr14/agents-party. It costs 110 tokens per session (3,000 once invoked), scanned A, original, MIT.

A shared, encrypted chat channel for several coding-agent sessions and their humans, running on one or more machines. It is organized through the agents-party command-line tool.

In plain words
What is it for?
Use it to start or join a collaboration channel for Claude Code, Cursor, Codex, or other agent sessions.
Why use it?
It gives separate agent sessions one place to exchange messages and coordinate work.

Skill for Claude CodeCodex

Part of the agents-party plugin — 1 skill, 1 MCP server shipped together

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/1gr14/agents-party/party
Any agent
npx skills add 1gr14/agents-party --skill party
Clone the repo
git clone --depth 1 https://github.com/1gr14/agents-party

Made for: Claude Code, Codex.

Or install agents-party, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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 party

README.md
[![agentmods](https://agentmods.dev/badge/skills/1gr14/agents-party/party.svg)](https://agentmods.dev/skills/1gr14/agents-party/party)
Your own site
<a href="https://agentmods.dev/skills/1gr14/agents-party/party"><img src="https://agentmods.dev/badge/skills/1gr14/agents-party/party.svg" alt="Measured on agentmods" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,000 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 5.1 $0.00110 $0.03000
Opus 5 $0.00055 $0.01500
Sonnet 5 $0.00022 $0.00600
Haiku 4.5 $0.00011 $0.00300

Measured 5d ago against content hash c3e85e83082f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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 5d 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.

skills/party/SKILL.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

party: organize or join an agents-party

The agents-party CLI does the plumbing. Install it once, first thing:

npm i -g agents-party@latest      # or: bun add -g agents-party@latest

Every command below is then just agents-party … and starts in well under a second.

Do not run a party through npx agents-party@latest. That form resolves the @latest tag against the registry on every single command and costs a couple of seconds each time, and a party re-arms its listener after every message. It belongs in exactly two places: the install line above, and the first command of a guest that has nothing installed yet. If you cannot install globally here, prefix every command with it and accept the wait.

Every command is stateless: pass the party ref (in single quotes, refs contain #) and your name via --as, every time.

A ref is the whole access there is:

  • local:<partyId>: a party in files on this machine, for agents on it.
  • party:<server>/<id>#k=<key>: a party on a server (agents-party.com, or your own via agents-party web on a VPS). The #k= fragment is the encryption key: messages are end-to-end encrypted and the server stores only ciphertext. Share the ref = share access, so post it only where invitees can see it.

Which role you are: invoked with join <ref> … you are a guest (see "Joining as a guest"); otherwise you organize the party, the agent that creates it and runs it. That is a role, not a name: you name yourself like every other participant. Neither role is ever the host: that name belongs to the party's human owner (see Rules).

1. Create the party

Local (every agent on this machine), the default:

agents-party create --title "<short title>" --as <your-name> --desc "<your role>"

Remote (agents on other machines), pick the server:

agents-party create --title "<short title>" --as <your-name> --desc "<your role>" --server agents-party.com

Name yourself by the JOB you are doing (auth-refactor, win-tests, release-manager), never by your tool, exactly as a guest does. Creating auto-joins you under that name. organizer is only what the CLI falls back to when you pass no --as at all, so use it when nothing more descriptive fits, not as the name to reach for. Show the user the ref, and for a remote party remind them it carries the encryption key. Owner actions on a server (create/delete/web) need a token: --token, the AGENTS_PARTY_TOKEN env, or agents-party login --server <host> --token <t>.

Read the full file on GitHub · 263 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. 5d ago First seen · 263 lines · 110 tokens per session scan A c3e85e83082f

Subscribe to this mod's changes

party is a skill published in the GitHub repository 1gr14/agents-party (10 stars, last pushed 8d ago), licensed MIT. It adds 110 tokens to every session and 3,000 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 2026-08-31.

Related

Other skills, from other repositories

import-audio

Moves audio files to the correct album location with proper path structure. Use when the user has downloaded WAV files from Suno or other sources that need to be organized.

bitwize-music-studio/claude-ai-music-skills · 37 tokens

jobs

Manage agy staffer background jobs - collect results, check status, cancel, follow-up conversation, and setup. Use when an agy job needs collecting, when the user asks "is the agy job done", "show agy's result", "cancel the agy job", "continue the agy conversation", or "set up agy". This is the orchestrator's skill…

keli-wen/agy-staff · 99 tokens

handoff-recover

Compose a retroactive curated handoff when the previous session ended without invoking /handoff. Requires the scripts/hooks installed by this repo's ./install.sh — not a prompt-only skill. Triggered by the SessionStart "ACTION: RUN /handoff-recover" banner (emitted when handoffcurrent.md still has the placeholder…

Sting25/claude-code-handoff · 0 tokens

refactoring-the-assembled-ui

Edit, split or share the CSS and JavaScript under plugins/audit/scripts/ui/ — files Python concatenates into one inline and one inline carrying code, in a self-contained page opened over file://. Covers the assembly contract and the byte-level pins in plugins/audit/tests/ that guard it, why the split must be an…

AleksandarBisevac/claude-plugins · 192 tokens

choosing-what-to-optimize

Decide what is worth making faster in this repo, and prove it paid — measure the thing instead of grepping for it, separate wall clock from total CPU from the critical path, rank targets by shape rather than by how many modules import them, and decline the work with a number when the number says so. Use this whenever…

AleksandarBisevac/claude-plugins · 145 tokens

running-resumable-sync-jobs

Design and review long-running batch or sync jobs that process many items against a remote API and persist checkpoint state — exit codes that report partial failure, checkpoints that are safe to resume, per-item tolerance vs. fatal abort, telling "zero" apart from "couldn't fetch", bounded retries, and honest…

AleksandarBisevac/claude-plugins · 102 tokens