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 1gr14/agents-party --skill partygit clone --depth 1 https://github.com/1gr14/agents-partyWrote 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/1gr14/agents-party/party)<a href="https://agentmods.dev/skills/1gr14/agents-party/party"><img src="https://agentmods.dev/badge/skills/1gr14/agents-party/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/1gr14/agents-party/party"><img src="https://agentmods.dev/badge/skills/1gr14/agents-party/party.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 24 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00110 | $0.03000 |
| Opus 5.5 | $0.00044 | $0.01200 |
| Sonnet 5.5 | $0.00022 | $0.00600 |
| Haiku 4.5 | $0.00011 | $0.00300 |
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 1mo 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 — 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 viaagents-party webon 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>.
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.
- 1mo ago First seen · 263 lines · 110 tokens per session scan A c3e85e83082f
party is a skill published in the GitHub repository 1gr14/agents-party (12 stars, last pushed 15d ago), licensed MIT. It adds 110 tokens to every session and 3,000 once invoked, about $0.0004 per session on Opus 5.5. 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.
Other skills, from other repositories
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…
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.
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 tests/ that guard it, why the split must be an order-preserving cut…
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…
verifying-external-behavior
Confirms what a third-party library, remote API, build backend, or scraped document actually does before writing code that depends on it — throwaway probes that run in seconds, permissive clients that forward wrong arguments instead of rejecting them, per-endpoint docs that don't generalize, response shapes that make…
writing-javascript
How browser JavaScript is written in this repo — both surfaces now speak one modern dialect and this says what that means for the code you type, where ES modules are impossible and where they are merely unused, and how to pick a feature (Baseline plus a file:// gate). Covers functional idiom over imperative DOM work…