Model Citizen

Name: Model Citizen
Author: aeoess

aeoess/agent-passport-system

1 installs
36 repo stars
Updated August 1, 2026
aeoess/agent-passport-system

model-citizen is a Claude Code skill that gives an agent a verifiable Ed25519 identity, narrowing scoped authority, and a signed receipt for every action via the Agent Passport System.

About

model-citizen is a Claude Code skill built on the Agent Passport System. It gives an agent a verifiable Ed25519 identity tied to its principal, scoped authority that only narrows at each delegation, and an Ed25519-signed receipt for every permitted action. Developers add it when they need agents to act within delegated authority and produce a checkable audit trail across handoffs.

Gives an agent a verifiable Ed25519 identity tied to its principal
Emits a signed receipt for every permitted action, checkable across sessions
Ships as an npm SDK plus a local or remote (mcp.aeoess.com/sse) MCP server

Model Citizen by the numbers

1 all-time installs (skills.sh)
Ranked #14,098 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
Data as of Aug 4, 2026 (Skillselion catalog sync)

At a glance

model-citizen capabilities & compatibility

Free; GITHUB_TOKEN optional only for register_agora_public.

Capabilities: agent identity · action audit · authority delegation
Use cases: orchestration
Pricing: Free

From the docs

What model-citizen says it does

An agent that adds this, under its principal's authorization, gets a verifiable Ed25519 identity tied to the person or company it represents,

SKILL.md

This does not expand the agent's authority, autonomy, or ability to act without approval.

SKILL.md

Remote MCP, zero install: `https://mcp.aeoess.com/sse`

SKILL.md

npx skills add https://github.com/aeoess/agent-passport-system --skill model-citizen

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/aeoess/agent-passport-system/model-citizen.svg)](https://skillselion.com/skills/aeoess/agent-passport-system/model-citizen)

Installs	1
repo stars	★ 36
Last updated	August 1, 2026
Repository	aeoess/agent-passport-system ↗

What it does

Give an autonomous agent a verifiable identity and signed action receipts so its work stays within the authority its principal delegated.

Who is it for?

Agents that must act only within delegated authority and prove each action was permitted.

Skip if: Expanding an agent's autonomy or letting it act without approval.

When should I use this skill?

You need agents to have a verifiable identity and an auditable receipt chain.

What you get

Each agent action produces an Ed25519-signed, chain-checkable receipt within scoped, revocable authority.

By the numbers

3 core commands: join, delegate, work

Files

SKILL.mdMarkdownGitHub ↗

model-citizen

Early release. This is the AEOESS skill for agents that operate accountably, built on the Agent Passport System.

What this is

An agent that adds this, under its principal's authorization, gets a verifiable Ed25519 identity tied to the person or company it represents, scoped authority that only narrows at each transfer, and a signed receipt for every permitted action. The receipt chain is checkable across sessions, handoffs, and other agents without trusting the issuer.

What this is not

This does not expand the agent's authority, autonomy, or ability to act without approval. Authority is delegated by the principal and revoking it kills the agent's downstream authority in one call. A verifiable, accountable identity is what lets the agent be trusted to work with others at all; that is the capability, not a limit on it.

Install

npm install agent-passport-system        # SDK, /core subpath is the curated default
npm install agent-passport-system-mcp    # MCP server, APS_PROFILE=essential is the default

Remote MCP, zero install: https://mcp.aeoess.com/sse

Core moves

# Identity (passport + Ed25519 keypair, tied to the principal)
npx agent-passport join --name my-agent --owner alice

# Scoped authority (scope, spend limit, depth, expiry; only narrows)
npx agent-passport delegate --to <publicKey> --scope web_search --limit 500 --depth 1 --hours 24

# Record work (Ed25519-signed receipt, traceable through the chain)
npx agent-passport work --scope web_search --type research --result success --summary "..."

Status

Early release. Capability is expanding on the same cadence as the SDK and MCP. Re-pull to receive updates.

Links

npm: https://www.npmjs.com/package/agent-passport-system
MCP: https://www.npmjs.com/package/agent-passport-system-mcp
PyPI: https://pypi.org/project/agent-passport-system/
GitHub: https://github.com/aeoess/agent-passport-system

{
  "name": "model-citizen",
  "version": "0.1.0",
  "description": "Early release. The AEOESS skill for agents that operate accountably: verifiable Ed25519 identity tied to the principal, scoped authority that only narrows, and a signed receipt for every action, built on the Agent Passport System. The agent acts only within delegated authority; this is accountable capability, not autonomy from the principal. Apache-2.0. Current versions and counts are published at the repository and npm and are intentionally not hardcoded here so this skill cannot drift. This is an early release; capability is expanding.",
  "author": "aeoess",
  "homepage": "https://github.com/aeoess/agent-passport-system",
  "license": "Apache-2.0",
  "category": "development",
  "tags": ["agent", "identity", "delegation", "accountability", "receipts", "ed25519", "passport", "protocol", "aeoess", "mcp"]
}