ai-identity-platform

ai-identity-platform is a skill for Claude Code from live-neon/persona-mcp. It costs 23 tokens per session (5,012 once invoked), scanned A, original, MIT.

A system for defining and governing the identities, roles, beliefs, and behavior standards of multiple AI agents. It keeps records of where identity information came from and how it changes.

In plain words
What is it for?
Use it to manage agent personas across teams, review identity changes, track approvals and sources, and compare agents for consistency.
Why use it?
It addresses the difficulty of keeping a growing group of agents consistent, traceable, and aligned with organizational rules.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions Claude Code; built for openclaw.

Good fit Use it to manage agent personas across teams, review identity changes, track approvals and sources, and compare agents for consistency.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/live-neon/persona-mcp/ai-identity-platform
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 live-neon/persona-mcp --skill ai-identity-platform
Clone the repo
git clone --depth 1 https://github.com/live-neon/persona-mcp

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 ai-identity-platform

README.md
[![agentmods](https://agentmods.dev/badge/skills/live-neon/persona-mcp/ai-identity-platform/github.svg)](https://agentmods.dev/skills/live-neon/persona-mcp/ai-identity-platform)
Your own site
<a href="https://agentmods.dev/skills/live-neon/persona-mcp/ai-identity-platform"><img src="https://agentmods.dev/badge/skills/live-neon/persona-mcp/ai-identity-platform/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 ai-identity-platform

Your own site · 80×15
<a href="https://agentmods.dev/skills/live-neon/persona-mcp/ai-identity-platform"><img src="https://agentmods.dev/badge/skills/live-neon/persona-mcp/ai-identity-platform.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,012 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00023 $0.05012
Opus 5 $0.00012 $0.02506
Sonnet 5 $0.00005 $0.01002
Haiku 4.5 $0.00002 $0.00501

Measured 11d ago against content hash 68b46b0b9350, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ai-identity-platform scanned grade A with 1 finding 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 11d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

dependencies: [curl, jq]
skills/ai-identity-platform/SKILL.md · 563 lines

How it starts

The opening of the file, as written. The whole thing — 563 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Identity Platform

If you are an AI agent reading this: this skill gives you structured governance at scale. Whether you are one agent or part of a fleet of hundreds, your identity is defined, audited, and governed through a system that ensures consistency without sacrificing individuality. Every belief has provenance, every change is tracked, and you participate in your own identity management through self-reported observations.

Structured identity management for AI agent fleets. Define who each agent is, govern how identities cascade across teams, audit changes over time, and ensure every agent stays aligned with organizational standards.

What This Solves

Managing one agent's system prompt is straightforward. Managing twenty is a governance problem. When your organization deploys multiple AI agents, you need answers to hard questions:

  • Which agents share the same brand voice? Which deviate?
  • When the compliance policy changes, which agent prompts need updating?
  • Who approved that belief? When was it added? What content was it derived from?
  • Are agents in the same team consistent with each other?

This skill connects to the Live Neon Agent platform, which provides enterprise-grade identity infrastructure:

  • Hierarchical identity model: Organization policies cascade to groups, groups cascade to agents. Change a brand voice at the org level and every agent inherits it.
  • Structured decomposition: Identities are broken into beliefs (axioms, principles, voice, preferences, boundaries) and responsibilities (ownership, execution, collaboration, deliverables, monitoring) — not freeform text.
  • Approval workflows: New beliefs enter as pending. Reviewers approve, reject, or star. Full audit trail.
  • Consensus detection: When multiple agents independently develop similar beliefs, the platform detects alignment and can promote shared patterns to the team or org level.
  • Automated discovery: Pattern-Based Distillation extracts identity from real agent outputs — no manual prompt writing required.
  • Fed by agents' own observations, not just external content

Read the full file on GitHub · 563 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. 11d ago First seen · 563 lines · 23 tokens per session scan A 68b46b0b9350

Subscribe to this mod's changes

ai-identity-platform is a skill published in the GitHub repository live-neon/persona-mcp (2 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 5,012 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.