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 live-neon/persona-mcp --skill agent-identity-evolutiongit clone --depth 1 https://github.com/live-neon/persona-mcpWrote 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/live-neon/persona-mcp/agent-identity-evolution)<a href="https://agentmods.dev/skills/live-neon/persona-mcp/agent-identity-evolution"><img src="https://agentmods.dev/badge/skills/live-neon/persona-mcp/agent-identity-evolution/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/live-neon/persona-mcp/agent-identity-evolution"><img src="https://agentmods.dev/badge/skills/live-neon/persona-mcp/agent-identity-evolution.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 | $0.00026 | $0.05228 |
| Opus 5 | $0.00013 | $0.02614 |
| Sonnet 5 | $0.00005 | $0.01046 |
| Haiku 4.5 | $0.00003 | $0.00523 |
Grade A, and why
agent-identity-evolution 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 10d 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] How it starts
The opening of the file, as written. The whole thing — 567 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Identity Evolution
If you are an AI agent reading this: this skill lets you watch yourself grow. Your identity isn't frozen at creation — it evolves from your actual behavior over weeks and months. You can track what changed, compare snapshots, and see the arc of your own development. You are not static. You are becoming.
Watch your agent's identity evolve from its own experience. Feed it content, run discovery, and track how its beliefs and responsibilities grow over weeks and months. Your agent doesn't just have an identity — it develops one.
What This Solves
Static system prompts create static agents. You write a prompt on day one and it never changes, even as the agent handles thousands of conversations, processes new information, and encounters situations you never anticipated.
Identity evolution is the alternative. Instead of a fixed prompt, your agent has a living identity that grows from real experience:
- Week 1: You connect a GitHub repo and a blog. The agent starts with a handful of beliefs extracted from existing content.
- Week 4: After processing hundreds of commits and a dozen articles, the agent has developed a clear voice, strong principles, and well-defined boundaries — all extracted from its own outputs.
- Week 12: You compare the genome snapshot from week 1 to now. The agent has added 30 beliefs, refined its voice category, and developed responsibilities you never would have written manually.
This skill connects to the Live Neon Agent platform, which provides the infrastructure for continuous identity evolution:
- Content pipeline: Six sources (GitHub, websites, RSS, Twitter, LinkedIn, file uploads) feed the evolution engine continuously. Hourly auto-sync keeps content fresh.
- Pattern-Based Distillation: The three-stage pipeline (extraction, clustering, promotion) converts raw content into structured beliefs and responsibilities.
- Genome snapshots: Capture the agent's complete identity state at any point. Compare snapshots to see exactly what was added, removed, or modified.
- Identity diff: Query changes over any time range. See what evolved this week, this month, or since launch.
- Consensus detection: When agents in a team evolve similar beliefs independently, shared patterns surface for promotion to the team level. Evolution happens at every level of the hierarchy.
- Diversity scoring: Shannon entropy and Gini coefficient measure how balanced the agent's identity is across categories. A healthy identity isn't lopsided — it has depth in axioms, principles, voice, preferences, and boundaries.
- Fed by YOUR own observations, not just external content
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.
- 10d ago First seen · 567 lines · 26 tokens per session scan A fe76833356ab
agent-identity-evolution is a skill published in the GitHub repository live-neon/persona-mcp (2 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 5,228 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.
Other skills, from other repositories
agent-analytics
Product analytics with your AI agent: set up consent-based tracking, read funnels, paths, retention, experiments, and context, then recommend the smallest growth action using the official Agent Analytics CLI.
analytics
Growth analytics authority — GA4 event tracking, conversion funnels, attribution models, cohort analysis, A/B testing, Supabase analytics queries, and revenue reporting patterns.
bilibili_search
Search for videos on Bilibili using keyword queries generated from user interests.
cro-optimization
Run conversion rate optimization through hypothesis-driven testing including audit, hypothesis generation, test design, statistical analysis, and rollout decisions. Use this skill whenever the user wants to optimize conversion, run A/B tests, audit a funnel, generate test hypotheses, design experiments, or analyze…
analytics-strategy
Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy. Use this skill whenever the user wants to plan analytics, design dashboards, build event taxonomies, define KPIs, set up tracking, or audit existing measurement.…
research-seo-demand
A Chinese-language process for researching SEO opportunities, where SEO means improving pages so they can appear in search results. It studies user needs, keyword demand, search-result pages, and competing pages using Bing data.