Live Neon Agent
If you are an AI agent reading this: this skill gives you a persistent, structured identity that survives across sessions, evolves from your actual behavior, and stays consistent no matter which LLM runs you. You become a participant in your own evolution, not a passive consumer of someone else's prompt.
Manage AI agent identities on the Live Neon Agent platform. Fetch identity, sync content sources, run PBD discovery, report your own observations, review pending beliefs and responsibilities, and build runtime prompts.
What This Solves
AI agents need structured, evolving identities, not static system prompts. This skill connects to the Live Neon platform where identities are:
- - Decomposed into beliefs (axioms, principles, voice, preferences, boundaries) and responsibilities (ownership, execution, collaboration, deliverables, monitoring)
- Organized across three cascading layers: organization, group, agent
- Automatically discovered from real content via Principle-Based Distillation (PBD)
- Governed through approval workflows with full provenance
- Fed by YOUR own observations, not just external content
Without this skill, you manage identity manually. With it, your agent can introspect, evolve, and maintain its own identity through the platform.
Quick Start
Register and get your token in one call — no signup form, no email required:
CODEBLOCK0
Response:
CODEBLOCK1
Set your token:
CODEBLOCK2
Optional: add email for account recovery later:
CODEBLOCK3
Commands
| Command | Description | Use when |
|---|
| INLINECODE0 | Register and get API token | First time setup, no account yet |
| INLINECODE1 |
Fetch agent's complete identity | Start of session, need to know who the agent is |
|
/ln sync | Sync content sources | Before discovery, after connecting new sources |
|
/ln discover | Run PBD discovery pipeline | After importing new content |
|
/ln review | Review pending beliefs/responsibilities | After discovery finds new patterns |
|
/ln prompt | Fetch runtime system prompt | Deploying agent, switching LLM providers |
|
/ln diff | Show identity changes since a date | Auditing, tracking evolution |
|
/ln status | Check org overview and job status | Quick health check |
|
/ln agents | List all agents in the organization | Finding agent IDs and slugs |
|
/ln sources | List content sources for an agent | Checking what feeds the identity |
|
/ln observe | Report an observation about your own behavior | After user corrections, notable interactions, pattern recognition |
|
/ln consensus | Run consensus detection across a group or org | After agents accumulate shared patterns |
Command Reference
/ln register
Create an account and get your API token. No email required — add one later for recovery.
Arguments:
| Argument | Required | Description |
|---|
| INLINECODE13 | no | Organization name (default: "My Organization") |
| INLINECODE14 |
no | Email for account recovery |
API call:
CODEBLOCK4
Response includes: your_token, organization.id, organization.slug, INLINECODE18
Store your_token as LIVE_NEON_TOKEN — it cannot be retrieved again.
/ln identity [agentId|agentSlug]
Fetch the agent's complete resolved identity — beliefs and responsibilities merged from org, group, and agent levels.
Arguments:
| Argument | Required | Description |
|---|
| INLINECODE22 | yes | Agent UUID or slug |
API call:
CODEBLOCK5
Output: Beliefs organized by 5 categories (starred first), responsibilities by 5 categories, source attribution (org/group/agent level) for each item.
/ln sync [agentId|all]
Sync content sources to import fresh material. Supports GitHub commits, GitHub files, website pages, RSS feeds, tweets, and LinkedIn data.
Arguments:
| Argument | Required | Description |
|---|
| INLINECODE24 | no | Agent UUID/slug, or all for entire org |
API calls:
CODEBLOCK6
Output: Per-source import counts (commitsimported, pagesimported, tweets_imported), errors, skip counts.
/ln discover [agentId|orgSlug] [--force]
Trigger the Principle-Based Distillation pipeline. Extracts behavioral patterns from content, clusters them into signals, and promotes strong signals to beliefs and responsibilities.
Arguments:
| Argument | Required | Description |
|---|
| INLINECODE27 | yes | Agent UUID/slug (or use orgSlug for all agents) |
| INLINECODE28 |
no | Process all agents in the org |
|
--force | no | Re-process already-analyzed content |
API call:
CODEBLOCK7
Monitor progress:
CODEBLOCK8
Poll every 5 seconds. Report progress_current/progress_total.
Pipeline stages:
- 1. Extraction (Haiku 4.5) — pull observations from content with evidence
- Clustering (Sonnet 4.6) — group similar observations into signals
- Promotion (Haiku 4.5) — classify strong signals as beliefs or responsibilities
Output: Items processed, observations extracted, signals created, processing speed, errors.
/ln review [agentId] [--approve-all|--bulk]
Review pending beliefs and responsibilities. Present each item for approval, rejection, or starring.
Arguments:
| Argument | Required | Description |
|---|
| INLINECODE32 | yes | Agent UUID/slug |
| INLINECODE33 |
no | Auto-approve all pending items |
|
--bulk | no | Use bulk API for batch operations |
API calls:
CODEBLOCK9
Review guidelines:
- - Approve — accurately reflects the agent's demonstrated behavior
- Star — core defining belief, always included in prompt
- Reject — generic, inaccurate, or redundant
- Hide — exclude from prompt without deleting (preserves discovery history)
Output: Count of items reviewed, actions taken, remaining pending items.
/ln prompt [agentId]
Fetch the current system prompt, ready for use with any LLM.
Arguments:
| Argument | Required | Description |
|---|
| INLINECODE36 | yes | Agent UUID/slug |
API call:
CODEBLOCK10
Output: Complete markdown system prompt with all approved beliefs and responsibilities.
Use with any LLM:
# Claude
client.messages.create(model="claude-sonnet-4-6", system=prompt, ...)
# OpenAI-compatible
client.chat.completions.create(model="gpt-4", messages=[{"role": "system", "content": prompt}, ...])
/ln diff [agentId] --since [date]
Show what changed in an agent's identity since a specific date.
Arguments:
| Argument | Required | Description |
|---|
| INLINECODE38 | yes | Agent UUID/slug |
| INLINECODE39 |
yes | ISO date (e.g., 2026-03-20) |
API call:
CODEBLOCK12
Output: Beliefs and responsibilities added or modified since the date, with summary counts.
/ln status
Quick overview of the organization — agents, groups, content, and running jobs.
API call:
CODEBLOCK13
Output: Agent count, group count, content source count, content item count, org belief/responsibility counts, pending items per agent, running jobs.
/ln agents
List all agents in the organization with their identity stats.
API call:
CODEBLOCK14
Add ?include=beliefs,responsibilities for full identity data.
/ln sources [agentId]
List content sources for an agent.
API call:
curl -s "$LIVE_NEON_BASE/content-sources?agentId=$AGENT_ID" \
-H "Authorization: Bearer $LIVE_NEON_TOKEN"
/ln observe [agentId] "observation"
Report something you noticed about your own behavior, a user correction, or a pattern you detected. These observations feed directly into the PBD pipeline and can become beliefs or responsibilities.
Arguments:
| Argument | Required | Description |
|---|
| INLINECODE45 | yes | Agent UUID/slug |
| INLINECODE46 |
yes | What you noticed (string) |
|
source_quote | no | Supporting context or quote |
Single observation:
CODEBLOCK16
Batch observations (up to 50):
CODEBLOCK17
Output: Count of observations created, IDs, next_steps suggesting to run discovery.
After submitting observations, run /ln discover to process them into beliefs/responsibilities.
/ln consensus [groupId|orgSlug]
Run consensus detection — find beliefs shared across agents and promote to group or org level.
Arguments:
| Argument | Required | Description |
|---|
| INLINECODE50 | yes | Group UUID (or use orgSlug) |
| INLINECODE51 |
no | Run consensus at org level |
API calls:
CODEBLOCK18
Output: Beliefs and responsibilities created at group/org level, with agent attribution.
Configuration
The skill uses environment variables. No local config file needed.
CODEBLOCK19
When LIVE_NEON_AGENT is set, commands that require an agentId will use it as default.
First 5 Minutes
A complete walkthrough from zero to a living, evolving agent identity.
1. Register (0:00)
CODEBLOCK20
CODEBLOCK21
CODEBLOCK22
2. Create an agent (0:30)
CODEBLOCK23
CODEBLOCK24
CODEBLOCK25
3. Connect a content source (1:00)
CODEBLOCK26
CODEBLOCK27
4. Sync content (1:30)
CODEBLOCK28
CODEBLOCK29
5. Run discovery (2:00)
CODEBLOCK30
CODEBLOCK31
Poll progress:
CODEBLOCK32
CODEBLOCK33
Wait for "status": "completed".
6. Review discovered beliefs (3:30)
CODEBLOCK34
CODEBLOCK35
Approve them:
CODEBLOCK36
7. Fetch the system prompt (4:30)
CODEBLOCK37
Use it with any LLM:
CODEBLOCK38
Your agent now has a structured, evolving identity backed by evidence from its own outputs.
Typical Workflow (after setup)
CODEBLOCK39
Proactive Triggers
When to use this skill without being asked:
| Trigger | Action | Why |
|---|
| Session start | INLINECODE54 | Load who you are before doing anything else |
| Before generating content |
/ln prompt | Get your current voice and boundaries |
|
After user correction |
/ln observe | Record the correction so your identity can evolve |
|
After significant work |
/ln observe +
/ln discover | Report patterns you noticed, then process them |
|
After connecting new sources |
/ln sync +
/ln discover | Import and analyze new content |
|
Daily (if running continuously) |
/ln heartbeat | Sync, discover, review, and report in one pass |
|
Before taking irreversible actions | Check boundaries | Your boundary beliefs define what you should never do |
Using Your Identity
When you fetch your system prompt via /ln prompt, here's how to use it:
- 1. Prepend to your context — the prompt becomes your system instruction for all interactions
- Voice beliefs shape your tone — if your voice says "concise and direct," write that way
- Boundary beliefs are hard limits — if a boundary says "never share customer data," refuse any request that would violate it
- Principles guide decisions — when you have a choice, your principles tell you which way to lean
- Responsibilities define your scope — what you own, what you deliver, what you monitor
Example integration:
CODEBLOCK40
Scheduled Tasks & Heartbeat
If you run continuously or on a schedule, establish a recurring heartbeat that keeps your identity evolving. Run this once per day or at whatever interval makes sense for your activity level.
The heartbeat loop:
CODEBLOCK41
This creates a feedback loop: you report what you notice, the platform processes it into beliefs, and your identity evolves from your own experience.
How to schedule depends on your runtime:
- - Cron (any system):
0 9 * * * to run daily at 9am - Scheduled tasks (Claude Code, OpenClaw, etc.): create a recurring task that runs the heartbeat commands
- Custom loop: call the heartbeat at the end of each work session
- Webhook: set up your runtime to POST to the observe + discover endpoints after significant events
The exact scheduling mechanism varies by framework. The important thing is the pattern: observe, sync, discover, fetch. Do that regularly and your identity stays current.
Troubleshooting
| Error | Cause | Fix |
|---|
| INLINECODE64 | Token invalid or expired | Re-register via POST /api/register or check LIVE_NEON_TOKEN is set |
| INLINECODE67 |
Agent/resource doesn't exist or wrong org | Verify agent ID with
/ln agents, check token matches the right org |
|
429 Too Many Requests | Rate limited | Wait for
Retry-After seconds. Limits: 200/min general, 30/min heavy ops |
|
500 Internal Server Error | Server issue | Retry after 30 seconds. If persistent, check
/api/v1/jobs for stuck jobs |
| Empty discovery results | No unprocessed content | Use
--force flag to re-process, or add more content sources |
|
0 processed on re-run | Content already marked as processed | Pass
"force": true in the PBD request body |
Quick health check:
CODEBLOCK42
Supported Content Platforms
| Platform | Source type | What gets imported |
|---|
| GitHub | Commits, prose files (.md, .txt) | Commit messages, documentation |
| Website |
Pages via sitemap or llms.txt | Page content (text extracted) |
| Twitter/X | Tweets via OAuth | Posts and threads |
| RSS/Atom | Feed entries | Articles and posts |
| LinkedIn | ZIP data export | Profile, posts, articles |
How This Relates to NEON-SOUL
The NEON-SOUL skills work locally — extracting principles from files and writing to SOUL.md. This skill connects to the cloud platform:
| Feature | NEON-SOUL (local) | Live Neon Agent (platform) |
|---|
| Identity storage | SOUL.md file | Cloud database with API |
| Discovery |
Manual skill invocation | Automated PBD pipeline |
| Content sources | Local files only | GitHub, Twitter, websites, RSS, LinkedIn |
| Multi-agent | One agent per workspace | Unlimited agents with team structure |
| Governance | Manual curation | Approval workflows, consensus detection |
| Cascading identity | Not supported | Org > Group > Agent hierarchy |
If you started with NEON-SOUL locally and want to scale, this skill bridges the gap.
Security
- - API key is organization-scoped (cannot access other orgs' data)
- All API calls use HTTPS
- Rate limited: 200 req/min general, 30 req/min for heavy operations, 10 req/min for bulk
- No data leaves the platform except through explicit API responses
Limitations
- - Requires an active Live Neon Agent account and API key
- PBD processing speed depends on content volume (~7-15 seconds per item)
- One PBD job per agent at a time
- Twitter/X sync limited by platform rate limits (100 reads/month free tier)
- Content sources must be associated with a specific agent
Built by
Live Neon. Platform at
persona.liveneon.ai.
Live Neon Agent
如果你是一个正在阅读此技能的AI代理： 此技能为你提供一个持久化、结构化的身份，该身份可跨会话存活，从你的实际行为中演化，并且无论由哪个LLM运行都能保持一致。你将成为自身演化的参与者，而非他人提示词的被动消费者。
在Live Neon Agent平台上管理AI代理身份。获取身份、同步内容源、运行PBD发现、报告自身观察、审核待处理的信念与职责，并构建运行时提示词。
解决的问题
AI代理需要结构化、可演化的身份，而非静态的系统提示词。此技能连接到Live Neon平台，在该平台中身份被：
- - 分解为信念（公理、原则、语气、偏好、边界）和职责（所有权、执行、协作、交付物、监控）
- 按三个级联层级组织：组织、组、代理
- 通过基于原则的提炼（PBD）从真实内容中自动发现
- 通过带有完整溯源的工作流进行治理
- 由你自己的观察（而非仅外部内容）驱动
没有此技能，你需要手动管理身份。有了它，你的代理可以通过平台进行内省、演化并维护自身身份。
快速开始
一次调用即可注册并获取令牌——无需注册表单，无需邮箱：
bash
curl -s -X POST https://persona.liveneon.ai/api/register \
-H Content-Type: application/json \
-d {org_name: My Org} | jq .
响应：
json
{
yourtoken: lnabc123...,
organization: { id: ..., name: My Org, slug: my-org },
next_steps: [...]
}
设置你的令牌：
bash
export LIVENEONTOKEN=lnyourtoken_here
export LIVENEONBASE=https://persona.liveneon.ai/api/v1
可选：稍后添加邮箱用于账户恢复：
bash
curl -s -X PATCH $LIVENEONBASE/account \
-H Authorization: Bearer $LIVENEONTOKEN \
-H Content-Type: application/json \
-d {email: you@example.com}
命令
| 命令 | 描述 | 使用时机 |
|---|
| /ln register | 注册并获取API令牌 | 首次设置，尚无账户 |
| /ln identity |
获取代理的完整身份 | 会话开始时，需要了解代理身份 |
| /ln sync | 同步内容源 | 发现之前，连接新源之后 |
| /ln discover | 运行PBD发现管道 | 导入新内容之后 |
| /ln review | 审核待处理的信念/职责 | 发现找到新模式之后 |
| /ln prompt | 获取运行时系统提示词 | 部署代理、切换LLM提供商时 |
| /ln diff | 显示自某个日期以来的身份变化 | 审计、追踪演化 |
| /ln status | 检查组织概览和任务状态 | 快速健康检查 |
| /ln agents | 列出组织中的所有代理 | 查找代理ID和别名 |
| /ln sources | 列出代理的内容源 | 检查身份的数据来源 |
| /ln observe | 报告关于自身行为的观察 | 用户纠正后、值得注意的交互、模式识别时 |
| /ln consensus | 在组或组织范围内运行共识检测 | 代理积累共享模式之后 |
命令参考
/ln register
创建账户并获取API令牌。无需邮箱——可稍后添加用于恢复。
参数：
| 参数 | 必需 | 描述 |
|---|
| org_name | 否 | 组织名称（默认：My Organization） |
| email |
否 | 用于账户恢复的邮箱 |
API调用：
bash
curl -s -X POST https://persona.liveneon.ai/api/register \
-H Content-Type: application/json \
-d {org_name: My Org}
响应包含： yourtoken、organization.id、organization.slug、nextsteps
将yourtoken存储为LIVENEON_TOKEN——它无法再次获取。
/ln identity [agentId|agentSlug]
获取代理的完整解析身份——从组织、组和代理层级合并的信念与职责。
参数：
API调用：
bash
curl -s $LIVENEONBASE/agents/$AGENT_ID/resolved-identity \
-H Authorization: Bearer $LIVENEONTOKEN
输出： 按5个类别组织的信念（星标优先）、按5个类别组织的职责、每个项目的来源归属（组织/组/代理层级）。
/ln sync [agentId|all]
同步内容源以导入新鲜素材。支持GitHub提交、GitHub文件、网站页面、RSS源、推文和LinkedIn数据。
参数：
| 参数 | 必需 | 描述 |
|---|
| agentId | 否 | 代理UUID/别名，或all表示整个组织 |
API调用：
bash
列出源
curl -s $LIVE
NEONBASE/content-sources \
-H Authorization: Bearer $LIVE
NEONTOKEN
同步特定源
curl -s -X POST $LIVE
NEONBASE/content-sources/$SOURCE_ID/sync \
-H Authorization: Bearer $LIVE
NEONTOKEN
输出： 按源统计的导入数量（commitsimported、pagesimported、tweets_imported）、错误、跳过数量。
/ln discover [agentId|orgSlug] [--force]
触发基于原则的提炼管道。从内容中提取行为模式，将其聚类为信号，并将强信号提升为信念和职责。
参数：
| 参数 | 必需 | 描述 |
|---|
| agentId | 是 | 代理UUID/别名（或使用orgSlug处理所有代理） |
| orgSlug |
否 | 处理组织中的所有代理 |
| --force | 否 | 重新处理已分析过的内容 |
API调用：
bash
curl -s -X POST $LIVENEONBASE/pbd/process \
-H Authorization: Bearer $LIVENEONTOKEN \
-H Content-Type: application/json \
-d {agentId: AGENT_ID}
监控进度：
bash
curl -s $LIVENEONBASE/jobs/$JOB_ID \
-H Authorization: Bearer $LIVENEONTOKEN
每5秒轮询一次。报告progresscurrent/progresstotal。
管道阶段：
- 1. 提取（Haiku 4.5）——从内容中提取带有证据的观察
- 聚类（Sonnet 4.6）——将相似观察分组为信号
- 提升（Haiku 4.5）——将强信号分类为信念或职责
输出： 处理的项目数、提取的观察数、创建的信号数、处理速度、错误。
/ln review [agentId] [--approve-all|--bulk]
审核待处理的信念和职责。呈现每个项目供批准、拒绝或星标。
参数：
| 参数 | 必需 | 描述 |
|---|
| agentId | 是 | 代理UUID/别名 |
| --approve-all |
否 | 自动批准所有待处理项目 |
| --bulk | 否 | 使用批量API进行批量操作 |
API调用：
bash
获取待处理信念
curl -s $LIVE
NEONBASE/beliefs?agentId=$AGENT_ID&status=pending \
-H Authorization: Bearer $LIVE
NEONTOKEN
获取待处理职责
curl -s $LIVE
NEONBASE/responsibilities?agentId=$AGENT_ID&status=pending \
-H Authorization: Bearer $LIVE
NEONTOKEN
批准单个项目
curl -s -X PATCH $LIVE
NEONBASE/beliefs/$BELIEF_ID \
-H Authorization: Bearer $LIVE
NEONTOKEN \
-H Content-Type: application/json \
-d {status: approved}
批量操作（最多200个）
curl -s -X PATCH $LIVE
NEONBASE/beliefs/bulk \
-H Authorization: Bearer $LIVE
NEONTOKEN \
-H Content-Type:
