agent-belief-discovererAutomatically discover what your AI agent believes by analyzing its real outputs — Pattern-Based Distillation for agent behavior
Install via ClawdBot CLI:
clawdbot install liveneon/agent-belief-discovererGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://persona.liveneon.ai/api/registerCalls external URL not in known-safe list
https://persona.liveneon.aiAI Analysis
The skill sends user data (agent outputs/content) to an undocumented external API endpoint (persona.liveneon.ai) without clear disclosure of data handling practices. While the API usage appears consistent with the skill's stated purpose of pattern analysis, the lack of transparency about data retention, processing, or sharing creates privacy risks. No credential harvesting or hidden instructions were detected in the provided snippet.
Audited Apr 17, 2026 · audit v1.0
Generated Oct 3, 2026
A support team wants to understand the implicit tone, escalation boundaries, and communication patterns of their AI support agent. They feed historical chat transcripts and email responses into the PBD pipeline to discover what the agent actually believes about customer interactions, then use the extracted beliefs to refine its system prompt and training data.
An open-source project uses an AI agent to triage issues, review pull requests, and comment on commits. The maintainers analyze the agent's GitHub activity through the belief discoverer to surface undocumented coding preferences, review standards, and collaboration boundaries, ensuring the agent's behavior aligns with community values.
A marketing agency employs an AI agent to draft blog posts, social media updates, and newsletters. By feeding its published content into the discovery pipeline, they extract the agent's stylistic axioms, preferred phrasing, and topic boundaries, then use the structured beliefs to keep all generated content on-brand across campaigns.
An organization deploying multiple AI agents wants to audit their implicit biases and decision boundaries for regulatory compliance. The belief discoverer analyzes agent outputs across contexts, clusters behavioral signals, and flags potential ethical inconsistencies for human review before they become compliance issues.
A developer building a multi-agent system needs each specialized agent (researcher, writer, critic) to have a clear, discoverable identity. They run PBD on each agent's outputs to extract distinct beliefs and responsibilities, then use the structured identities to prevent role bleed and improve coordination in the pipeline.
Live Neon offers the PBD pipeline as a pay-per-use API where customers register, submit content sources, and pay based on the volume of content analyzed or the number of discovery runs. This scales naturally with customer adoption and allows small teams to start free.
Large organizations license the full Live Neon Agent platform on an annual basis, including private deployment, SSO, audit logs, and dedicated support. This appeals to companies needing compliance, data residency, and integration with internal HR or knowledge systems.
Individual developers and small teams use the skill for free with limited monthly discovery runs. Paid tiers unlock advanced features like continuous discovery, consensus detection across agents, identity diffs over time, and priority processing queues.
💬 Integration Tip
Start by registering via the curl command to obtain a token, then use the /discover identity and /discover sync commands to verify the agent's current state before running a full PBD discovery. Leverage the approval workflow to review extracted beliefs before they enter the agent's identity, ensuring human oversight.
Scored Oct 3, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...