neuron-monitoring

neuron-monitoring is a skill for Claude Code, Codex from neuron-core/neuron-ai. It costs 80 tokens per session (2,865 once invoked), scanned A, original, MIT.

An observability guide for Neuron AI agents and workflows. It explains how to capture events in local logs or send traces to Neuron Cloud so you can see what runs and when.

In plain words
What is it for?
Use it to add event listeners, inspect workflow and agent runs, trace production activity, and analyse performance.
Why use it?
It helps explain why an agent behaves unexpectedly and identify errors or slow steps without guessing from the final response alone.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to add event listeners, inspect workflow and agent runs, trace production activity, and analyse performance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/neuron-core/neuron-ai/neuron-monitoring
About the project

Neuron AI is a PHP framework for building AI applications in which agents connect language models, tools, data loaders, vector databases, memory, and user interfaces. PHP developers use it to create and manage applications with agent workflows, multi-agent coordination, streaming, monitoring, and human involvement.

neuron-core/neuron-ai · 2,140 stars · on GitHub · neuron-ai.dev

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 neuron-core/neuron-ai --skill neuron-monitoring
Clone the repo
git clone --depth 1 https://github.com/neuron-core/neuron-ai

Made for: Claude Code, Codex.

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 neuron-monitoring

README.md
[![agentmods](https://agentmods.dev/badge/skills/neuron-core/neuron-ai/neuron-monitoring/github.svg)](https://agentmods.dev/skills/neuron-core/neuron-ai/neuron-monitoring)
Your own site
<a href="https://agentmods.dev/skills/neuron-core/neuron-ai/neuron-monitoring"><img src="https://agentmods.dev/badge/skills/neuron-core/neuron-ai/neuron-monitoring/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 neuron-monitoring

Your own site · 80×15
<a href="https://agentmods.dev/skills/neuron-core/neuron-ai/neuron-monitoring"><img src="https://agentmods.dev/badge/skills/neuron-core/neuron-ai/neuron-monitoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,865 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00080 $0.02865
Opus 5.5 $0.00032 $0.01146
Sonnet 5.5 $0.00016 $0.00573
Haiku 4.5 $0.00008 $0.00286

Measured 8d ago against content hash 47e2105b4450, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

neuron-monitoring scanned grade A with 0 findings 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 8d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/neuron-monitoring/SKILL.md · 382 lines

How it starts

The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Neuron AI Monitoring

This skill helps you debug and monitor Neuron AI applications using the framework's event-driven observability system.

The progression is always the same: components emit events → you subscribe listeners. A LogListener writing to stdout and a custom tracing listener are the same mechanism, differing only in where the events go.

Event System Observability

Neuron uses a PSR-14 event dispatcher owned by each Workflow/Agent instance for monitoring all framework events. There is no global state: listeners are registered on the instance and observe every run of it.

Event Emission

All components emit event objects automatically. Every event class extends NeuronAI\Observability\ObservabilityEvent and lives in the Observability namespace of the module that emits it:

// NeuronAI\Workflow\Observability — the lifecycle, emitted by the workflow engine:
// WorkflowStart, WorkflowEnd, WorkflowNodeStart, WorkflowNodeEnd,
// MiddlewareStart, MiddlewareEnd, BranchStart, BranchEnd, ChannelError,
// WorkflowInterrupted (run paused for external input), WorkflowError (failure)
//
// NeuronAI\Agent\Observability — emitted by agent nodes:
// InferenceStart, InferenceStop, ToolCalling, ToolCalled,
// MessageSaving, MessageSaved, SchemaGeneration, SchemaGenerated,
// Extracting, Extracted, Deserializing, Deserialized, Validating, Validated
//
// NeuronAI\RAG\Observability — emitted by RAG nodes:
// Retrieving, Retrieved, PreProcessing, PreProcessed, PostProcessing, PostProcessed

Each event carries its own data plus the emission context stamped by the framework: ->source (the emitting component), ->execution (the run identity) and ->branchId (the parallel branch, or null). ->name() returns the string name ('inference-start') and ->toArray() the event's own data.

Every node and middleware start is followed by its end, whatever the outcome: WorkflowNodeEnd and MiddlewareEnd carry ->outcome, a NodeOutcome (Completed, Suspended or Failed), so a span can be closed and marked as soon as its node ends.

Read the full file on GitHub · 382 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. 8d ago Changed · -123 lines · -8 tokens per session 47e2105b4450
  2. 15d ago First seen · 505 lines · 88 tokens per session scan A 94b4545f313d

Subscribe to this mod's changes

neuron-monitoring is a skill published in the GitHub repository neuron-core/neuron-ai (2,140 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 2,865 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-01.