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 neuron-core/neuron-laravel --skill neuron-monitoringgit clone --depth 1 https://github.com/neuron-core/neuron-laravelWrote 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/neuron-core/neuron-laravel/neuron-monitoring)<a href="https://agentmods.dev/skills/neuron-core/neuron-laravel/neuron-monitoring"><img src="https://agentmods.dev/badge/skills/neuron-core/neuron-laravel/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.
<a href="https://agentmods.dev/skills/neuron-core/neuron-laravel/neuron-monitoring"><img src="https://agentmods.dev/badge/skills/neuron-core/neuron-laravel/neuron-monitoring.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 | $0.00088 | $0.03612 |
| Opus 5.5 | $0.00035 | $0.01445 |
| Sonnet 5.5 | $0.00018 | $0.00722 |
| Haiku 4.5 | $0.00009 | $0.00361 |
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 15d 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.
This is a copy
92% identical to neuron-monitoring — 202 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 486 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 — from local logging with
LogListener up to production tracing on the Neuron Cloud platform
(setup instructions at the bottom of this document).
The progression is always the same: components emit events → you subscribe
listeners. A LogListener writing to stdout and the Neuron Cloud 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 lives in
NeuronAI\Observability\Events and extends
NeuronAI\Observability\ObservabilityEvent:
// Lifecycle (emitted by the executor):
// WorkflowStart, WorkflowEnd, WorkflowNodeStart, WorkflowNodeEnd,
// MiddlewareStart, MiddlewareEnd, BranchStart, BranchEnd,
// WorkflowInterrupted (run paused for external input), AgentError (failure)
//
// Domain (emitted by nodes):
// InferenceStart, InferenceStop, ToolCalling, ToolCalled,
// MessageSaving, MessageSaved, Retrieving, Retrieved,
// PreProcessing, PreProcessed, PostProcessing, PostProcessed,
// SchemaGeneration, SchemaGenerated, Extracting, Extracted, ...
Each event carries its own data plus the emission context stamped by the
framework: ->source (the emitting component) and ->branchId (the parallel
branch, or null). ->name() returns the string name ('inference-start').
Subscribing Listeners
Listeners are class-keyed with instanceof matching — subscribe to a specific
event class, or to ObservabilityEvent::class to receive everything:
use NeuronAI\Observability\Events\InferenceStop;
use NeuronAI\Observability\ObservabilityEvent;
// React to one event type
$agent->subscribe(InferenceStop::class, function (InferenceStop $event): void {
echo "Inference finished\n";
});
// Catch-all firehose
$agent->subscribe(ObservabilityEvent::class, function (ObservabilityEvent $event): void {
echo "Event: {$event->name()}\n";
echo "Source: " . ($event->source !== null ? $event->source::class : 'n/a') . "\n";
});
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.
- 15d ago First seen · 486 lines · 88 tokens per session scan A 84572b31bef3
neuron-monitoring is a skill published in the GitHub repository neuron-core/neuron-laravel (122 stars, last pushed 16d ago), licensed MIT. It adds 88 tokens to every session and 3,612 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 92% identical to neuron-monitoring, differing in 202 lines, and is treated as a copy.
Other skills, from other repositories
agent-performance-optimizer
Agent skill for performance-optimizer - invoke with $agent-performance-optimizer.
agent-refinement
Agent skill for refinement - invoke with $agent-refinement.
neuron-monitoring
Monitor Neuron AI agents and workflows with events observability, logging, and performance analysis. Use this skill whenever the user mentions debugging, monitoring, observability, performance analysis, tracing, or needs to understand why an agent is behaving a certain way. Also trigger for tasks involving agent…
debug-manual
Manual debug loop with deep Belmont context and in-place spec reconciliation — user-verified fix + correct the specs that let the bug exist.
debug-auto
Auto debug loop — investigate, fix, verify using agent-dispatched pipeline.
debug
Debug router — choose between auto (agent-verified, narrow code fix) and manual (user-verified, deep spec context, in-place spec reconciliation).