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.
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-ai --skill neuron-tool-approvalgit clone --depth 1 https://github.com/neuron-core/neuron-aiWrote 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-ai/neuron-tool-approval)<a href="https://agentmods.dev/skills/neuron-core/neuron-ai/neuron-tool-approval"><img src="https://agentmods.dev/badge/skills/neuron-core/neuron-ai/neuron-tool-approval/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-ai/neuron-tool-approval"><img src="https://agentmods.dev/badge/skills/neuron-core/neuron-ai/neuron-tool-approval.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 | $0.00103 | $0.04343 |
| Opus 5.5 | $0.00041 | $0.01737 |
| Sonnet 5.5 | $0.00021 | $0.00869 |
| Haiku 4.5 | $0.00010 | $0.00434 |
Grade A, and why
neuron-tool-approval scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 15d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Neuron AI Tool Approval
This skill helps you gate agent tool execution behind human approval and build the application around it: the server endpoint, the UI, and the decision round trip.
Use Agent::submitApprovalDecisions($decisions) for tool approval and Agent::submitToolResults($results) for deferred tool results. Both accept maps keyed by tool call ID and stage a continuation; finish with run() for an AgentState or events() for a stream.
The Mental Model
Approval is owned by ToolNode and configured on the tools themselves. There is no middleware to attach: each tool declares whether it needs approval, you override that per instance when you attach it to the agent, and the node suspends the run before executing anything undecided.
Chat history is what the application reads; the thread is the workflow ID. Which tools await a decision and why each one is asking live on the last message of the thread, written once at suspend time — a client that renders from the message list needs nothing else. A client that keeps approvals apart from messages (AG-UI, CopilotKit) asks the agent instead: Agent::pendingApprovals() (see Rebuilding the UI after a reload). Continuing needs no runId either: the run's durable records live in the partition named by the threadId itself, so the approve endpoint rebuilds the agent from the thread ID alone, stages the decisions with submitApprovalDecisions($decisions), and finishes with run() or events(). No workflow coordination ID is stored on the side.
Two facts shape the UI:
- History is append-only. The suspended
tool_callmessage keeps its pending snapshot forever; the final outcomes (approved/rejected + feedback + results) are recorded on thetool_call_resultmessage that follows it. "Is approval pending?" = the thread tail is atool_callwith pending tools. - Partial decisions are retained by ToolNode through durable memos. Each submission can contain only the newest decisions, through
submitApprovalDecisions($decisions). Explicit updates to an already-decided action in a still-open batch win.
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 · 313 lines · 103 tokens per session scan A be46e325c41e
neuron-tool-approval is a skill published in the GitHub repository neuron-core/neuron-ai (2,140 stars, last pushed yesterday), licensed MIT. It adds 103 tokens to every session and 4,343 once invoked, about $0.0004 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.
Other skills, from other repositories
neuron-evaluation
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
neuron-workflow
Build or modify Neuron AI Workflow graphs, including nodes, events, middleware, persistence, parallel branches, streaming, and human-in-the-loop interruption. Use for tasks specifically involving Neuron's Workflow APIs or custom Neuron agentic orchestration; do not trigger for generic workflow or event-driven design…
neuron-streaming
Stream Neuron AI agent and workflow output to a consumer — iterating native chunks, yielding portable progress events from nodes, attaching a stream adapter for a UI protocol (Vercel AI SDK, AG-UI, SSE) or for Neuron's native vocabulary, and pushing output through a streaming channel when the consumer is not the HTTP…
neuron-frontend-integration
Connect a Neuron AI agent to a real frontend that executes tools in the browser — declaring deferred (frontend) tools, building the endpoint that serves a new turn or continues a suspended run, translating tool results and approval decisions coming from the Vercel AI SDK (useChat), the official AG-UI client, or…
neuron-test
Write tests for Neuron AI agents, RAG systems, workflows, and tools using the built-in testing utilities. Use this skill when the user mentions testing agents, writing unit tests, mocking AI providers, testing tool execution, verifying RAG retrieval, testing workflow behavior, or creating test cases for Neuron AI…
neuron-tool
Create custom tools, toolkits, and MCP integrations for Neuron AI agents. Use this skill when the user mentions creating tools, building toolkits, extending Tool class, defining tool properties, implementing tool execution, MCP server integration, Model Context Protocol, connecting external tools, multimodal tool…