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 neurarch-ai/neurarch-mcp --skill neurarch-skillgit clone --depth 1 https://github.com/neurarch-ai/neurarch-mcpWrote 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/neurarch-ai/neurarch-mcp/neurarch-skill)<a href="https://agentmods.dev/skills/neurarch-ai/neurarch-mcp/neurarch-skill"><img src="https://agentmods.dev/badge/skills/neurarch-ai/neurarch-mcp/neurarch-skill/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/neurarch-ai/neurarch-mcp/neurarch-skill"><img src="https://agentmods.dev/badge/skills/neurarch-ai/neurarch-mcp/neurarch-skill.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 | $0.00125 | $0.02174 |
| Opus 5 | $0.00063 | $0.01087 |
| Sonnet 5 | $0.00025 | $0.00435 |
| Haiku 4.5 | $0.00013 | $0.00217 |
Grade A, and why
neurarch-skill 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.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Neurarch Graph Loop
Use the Neurarch model graph as the single source of truth for a network's structure. Move every architecture question or edit through one bounded, evidence-gated pass using only the neurarch-mcp tools exposed by the host. Numbers come from tools, not from the model's memory of similar architectures.
Read the references
- Read references/neurarch-mcp-tools.md before the first neurarch-mcp operation in a session and whenever a required capability or payload is unclear.
- Read references/graph-conventions.md before creating a layer or substantially rewiring a graph.
Operating contract
- Use only the connected neurarch-mcp server for graph reads and writes. Do not hand-edit the
.neurarch.jsonfile while the server is connected: the server holds an in-memory copy, and direct file edits either get overwritten bysave_modelor silently diverge from what the tools report. - Treat the connected tool schemas as authoritative. MCP hosts may namespace tool names; match the terminal tool name and semantics rather than assuming a prefix.
- Discover the model's vocabulary at runtime: layer types, layer names, scopes, blocks, and hyperparameters come from the live graph, never from another model, a template, or memory of a similar architecture.
- Frame one authorized edit at a time, including the evidence that will prove it landed and the condition that would stop the loop.
- Make the smallest mutation that can complete that edit, then re-read the affected part of the graph.
- Treat a write tool's success response as a claim. Only a follow-up read (
get_layer,list_connections,validate_model) confirms the intended state. - Run
validate_modelbefore the first edit and record the result. Pre-existing issues belong to the baseline; only new issues belong to your change. - Call
save_modelafter verified mutations. In-memory edits are lost on server restart, and with--watchan external save from the Neurarch app overwrites them. - Preserve the model's existing naming style, scope structure, and design notes unless the user explicitly asks to change them.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 130 lines · 125 tokens per session scan A 95ee026809d0
neurarch-skill is a skill published in the GitHub repository neurarch-ai/neurarch-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 125 tokens to every session and 2,174 once invoked, about $0.0006 per session on Opus 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 2026-09-04.
Other skills, from other repositories
solr-semantic-search
To build Solr phrase-tagging semantic search: concept tagging, taxonomy, graph paths.
coding-agents-prompt-authoring
To author, adapt, review, and validate prompts (skills, agents, workflows, rules, etc.) with brief, contracts, and a validation pack.
solr-query
To build and debug Solr queries: eDisMax, block join, JSON facets, kNN, explain.
markitdown
A Python utility for converting various file formats (PDF, Word, Excel, PowerPoint, etc.) to Markdown. Use this skill to install and use MarkItDown for document conversion.
AIChat All-in-One LLM CLI with Shell Assistant and RAG
AIChat is a comprehensive LLM command-line tool written in Rust that combines chat-REPL, shell command generation, RAG, AI tools, and multi-provider support into a single binary. It connects to 20+ LLM providers including OpenAI, Claude, Gemini, and Ollama.
agent-mle-reviewer
Production machine-learning engineering reviewer for data contracts, feature pipelines, training reproducibility, offline/online evaluation, model serving, monitoring, and rollback. Use when ML, MLOps, model training, inference, feature store, or evaluation code changes.