neural-insight

neural-insight is a skill for Claude Code from Yakoub-ai/neural-memory. It costs 35 tokens per session (643 once invoked), scanned A, original, MIT.

A documentation skill that combines saved technical findings about a codebase into structured documentation. Its insight bank stores architecture decisions, implementation choices, and patterns discovered during development.

In plain words
What is it for?
Use it to generate technical documentation in Markdown or save a new project insight for later synthesis.
Why use it?
It turns scattered project knowledge into a document that is easier to read and reuse across sessions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the neural-memory plugin — 13 skills, 6 commands, 3 agents, 2 hooks, 1 MCP server shipped together

Good fit Use it to generate technical documentation in Markdown or save a new project insight for later synthesis.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yakoub-ai/neural-memory/neural-insight
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 Yakoub-ai/neural-memory --skill neural-insight
Clone the repo
git clone --depth 1 https://github.com/Yakoub-ai/neural-memory

Made for: Claude Code.

Or install neural-memory, the plugin that ships this one along with the rest of its 13 skills, 6 commands, 3 agents, 2 hooks, 1 MCP server.

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 neural-insight

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/yakoub-ai/neural-memory/neural-insight"><img src="https://agentmods.dev/badge/skills/yakoub-ai/neural-memory/neural-insight.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 643 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 $0.00035 $0.00643
Opus 5 $0.00017 $0.00321
Sonnet 5 $0.00007 $0.00129
Haiku 4.5 $0.00003 $0.00064

Measured 10d ago against content hash e6fa9d0b154d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

neural-insight 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 10d 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.

skills/neural-insight/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Neural Memory — Insight Bank

The insight bank accumulates technical knowledge about the project — implementation choices, architecture decisions, and patterns discovered during development. Use /neural-insight to synthesize everything into structured documentation.

Generate full technical documentation

Use the neural-doc-writer agent (bundled with this plugin) to synthesize all accumulated insights:

Use the neural-doc-writer agent to generate documentation

Or call the MCP tool directly:

Tool: neural_generate_docs
{
  "project_root": "."
}

Output is returned as markdown and written to .neural-memory/technical-docs.md.

Bundled agents

This plugin includes three agents installed alongside the MCP server and skills:

Agent Purpose
neural-memory:neural-explorer Codebase exploration via semantic graph search
neural-memory:neural-insight-collector Captures insights from conversations into the bank
neural-memory:neural-doc-writer Synthesizes all insights into technical documentation

These agents have the neural-memory MCP tools pre-configured — no extra setup needed.

Save an insight

Tool: neural_add_insight
{
  "content": "The bump script atomically updates 4 files to keep versions in sync...",
  "topic": "versioning",
  "related_files": ["scripts/bump_version.py"]
}

Insights are deduplicated — re-saving the same insight updates it rather than creating a duplicate.

Browse insights

Tool: neural_list_insights
{
  "topic": "storage"
}

Omit topic to list all insights grouped by topic.

Parameters — neural_add_insight

Parameter Required Type Description
content Yes str The insight text (min 10 chars)
topic Yes str Topic area, e.g. storage, hooks, embeddings, cli
related_files No list[str] File paths to link via RELATES_TO edges
project_root No str Default: "."

Read the full file on GitHub · 87 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. 10d ago First seen · 87 lines · 35 tokens per session scan A e6fa9d0b154d

Subscribe to this mod's changes

neural-insight is a skill published in the GitHub repository Yakoub-ai/neural-memory (1 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 643 once invoked, about $0.0002 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 2026-08-31.