neural-config

neural-config is a skill for Claude Code from Yakoub-ai/neural-memory. It costs 26 tokens per session (507 once invoked), scanned A, original, MIT.

A configuration skill for a codebase memory system. It lets you view settings, choose how code is indexed, exclude files, define patterns for hiding secrets, and set when the index is considered out of date.

In plain words
What is it for?
Use it to inspect or change indexing modes, excluded paths, secret-redaction rules, and commit-based staleness warnings.
Why use it?
It lets you control what the index processes, how much external AI analysis it uses, and how it handles sensitive code.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

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

Good fit Use it to inspect or change indexing modes, excluded paths, secret-redaction rules, and commit-based staleness warnings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yakoub-ai/neural-memory/neural-config
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-config
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-config

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/yakoub-ai/neural-memory/neural-config"><img src="https://agentmods.dev/badge/skills/yakoub-ai/neural-memory/neural-config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 507 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 $0.00026 $0.00507
Opus 5 $0.00013 $0.00253
Sonnet 5 $0.00005 $0.00101
Haiku 4.5 $0.00003 $0.00051

Measured 10d ago against content hash 0f672fbd798d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

neural-config 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-config/SKILL.md · 59 lines

What it actually says

Neural Memory — Configuration

View and modify neural memory settings.

Available actions

  • view: Show current configuration as JSON
  • set_mode: Change indexing mode
    • ast_only — Fast, local-only, no API cost. Uses AST heuristics for summaries.
    • api_only — Rich AI summaries via Claude. Sends code to API.
    • both — Heuristic base + API enrichment for important nodes (default).
  • add_exclude: Add a glob pattern to exclude files (e.g., **/tests/**)
  • add_redaction_pattern: Add a custom regex for secret detection
  • set_staleness_threshold: How many commits behind before the agent warns you (default: 5)

How to call

Via MCP tool (neural-memory configured as MCP server in Claude Code):

Tool: neural_config
{ "action": "view" }
{ "action": "set_mode", "value": "ast_only" }

Via Python (working directly in the project):

import asyncio
from neural_memory.server import neural_config, ConfigInput

# View config
asyncio.run(neural_config(ConfigInput(action="view")))

# Set indexing mode
asyncio.run(neural_config(ConfigInput(action="set_mode", value="ast_only")))

# Add an exclusion pattern
asyncio.run(neural_config(ConfigInput(action="add_exclude", value="**/tests/**")))

# Set staleness threshold
asyncio.run(neural_config(ConfigInput(action="set_staleness_threshold", value="10")))

Parameters

Parameter Type Default Description
project_root str "." Project root directory
action str "view" One of: view, set_mode, add_exclude, add_redaction_pattern, set_staleness_threshold
value str None Value for the action (required for all actions except view)

Data residency

If your code must stay local, use set_mode with ast_only. No code will leave your machine.

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 · 59 lines · 26 tokens per session scan A 0f672fbd798d

Subscribe to this mod's changes

neural-config is a skill published in the GitHub repository Yakoub-ai/neural-memory (1 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 507 once invoked, about $0.0001 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.