neural-context

neural-context is a skill for Claude Code from Yakoub-ai/neural-memory. It costs 49 tokens per session (649 once invoked), scanned A, original, MIT.

A context skill for recording and retrieving a compact summary of a project's current state. It includes the project overview, open bugs and tasks, related code locations, recent commits, and important code nodes.

In plain words
What is it for?
Use it before a task to inspect relevant context, between major steps to check work, or at the end of a session to save context for later.
Why use it?
It helps an agent quickly regain orientation when starting work or returning to a project after a break.

Skill for Claude Code

Written for Claude Code: UserPromptSubmit hook event.

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

Good fit Use it before a task to inspect relevant context, between major steps to check work, or at the end of a session to save context for later.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/yakoub-ai/neural-memory/neural-context"><img src="https://agentmods.dev/badge/skills/yakoub-ai/neural-memory/neural-context.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 649 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 $0.00049 $0.00649
Opus 5 $0.00024 $0.00324
Sonnet 5 $0.00010 $0.00130
Haiku 4.5 $0.00005 $0.00065

Measured 9d ago against content hash 5a2f6d61aced, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

neural-context 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 9d 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-context/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Neural Memory — Compact Context + Session Save

Get a token-budgeted (~500 token) snapshot of the current project's knowledge graph, and save a richer persistent snapshot for cross-session continuity.

What this does

Returns in one call:

  • Staleness status — is the index current?
  • Project overview — what this codebase does
  • Active bugs — open, non-archived bugs
  • Active tasks — pending/in-progress/testing, non-archived tasks
  • Relevant nodes — code nodes semantically matching your query (if provided)

And saves to .neural-memory/session_context.md:

  • Active tasks and bugs with their code node connections (file + line)
  • Last 5 git commits
  • Top 5 most important code nodes

When to use

  • At the start of any task to orient yourself
  • At the end of a session to persist context for the next session
  • Between major steps to check active bugs and tasks
  • Before modifying a specific area (pass that area as query_hint)

How to call

Via MCP tool (snapshot + save):

Tool: neural_save_context
{ "token_budget": 800 }

Via MCP tool (snapshot only):

Tool: neural_context
{ "query_hint": "authentication middleware", "token_budget": 500 }

Minimal call (no query hint — overview + bugs + tasks only):

Tool: neural_context
{}

Parameters

Parameter Type Default Description
project_root str "." Project root directory
query_hint str null Prompt or keyword to drive semantic pre-fetch of relevant nodes
token_budget int 500 Approximate token budget (100–2000)

Session Persistence

The saved snapshot at .neural-memory/session_context.md is automatically:

  • Written at session end (Stop hook) — no manual action needed
  • Loaded at session start (UserPromptSubmit hook) when no query hint is present
  • Refreshed whenever you run /neural-context manually

This gives new sessions immediate deep context without re-discovery.

Read the full file on GitHub · 77 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. 9d ago First seen · 77 lines · 49 tokens per session scan A 5a2f6d61aced

Subscribe to this mod's changes

neural-context is a skill published in the GitHub repository Yakoub-ai/neural-memory (1 stars, last pushed 5mo ago), licensed MIT. It adds 49 tokens to every session and 649 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.