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 Yakoub-ai/neural-memory --skill neural-contextgit clone --depth 1 https://github.com/Yakoub-ai/neural-memoryWrote 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/yakoub-ai/neural-memory/neural-context)<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.
<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>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 | $0.00049 | $0.00649 |
| Opus 5 | $0.00024 | $0.00324 |
| Sonnet 5 | $0.00010 | $0.00130 |
| Haiku 4.5 | $0.00005 | $0.00065 |
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.
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-contextmanually
This gives new sessions immediate deep context without re-discovery.
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.
- 9d ago First seen · 77 lines · 49 tokens per session scan A 5a2f6d61aced
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.
Other skills, from other repositories
memory
Retrieve relevant durable BB memories or save verified knowledge useful to future threads.
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
cross-session-handoff
Read, write, snapshot, and lock .arcgentic/state.yaml across planner, dev, audit, and optional test sessions.
recall
Must be used at the start of any non-trivial task involving code changes, debugging, repo exploration, file inspection, or environment/tooling investigation to surface stored guidance before analysis or tool use.
knowledge-priming-refiner
Facilitate a structured conversation to create a project-specific knowledge base document. Produces a knowledge-base.md that primes AI with the project's tech stack, architecture, trusted sources, and project structure. Use when the user says 'set up knowledge base', 'prime the project', 'onboard AI', 'create…
alive-inbox
Scan 03Inbox/ for unrouted files, present routing suggestions.