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-querygit 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-query)<a href="https://agentmods.dev/skills/yakoub-ai/neural-memory/neural-query"><img src="https://agentmods.dev/badge/skills/yakoub-ai/neural-memory/neural-query/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-query"><img src="https://agentmods.dev/badge/skills/yakoub-ai/neural-memory/neural-query.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 | $0.00025 | $0.00347 |
| Opus 5 | $0.00013 | $0.00173 |
| Sonnet 5 | $0.00005 | $0.00069 |
| Haiku 4.5 | $0.00003 | $0.00035 |
Grade A, and why
neural-query 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.
What it actually says
Neural Memory — Query
Search the neural knowledge graph for functions, classes, modules, or concepts.
What this does
Returns layered results:
- Short summary: Understand what a node does at a glance
- Node ID: Use with
/neural-inspectto go deeper - Location: File path and line numbers
How to call
Via MCP tool (neural-memory configured as MCP server in Claude Code):
Tool: neural_query
{ "query": "your search term", "limit": 10 }
Via Python (working directly in the project):
import asyncio
from neural_memory.server import neural_query, QueryInput
asyncio.run(neural_query(QueryInput(query="your search term")))
Parameters
| Parameter | Type | Default | Description |
|---|---|---|---|
query |
str | required | Function name, class name, or concept keyword |
project_root |
str | "." |
Project root directory |
limit |
int | 10 |
Max results (1–50) |
language |
str | null |
Filter results to a specific language (e.g. 'python', 'typescript', 'rust') |
Results are ranked by importance score — the most connected, public-facing code appears first.
Use /neural-inspect on any result's node_id to see full context, callers, callees, and source code.
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 · 43 lines · 25 tokens per session scan A fdd89123da43
neural-query is a skill published in the GitHub repository Yakoub-ai/neural-memory (1 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 347 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.
Other skills, from other repositories
deploy-setup
Wire up a freshly scaffolded Starter Series project for its first release — detect the template, register required GitHub secrets, set up OIDC trusted publishing where applicable, and trigger the first CD run. Pairs with the create skill (you scaffold first, then run this).
create
Scaffold a new project from the Starter Series templates (MCP server, Discord/Telegram bot, VS Code / browser extension, Electron, React Native, Cloudflare Pages, npm package, Docker deploy).
landing-build
LandingForge build orchestrator — manufactures a SaaS, dev-tool, or B2C consumer-app landing page to a spec by running gated specialist phases 1-8 end to end, scoring the result and looping to ship. Phases 1-4 (strategy -> copy -> design -> build) each spawn an lp- agent, write an artifact to .landingforge/ /, and…
landing-copy
Phase 2 of LandingForge, standalone — turn a committed strategy brief into full, section-by-section persuasive landing copy: every block keyed to the fixed section skeleton, tagged with the framework that produced it (PAS / BAB / house-voice), and cleared through the specificity linter so no reversible filler or…
landing-critique
Audit and 10-star-score ANY existing landing page (live URL or local path) against the same four-axis LandingForge rubric the generator targets. Inspects the rendered page with the bundled browser, delegates the Discoverability axis to claude-seo (with a labeled inline fallback), scores via the lp-scorer contract, and…
landing-discoverability
Phase 5 of LandingForge, standalone — run ONLY the SEO/GEO discoverability pass on a built landing page (local site/ path or live URL) and write seo-report.md. Spawns the lp-discoverability agent, which delegates the schema / GEO / technical SEO axis to claude-seo (seo-schema, seo-geo, seo-technical) when installed…