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 vizra-ai/vizra-adk --skill vizra-memorygit clone --depth 1 https://github.com/vizra-ai/vizra-adkWrote 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/vizra-ai/vizra-adk/vizra-memory)<a href="https://agentmods.dev/skills/vizra-ai/vizra-adk/vizra-memory"><img src="https://agentmods.dev/badge/skills/vizra-ai/vizra-adk/vizra-memory/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/vizra-ai/vizra-adk/vizra-memory"><img src="https://agentmods.dev/badge/skills/vizra-ai/vizra-adk/vizra-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00024 | $0.02519 |
| Opus 5 | $0.00012 | $0.01260 |
| Sonnet 5 | $0.00005 | $0.00504 |
| Haiku 4.5 | $0.00002 | $0.00252 |
Grade A, and why
Vizra ADK Memory System 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 12d 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 — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vizra ADK Memory System
Vizra ADK provides multiple memory types for agents to maintain context across conversations and sessions.
Memory Types
| Type | Purpose | Persistence |
|---|---|---|
| Session Memory | Conversation history within a session | Session lifetime |
| User Memory | Information tied to a specific user | Permanent |
| Vector Memory | Semantic search and RAG | Permanent |
Basic Memory Usage
Session-Based Memory
Conversation history persists within a session:
use App\Agents\MyAgent;
$sessionId = 'conversation-123';
// First message in session
$response1 = MyAgent::run('My name is John')
->forUser($user)
->withSession($sessionId)
->go();
// Later in the same session - agent remembers context
$response2 = MyAgent::run('What is my name?')
->forUser($user)
->withSession($sessionId)
->go(); // Will remember "John"
User-Based Memory
Memory persists across all sessions for a user:
// First conversation
$response1 = MyAgent::run('I prefer dark mode and short responses')
->forUser($user)
->go();
// New conversation - user preferences are remembered
$response2 = MyAgent::run('Help me with my project')
->forUser($user)
->go(); // Agent remembers preferences
Memory Tools
MemoryTool
Allow agents to explicitly store and retrieve memories:
use Vizra\VizraADK\Tools\MemoryTool;
class PersonalAssistantAgent extends BaseLlmAgent
{
protected string $name = 'personal_assistant';
protected string $instructions = <<<'INSTRUCTIONS'
You are a personal assistant. Use the memory tool to:
- Remember important facts the user tells you
- Recall information when asked
- Update memories when information changes
INSTRUCTIONS;
protected array $tools = [
MemoryTool::class,
];
}
The agent can then use commands like:
remember: User's birthday is March 15recall: birthdayforget: old address
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.
- 12d ago First seen · 433 lines · 24 tokens per session scan A b70dfcbed7ac
Vizra ADK Memory System is a skill published in the GitHub repository vizra-ai/vizra-adk (295 stars, last pushed 18d ago), licensed MIT. It adds 24 tokens to every session and 2,519 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 2026-08-30.
Other skills, from other repositories
knowledge-graph-builder
Activates KnowledgeGraph — an expert in building, querying, and reasoning over knowledge graphs. Use when you need entity extraction, relationship mapping, ontology design, Neo4j/RDF graph construction, graph-RAG pipelines, or complex multi-hop reasoning over structured knowledge.
rag-architect
Activates the RAG-Architect agent for designing and building Retrieval-Augmented Generation systems. Use this skill when you need to build a document Q&A system, design a knowledge base with semantic search, set up vector stores (Chroma, Pinecone, pgvector), implement hybrid retrieval (dense + BM25 sparse), add…
vector-db
Vector database expert for embeddings, similarity search, RAG patterns, and indexing strategies.
pinecone-research
Agent RAG and long-term memory with Pinecone.
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…
hive.context-preservation
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.