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 agentmods add skills/spencermarx/open-code-review/v3-memory-unificationnpx skills add spencermarx/open-code-review --skill v3-memory-unificationgit clone --depth 1 https://github.com/spencermarx/open-code-reviewWrote 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/spencermarx/open-code-review/v3-memory-unification)<a href="https://agentmods.dev/skills/spencermarx/open-code-review/v3-memory-unification"><img src="https://agentmods.dev/badge/skills/spencermarx/open-code-review/v3-memory-unification.svg" alt="Measured on agentmods" 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 | $0.00051 | $0.01172 |
| Opus 5 | $0.00026 | $0.00586 |
| Sonnet 5 | $0.00010 | $0.00234 |
| Haiku 4.5 | $0.00005 | $0.00117 |
Grade A, and why
V3 Memory Unification 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 yesterday.
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.
This is a copy
100% identical to V3 Memory Unification — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
V3 Memory Unification
What This Skill Does
Consolidates disparate memory systems into unified AgentDB backend with HNSW vector search, achieving 150x-12,500x search performance improvements while maintaining backward compatibility.
Quick Start
# Initialize memory unification
Task("Memory architecture", "Design AgentDB unification strategy", "v3-memory-specialist")
# AgentDB integration
Task("AgentDB setup", "Configure HNSW indexing and vector search", "v3-memory-specialist")
# Data migration
Task("Memory migration", "Migrate SQLite/Markdown to AgentDB", "v3-memory-specialist")
Systems to Unify
Legacy Systems → AgentDB
┌─────────────────────────────────────────┐
│ • MemoryManager (basic operations) │
│ • DistributedMemorySystem (clustering) │
│ • SwarmMemory (agent-specific) │
│ • AdvancedMemoryManager (features) │
│ • SQLiteBackend (structured) │
│ • MarkdownBackend (file-based) │
│ • HybridBackend (combination) │
└─────────────────────────────────────────┘
↓
┌─────────────────────────────────────────┐
│ 🚀 AgentDB with HNSW │
│ • 150x-12,500x faster search │
│ • Unified query interface │
│ • Cross-agent memory sharing │
│ • SONA learning integration │
└─────────────────────────────────────────┘
Implementation Architecture
Unified Memory Service
class UnifiedMemoryService implements IMemoryBackend {
constructor(
private agentdb: AgentDBAdapter,
private indexer: HNSWIndexer,
private migrator: DataMigrator
) {}
async store(entry: MemoryEntry): Promise<void> {
await this.agentdb.store(entry);
await this.indexer.index(entry);
}
async query(query: MemoryQuery): Promise<MemoryEntry[]> {
if (query.semantic) {
return this.indexer.search(query); // 150x-12,500x faster
}
return this.agentdb.query(query);
}
}
HNSW Vector Search
class HNSWIndexer {
constructor(dimensions: number = 1536) {
this.index = new HNSWIndex({
dimensions,
efConstruction: 200,
M: 16,
speedupTarget: '150x-12500x'
});
}
async search(query: MemoryQuery): Promise<MemoryEntry[]> {
const embedding = await this.embedContent(query.content);
const results = this.index.search(embedding, query.limit || 10);
return this.retrieveEntries(results);
}
}
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.
- yesterday First seen · 174 lines · 51 tokens per session scan A 4853ec2fec84
V3 Memory Unification is a skill published in the GitHub repository spencermarx/open-code-review (355 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 51 tokens to every session and 1,172 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to V3 Memory Unification, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
agent-v3-memory-specialist
Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist.
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…
memory-config
Diagnose and configure MemSearch memory behavior. Use when the user asks about MemSearch configuration, plugin summarization, PROJECT.md/USER.md maintenance, memory directories, index health, provider routing, prompt files, or migration/compatibility questions.
vector-memory
HNSW vector search for pattern similarity retrieval and knowledge graph maintenance with PageRank scoring, community detection, and 3-tier memory management.
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
memory-lancedb
LanceDB-backed vector memory for high-volume embedding and retrieval workloads.