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 ayushcodes10/echo-mem --skill v3-memory-unificationgit clone --depth 1 https://github.com/ayushcodes10/echo-memWrote 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/ayushcodes10/echo-mem/v3-memory-unification)<a href="https://agentmods.dev/skills/ayushcodes10/echo-mem/v3-memory-unification"><img src="https://agentmods.dev/badge/skills/ayushcodes10/echo-mem/v3-memory-unification/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/ayushcodes10/echo-mem/v3-memory-unification"><img src="https://agentmods.dev/badge/skills/ayushcodes10/echo-mem/v3-memory-unification.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 | $0.00051 | $0.01172 |
| Opus 5.5 | $0.00020 | $0.00469 |
| Sonnet 5.5 | $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 1mo 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.
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.
- 1mo ago First seen · 174 lines · 51 tokens per session scan A 4853ec2fec84
V3 Memory Unification is a skill published in the GitHub repository ayushcodes10/echo-mem (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 51 tokens to every session and 1,172 once invoked, about $0.0002 per session on Opus 5.5. 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
omnigraph
Operate OmniGraph graphs and deployments. Use for .pg schemas, .gq queries, OmniGraph CLI commands, file:///s3:///az:// graph URIs, cluster.yaml, operator config, bearer-authenticated servers, graph-backed knowledge or memory, Blob values, embeddings, branches, commits, and change feeds. Apply especially before schema…
mesh-memory
Self-hosted semantic memory for AI agents via MCP. Save worklogs, decisions, and notes, then recall them across sessions by meaning, not keyword. Postgres + pgvector with auto-tagging.
setup
Set up memex with provisioned Postgres (RDS + pgvector), AGENTS.md injection, first import.
databases
Use when creating, changing, or reviewing MongoDB/PostgreSQL/SQLite database work in a real repository, including schema, models, migrations, queries, indexes, transactions, connection config, backup/restore assumptions, dual-database desktop sync, or performance; follow repo-native tooling and meet the production…
squish
ALWAYS use this skill when working with agents, memory, context, persistence, or AI agent state. Use when the user mentions: 'the agent forgot', 'save this', 'remember that', 'context is lost', 'memory', 'MCP server', 'agent memory', 'persistent memory', 'session context', 'project context', 'recall', 'remember'…
squish-memory
Persistent memory system for Claude Code. Use when you need to store, recall, or search project memories, facts, decisions, and learnings across sessions. Triggers on: remember, recall, memory, forget, search memories, store context, project knowledge, what did we decide, previous conversation.