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 roedyrustam/vibes-plug --skill agentic-memory-architectgit clone --depth 1 https://github.com/roedyrustam/vibes-plugWrote 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/roedyrustam/vibes-plug/agentic-memory-architect)<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/agentic-memory-architect"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/agentic-memory-architect/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/roedyrustam/vibes-plug/agentic-memory-architect"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/agentic-memory-architect.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 | $0.00112 | $0.06903 |
| Opus 5.5 | $0.00045 | $0.02761 |
| Sonnet 5.5 | $0.00022 | $0.01381 |
| Haiku 4.5 | $0.00011 | $0.00690 |
Grade A, and why
agentic-memory-architect 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 5d 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 — 800 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Memory Architect & Episodic Memory Guide
English
Orchestration & Integration
Connects and orchestrates with:
multi-agent-orchestration— shared memory state across agent swarmspydantic-ai-expert— type-safe memory injection into Pydantic AI agentssession-memory-manager— short-term session checkpoint layervector-db-rag-expert— pgvector/HNSW for long-term episodic retrievaldatabase-orm-expert— Prisma/Drizzle schema for memory persistenceai-llm-integration-expert— context window injection at inference timezero-to-prod-orchestrator— memory layer provisioned in Phase 2 (Foundation)
Purpose
Design and implement persistent, multi-tier memory systems for autonomous AI agents that transcend simple context windows. Enable agents to remember users across sessions, recall past decisions, maintain knowledge graphs, and operate with human-like episodic continuity — all while remaining within token budget constraints.
Memory Tier Architecture
┌─────────────────────────────────────────────────────────────────┐
│ AGENT MEMORY HIERARCHY │
├─────────────────────────────────────────────────────────────────┤
│ TIER 0 │ In-Context Working Memory (current conversation) │
│ │ ≤ 128K tokens │ Lost on session end │
│ │ Implementation: Raw messages array in LLM call │
├─────────────────────────────────────────────────────────────────┤
│ TIER 1 │ Session Memory (within-session graph) │
│ │ Hours to days │ Redis / Zep session store │
│ │ Implementation: Zep v2 session + entity graph │
├─────────────────────────────────────────────────────────────────┤
│ TIER 2 │ Episodic Memory (cross-session, user-scoped) │
│ │ Weeks to months │ Mem0 + pgvector HNSW │
│ │ Implementation: Mem0 Memory.add() / Memory.search() │
├─────────────────────────────────────────────────────────────────┤
│ TIER 3 │ Semantic / Procedural Memory (agent knowledge base) │
│ │ Permanent │ pgvector + structured KB tables │
│ │ Implementation: RAG pipeline over domain knowledge │
└─────────────────────────────────────────────────────────────────┘
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.
- 5d ago Changed 78c546c0b6a5
- 8d ago Changed · +747 lines · +51 tokens per session 244386131a85
- 10d ago Changed 362bc314d485
- 11d ago Changed b459d5300dc4
- 13d ago Changed c8e9181f3de6
- 19d ago First seen · 53 lines · 61 tokens per session scan A 490091a8220f
agentic-memory-architect is a skill published in the GitHub repository roedyrustam/vibes-plug (75 stars, last pushed 5d ago), licensed MIT. It adds 112 tokens to every session and 6,903 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-25.
Other skills, from other repositories
context-engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
self-improve
Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the appropriate knowledge layer (project AGENTS.md, auto memory, existing skills, or new skills). Use when the user asks to "self-improve", "distill this session", "distill past sessions", "sweep past…
recall-rationale
Recall why a past change was made by locating the Claude Code transcript that produced it. Use when the user asks to "recall the rationale", "find the rationale", "look up the rationale", "why did I do X", "why did we do X", "why was this changed", or "find the transcript for this commit".
vibe-reflect-and-compound
Captures reusable knowledge after work is done — learnings from feedback or failures, resolved bugs (symptom, root cause, prevention), and recurring code patterns — into the project's persistent memory file. Use after feedback, a non-trivial bug fix, a failed attempt, or the third repetition of a pattern.
context-level
Report how much of the session's context window remains. Use when the user asks "how much context is left", "check the context level", "how full is the context window", or "is context running low".
mm-save-session
An end-of-session recorder for Claude Code that saves the conversation summary and project state in Obsidian notes. Obsidian is a note-taking app that stores information as files.