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 j4flmao/agent-skills --skill memory-systemsgit clone --depth 1 https://github.com/j4flmao/agent-skillsWrote 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/j4flmao/agent-skills/memory-systems)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/memory-systems"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/memory-systems/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/j4flmao/agent-skills/memory-systems"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/memory-systems.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 | $0.00128 | $0.01797 |
| Opus 5.5 | $0.00051 | $0.00719 |
| Sonnet 5.5 | $0.00026 | $0.00359 |
| Haiku 4.5 | $0.00013 | $0.00180 |
Grade A, and why
ai-agent-memory-systems 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Memory Systems
Purpose
An LLM is stateless between calls; anything the agent "remembers" is either placed in the context window or retrieved into it. Memory design is therefore a set of policies: what stays verbatim in context, what gets compressed, what is persisted to external stores, how it is retrieved, and when it is updated or deleted. Bad memory design shows up as forgotten constraints, contradictory facts, and leaked data between users.
Agent Protocol
Trigger
"agent memory", "long-term memory", "remember across sessions", "context window full", "conversation summarization", "user profile memory", "episodic memory", "memory leaks between users".
Input Context
- Session length and turn count; model context size.
- What must persist across sessions (preferences, facts, past task outcomes).
- Privacy/tenancy constraints and retention requirements.
- Existing storage (Postgres, Redis, vector DB).
Output Artifact
Memory design: tiers, schemas, write/read/eviction policies, isolation and retention rules.
Response Format
Working memory: pinned={...} window={n turns} compression={summary|drop}
Semantic store: {schema} retrieval={hybrid+rerank} k={n}
Episodic store: {schema} written on={event}
Profile/facts: {key-value schema} update={upsert w/ provenance}
Isolation: {tenant/user key} Retention: {ttl} Deletion: {API}
Completion Criteria
- Pinned context (instructions, goal, constraints) never evicted.
- Every stored memory carries owner id, source, timestamp.
- Retrieval is scoped by owner before similarity search.
- Conflicting facts resolved by recency/provenance, not duplicated.
- User-facing delete path exists.
Memory Tiers
| Tier | Lives in | Content | Retrieval | Typical store |
|---|---|---|---|---|
| Working | Context window | System prompt, goal, plan, recent turns, tool results | Always present | In-process |
| Semantic | External | Facts, documents, user profile | Similarity + filters | Postgres/pgvector, vector DB, KV |
| Episodic | External | Past tasks: what was tried, outcome, lesson | By task similarity or recency | Table + embeddings |
| Procedural | Prompt/code | Learned instructions, tool usage rules | Loaded at start | Versioned prompt files |
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 · +108 lines · +103 tokens per session 6ebd1f85438a
- 2mo ago First seen · 48 lines · 25 tokens per session scan A 708a2673e807
ai-agent-memory-systems is a skill published in the GitHub repository j4flmao/agent-skills (38 stars, last pushed 5d ago), licensed MIT. It adds 128 tokens to every session and 1,797 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
FORGE-data-compression
Context-window-aware data compression for long logs, code dumps, and multi-source evidence bundles. Compresses input to fit within model context limits while preserving semantic fidelity (F2 TRUTH ≥ 0.95). Supports streaming chunk-and-summarize pipelines. USE WHEN: "compress this log", "summarize before context…
langchain-orchestration
Comprehensive guide for building production-grade LLM applications using LangChain's chains, agents, memory systems, RAG patterns, and advanced orchestration.
hindsight-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).
agentmemory-agents
How agentmemory wires into host coding agents via the connect command. Use when installing agentmemory into a specific agent, when asked which agents are supported, or when a connect adapter writes the wrong config path.
memory-retain
Save what was learned to Hindsight long-term memory. Use when a task finishes, when the user states a fact, decision or preference, and when you discover something a later run or another Bot would need.
last30Days
Resolve "last30Days" to a concrete ISO date range relative to your run time — a rolling 30-day window ending today. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a "last 30 days" / trailing-month task…