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 hajekim/agentic-design-patterns-skills --skill memory-managementgit clone --depth 1 https://github.com/hajekim/agentic-design-patterns-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/hajekim/agentic-design-patterns-skills/memory-management)<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-skills/memory-management"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-skills/memory-management/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/hajekim/agentic-design-patterns-skills/memory-management"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-skills/memory-management.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 | $0.00418 | $0.03503 |
| Opus 5 | $0.00209 | $0.01751 |
| Sonnet 5 | $0.00084 | $0.00701 |
| Haiku 4.5 | $0.00042 | $0.00350 |
Grade A, and why
memory-management 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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- memory-management — 100% identical, 3 lines differ
How it starts
The opening of the file, as written. The whole thing — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Management Pattern
Overview
The Memory Management Pattern enables agents to retain and utilize information from past interactions, observations, and learning experiences. Without memory, every agent turn is isolated — the agent has no awareness of prior context. With effective memory management, agents can maintain conversation continuity, personalize responses, track task progress, and improve over time.
Core Principle: Give agents the ability to remember — short-term for the current interaction, long-term for knowledge that persists across sessions.
When This Skill Applies
Activate this pattern when:
- Agents must maintain context across multiple conversation turns
- User preferences or past behaviors should influence future responses
- Multi-step tasks require tracking progress and intermediate results
- Agents need to recall information from previous sessions
- Personalization and continuity are key user experience requirements
- RAG (Retrieval-Augmented Generation) is needed for knowledge-grounded responses
Rule of thumb: If an agent needs to "remember" anything beyond the current prompt — use Memory Management.
Memory Types
Short-Term Memory (Contextual Memory)
- Lives within the context window of the current LLM call
- Contains: recent messages, tool outputs, agent reflections, session state
- Limited capacity: context windows have token limits
- Ephemeral: lost when the session ends
- Management strategies: summarize older segments, prioritize key information, use long-context models
Long-Term Memory (Persistent Memory)
- Stored outside the agent's immediate context in external systems
- Storage options: databases, knowledge graphs, vector databases
- Semantic search: vector embeddings enable similarity-based retrieval
- Persistent: survives session terminations, restarts, and time gaps
- Use cases: user preferences, learned knowledge, historical records
DEFINE → PLAN → ACTION Workflow
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.
- 9d ago First seen · 367 lines · 418 tokens per session scan A 77687048e4ec
memory-management is a skill published in the GitHub repository hajekim/agentic-design-patterns-skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 418 tokens to every session and 3,503 once invoked, about $0.0021 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 2026-08-31.
Other skills, from other repositories
iterative-retrieval
Pattern for progressively refining context retrieval to solve the subagent context problem.
wiki
Daniel's Zettelkasten knowledge engine — 9 verbs (ingest/query/save/lint/manage/synthesize/critique/compare/eli5) unified in one namespace. Realizes Karpathy's LLM Wiki Compiler·Runner cycle beyond simple storage: synthesis, self-critique, comparison, and plain explanation. Triggers on: "/wiki", "wiki ingest", "wiki…
knowledge-ops
Knowledge base management, ingestion, sync, and retrieval across multiple storage layers (local files, MCP memory, vector stores, Git repos). Use when the user wants to save, organize, sync, deduplicate, or search across their knowledge systems.
ck
Persistent per-project memory for Gemini CLI. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions.
memory-management
This skill should be used when the user wants to "persist agent state", "remember past conversations", "short-term memory", "long-term memory", "session management", "vector database for agents", "agent memory", "context window management", "store user preferences", "recall previous interactions", "stateful agents"…
ai-agents-architect
Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration.