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 navendubrajesh/context-management-for-agents --skill memory-systemsgit clone --depth 1 https://github.com/navendubrajesh/context-management-for-agentsWrote 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/navendubrajesh/context-management-for-agents/memory-systems)<a href="https://agentmods.dev/skills/navendubrajesh/context-management-for-agents/memory-systems"><img src="https://agentmods.dev/badge/skills/navendubrajesh/context-management-for-agents/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/navendubrajesh/context-management-for-agents/memory-systems"><img src="https://agentmods.dev/badge/skills/navendubrajesh/context-management-for-agents/memory-systems.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 | $0.00073 | $0.01543 |
| Opus 5 | $0.00036 | $0.00772 |
| Sonnet 5 | $0.00015 | $0.00309 |
| Haiku 4.5 | $0.00007 | $0.00154 |
Grade A, and why
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 12d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory System Design
Memory architectures determine how agents retain, retrieve, and update information across turns and sessions. The right memory design depends on the retention horizon (within-session vs. cross-session), the query pattern (keyword vs. semantic vs. structural), and the fidelity requirement (exact recall vs. gist). No single memory system dominates all use cases — production systems typically layer multiple strategies.
When to Activate
Activate this skill when:
- Designing cross-session knowledge persistence
- Choosing between vector RAG and knowledge graph approaches
- Building entity tracking systems for long-running agents
- Implementing scratchpad patterns for within-session state
- Evaluating memory system trade-offs for production deployment
Do not activate this skill for adjacent work owned by other skills:
- Filesystem-specific offloading and discovery patterns:
filesystem-context. - Compressing conversation history into handoff summaries:
context-compression. - Sharing state between agents in multi-agent systems:
multi-agent-patterns. - Designing hosted runtime environments for persistent agents:
hosted-agents. - Operational session learnings logged automatically: GStack
/learnand~/.gstack/projects/*/learnings.jsonl— use for tactical fixes; this skill designs durable memory architecture.
Core Concepts
Design memory around three horizons:
- Working memory (within-turn) — The context window itself. Information the model can directly attend to during inference. Limited by token capacity and attention mechanics.
- Short-term memory (within-session) — Scratchpads, plan files, accumulated tool outputs. Persists across turns but not across sessions. Implemented via message history or filesystem.
- Long-term memory (cross-session) — Knowledge bases, entity stores, learned preferences. Persists indefinitely. Implemented via databases, vector stores, or structured files.
The file-system-as-memory pattern bridges all three horizons: scratch files serve as working memory extensions, session files provide short-term persistence, and structured knowledge files provide long-term storage — all accessible through the same filesystem interface.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 143 lines · 73 tokens per session scan A 53e065a3d6bd
memory-systems is a skill published in the GitHub repository navendubrajesh/context-management-for-agents (2 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 1,543 once invoked, about $0.0004 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
AgentDB Memory Patterns
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.
pinecone-research
Agent RAG and long-term memory with Pinecone.
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…
llm-wiki
The foundational knowledge distillation pattern for building and maintaining an AI-powered Obsidian wiki. Based on Andrej Karpathy's LLM Wiki architecture. Use this skill whenever the user wants to understand the wiki pattern, set up a new knowledge base, or needs guidance on the three-layer architecture (raw sources…
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.