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 lingxling/awesome-skills-cn --skill agent-memory-systemsgit clone --depth 1 https://github.com/lingxling/awesome-skills-cnWrote 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/lingxling/awesome-skills-cn/agent-memory-systems)<a href="https://agentmods.dev/skills/lingxling/awesome-skills-cn/agent-memory-systems"><img src="https://agentmods.dev/badge/skills/lingxling/awesome-skills-cn/agent-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/lingxling/awesome-skills-cn/agent-memory-systems"><img src="https://agentmods.dev/badge/skills/lingxling/awesome-skills-cn/agent-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 | $0.00051 | $0.06847 |
| Opus 5 | $0.00026 | $0.03424 |
| Sonnet 5 | $0.00010 | $0.01369 |
| Haiku 4.5 | $0.00005 | $0.00685 |
Grade A, and why
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 11d 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 agent-memory-systems — 1,050 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 — 1,089 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Memory Systems
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them.
Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets.
The field is fragmented with inconsistent terminology. We use the CoALA cognitive architecture framework: semantic memory (facts), episodic memory (experiences), and procedural memory (how-to knowledge).
Principles
- Memory quality = retrieval quality, not storage quantity
- Chunk for retrieval, not for storage
- Context isolation is the enemy of memory
- Right memory type for right information
- Decay old memories - not everything should be forever
- Test retrieval accuracy before production
- Background memory formation beats real-time
Capabilities
- agent-memory
- long-term-memory
- short-term-memory
- working-memory
- episodic-memory
- semantic-memory
- procedural-memory
- memory-retrieval
- memory-formation
- memory-decay
Scope
- vector-database-operations → data-engineer
- rag-pipeline-architecture → llm-architect
- embedding-model-selection → ml-engineer
- knowledge-graph-design → knowledge-engineer
Tooling
Memory_frameworks
- LangMem (LangChain) - When: LangGraph agents with persistent memory Note: Semantic, episodic, procedural memory types
- MemGPT / Letta - When: Virtual context management, OS-style memory Note: Hierarchical memory tiers, automatic paging
- Mem0 - When: User memory layer for personalization Note: Designed for user preferences and history
Vector_stores
- Pinecone - When: Managed, enterprise-scale (billions of vectors) Note: Best query performance, highest cost
- Qdrant - When: Complex metadata filtering, open-source Note: Rust-based, excellent filtering
- Weaviate - When: Hybrid search, knowledge graph features Note: GraphQL interface, good for relationships
- ChromaDB - When: Prototyping, small/medium apps Note: Developer-friendly, ~20ms p50 at 100K vectors
- pgvector - When: Already using PostgreSQL, simpler setup Note: Good for <1M vectors, familiar tooling
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.
- 11d ago First seen · 1,089 lines · 51 tokens per session scan A 2003324855b6
agent-memory-systems is a skill published in the GitHub repository lingxling/awesome-skills-cn (281 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 6,847 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to agent-memory-systems, differing in 1,050 lines, and is treated as a copy.
Other skills, from other repositories
log-session
Append a structured entry to the project's session log (docs/LOGS.md): what was done this session, files touched, decisions taken, and the next step — so the next session (or another person) can pick up the thread without re-reading git history. Run it before /clear, before closing Claude Code, or at any natural…
context-compression
REDUCING context size — summarization strategies, anchored iterative summarization, tokens-per-task optimization, compaction triggers, and probe-based evaluation. Use when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions structured…
context-degradation
Diagnosing context FAILURES — lost-in-middle, poisoning, distraction, confusion, and clash patterns with model-agnostic measurement workflows. Use when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation…
context-fundamentals
Foundational theory of context engineering — what context IS, how attention works, progressive disclosure principles, and context budgeting basics. Use when the user asks to "understand context", "explain context windows", "learn context engineering", or discusses context components, attention mechanics, or context…
context-optimization
EXTENDING effective context capacity — KV-cache optimization, observation masking, context partitioning, and retrieval strategies. Use when the user asks to "optimize context", "implement KV-cache", "partition context", "mask observations", or mentions extending context capacity or cache-friendly prompt design. NOT…
memory-integration
Use to maintain context across sessions - integrates episodic-memory for conversation recall and mcpmemory knowledge graph for persistent facts.