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 khalilbenaz/claude-skills-collection --skill memory-designergit clone --depth 1 https://github.com/khalilbenaz/claude-skills-collectionWrote 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/khalilbenaz/claude-skills-collection/memory-designer)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/memory-designer"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/memory-designer/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/khalilbenaz/claude-skills-collection/memory-designer"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/memory-designer.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 | $0.00082 | $0.02289 |
| Opus 5.5 | $0.00033 | $0.00916 |
| Sonnet 5.5 | $0.00016 | $0.00458 |
| Haiku 4.5 | $0.00008 | $0.00229 |
Grade A, and why
memory-designer 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 1mo 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Memory Designer
Quand utiliser ce skill
Utilise ce skill pour concevoir ou améliorer le système de mémoire d'un agent IA dès que :
- l'agent doit se souvenir d'informations au-delà d'une seule conversation ;
- l'historique de conversation dépasse ou menace de dépasser la fenêtre de contexte ;
- plusieurs agents doivent partager une base de connaissance commune ;
- l'utilisateur se plaint que "l'agent ne se souvient pas".
Étape 1 — Diagnostic des besoins
Avant de choisir un backend, réponds à ces questions :
| Question | Réponse → choix |
|---|---|
| Les souvenirs doivent-ils survivre au redémarrage du processus ? | Oui → persistence ; Non → in-memory suffit |
| Plusieurs sessions/utilisateurs partagent-ils la mémoire ? | Oui → backend centralisé (DB/cloud) |
| Le volume de souvenirs dépasse-t-il 10 k entrées ? | Oui → vector store dédié (Pinecone, Weaviate) |
| La latence de retrieval est-elle critique (< 100 ms) ? | Oui → Redis ou FAISS local |
| Confidentialité par utilisateur requise ? | Oui → namespace/user_id strict obligatoire |
Étape 2 — Choisir les types de mémoire à implémenter
Chaque type a un rôle distinct ; ne pas tout mettre dans le même bucket.
| Type | Durée | Contenu typique | Backend |
|---|---|---|---|
| Working / short-term | Session en cours | Messages de la conversation | Buffer in-process |
| Episodic | Long terme | Interactions passées horodatées | Vector store + metadata |
| Semantic | Long terme | Faits, préférences utilisateur | Vector store ou SQL |
| Procedural | Persistant | Workflows mémorisés, "comment faire X" | Fichier structuré ou DB |
Règle de sélection : implémente working en priorité, puis episodic si l'utilisateur a besoin de continuité cross-session, semantic si l'agent doit raisonner sur des faits durables.
Étape 3 — Working memory (gestion de la fenêtre de contexte)
Objectif : maintenir un historique utile sans dépasser le budget de tokens.
Stratégie 1 — Sliding window (simple, prototypage)
def sliding_window(messages: list, max_messages: int = 20) -> list:
system = [m for m in messages if m["role"] == "system"]
rest = [m for m in messages if m["role"] != "system"]
return system + rest[-max_messages:]
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.
- 1mo ago First seen · 225 lines · 82 tokens per session scan A 44922d3fe8f7
memory-designer is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (27 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 2,289 once invoked, about $0.0003 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
model-architecture-litgpt
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
liter-llm-running-the-proxy
Use when running the liter-llm api OpenAI-compatible gateway — virtual keys, per-key rate limits, budgets, cost tracking, and model routing. Covers the TOML config and the 22 REST endpoints.
rag-patterns
RAG: embeddings, chunking, hybrid search (BM25+vector), reranking, CRAG, multi-hop. Triggers: RAG, embedding, pgvector, Qdrant, Pinecone, Weaviate, reranker, semantic search.
evaluate
Evaluates RAG retrieval and LLM-as-judge metrics (faithfulness, relevancy, context precision). Triggers: measure RAG quality, knowledge gap, RAG eval, golden dataset.
json-mode-patterns
Structured JSON output from Claude: native JSON schemas, strict tools, local validation, refusal and truncation handling. Triggers: JSON mode, structured output, schema validation, JSON parsing.
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.