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 agentmods add skills/mickeyyaya/refactoring-skills/agent-memory-patternsnpx skills add mickeyyaya/refactoring-skills --skill agent-memory-patternsgit clone --depth 1 https://github.com/mickeyyaya/refactoring-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/mickeyyaya/refactoring-skills/agent-memory-patterns)<a href="https://agentmods.dev/skills/mickeyyaya/refactoring-skills/agent-memory-patterns"><img src="https://agentmods.dev/badge/skills/mickeyyaya/refactoring-skills/agent-memory-patterns.svg" alt="Measured on agentmods" 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 | $0.00076 | $0.03887 |
| Opus 5 | $0.00038 | $0.01944 |
| Sonnet 5 | $0.00015 | $0.00777 |
| Haiku 4.5 | $0.00008 | $0.00389 |
Grade A, and why
agent-memory-patterns 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 6d 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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Memory Patterns
Overview
Memory is the foundation of agent intelligence. Without structured memory, agents repeat mistakes, lose context across sessions, and cannot build compound knowledge over time. A well-designed memory system determines what the agent remembers, how it retrieves relevant context, and when it safely forgets.
When to use: Designing a stateful AI agent or autonomous workflow; reviewing agent code for context management; evaluating retrieval latency or cost; any system where an agent must persist knowledge across conversation turns, sessions, or agent boundaries.
Quick Reference
| Memory Type | Storage | Retrieval Strategy | Lifetime | Use Case |
|---|---|---|---|---|
| Short-term | Context window (in-memory) | Direct inclusion — no retrieval needed | Single session | Active conversation, current task state |
| Working | Scratchpad / todo file | Sequential read — agent writes and reads directly | Task duration | Reasoning steps, partial results, sub-goals |
| Long-term episodic | Vector DB with timestamps | Embedding similarity + recency weighting | Months to permanent | Past interactions, specific sessions, event log |
| Long-term semantic | Structured store / knowledge graph | Keyword or concept-graph traversal | Permanent until invalidated | Facts, entities, domain knowledge |
| Procedural | File store / instinct YAML | Template match on task type | Permanent | Reusable patterns, learned workflows, instincts |
Memory Type Taxonomy
Short-term Memory (Context Window)
Short-term memory is the active context window — everything currently visible to the model. It is the fastest and most reliable form of retrieval because no lookup is required.
Capacity constraint: Modern models support 8K–200K tokens, but the effective working range for coherent reasoning is typically 20–50K tokens. Beyond that, attention degrades on early content ("lost in the middle" problem).
Management strategy: Use a token budget allocator that reserves slots for system prompt, tool definitions, recent history, and retrieved context. Drop oldest turns first when the budget is exceeded.
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.
- 6d ago First seen · 369 lines · 76 tokens per session scan A 6d244952b783
agent-memory-patterns is a skill published in the GitHub repository mickeyyaya/refactoring-skills (6 stars, last pushed 5mo ago), licensed MIT. It adds 76 tokens to every session and 3,887 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.