Borrowing it
Nothing to install: this file belongs to Smart-AI-Memory/attune-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Smart-AI-Memory/attune-ai/main/.agents/skills/memory-and-context/SKILL.mdgit clone --depth 1 https://github.com/Smart-AI-Memory/attune-aiWrote 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/smart-ai-memory/attune-ai/memory-and-context)<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/memory-and-context"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/memory-and-context.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.02024 |
| Opus 5 | $0.00019 | $0.01012 |
| Sonnet 5 | $0.00008 | $0.00405 |
| Haiku 4.5 | $0.00004 | $0.00202 |
Grade A, and why
memory-and-context 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 4d 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory and Context
IMPORTANT: Start your response with a context preamble.
Call help_lookup(topic="memory", mode="preamble") and
display the returned preamble text as a blockquote. Then
tell the user they can say "tell me more" for a step-by-step
guide, or answer the scoping questions below to proceed.
If the MCP call fails, fall back to:
Memory and Context — Stores and retrieves persistent context across sessions — notes, preferences, project state.
Scoping
Before running, ask:
- Operation: "What do you need? Store, retrieve, search, or forget?"
- Key/query: "What key or search term?"
- Classification (store only): "PUBLIC, INTERNAL, or SENSITIVE?"
Execution
Shared command workspace (preferred)
Open adapter memory-and-context with the selected operation and scoped
arguments. Present its widget or returned Markdown and collect its bound
action before calling the existing memory tool. Store and forget are external
writes and require explicit confirmation; retrieve and search remain
read-only. Publish the exact tool response as operation_result.
After a successful store or forget, follow the workspace's returned
memory_retrieve verification request and publish it as
verification_result. Store succeeds only when the same value and
classification are retrieved; forget succeeds only when the post-delete read
misses. Never render stored values—especially SENSITIVE values—in the
workspace. A failed backend call must say “did not complete.” Preserve these
decisions and verification receipts in compact text when the shared tools are
unavailable.
Based on the user's answer, call the appropriate MCP tool:
- Store:
memory_store(key, value, classification) - Retrieve:
memory_retrieve(key) - Search:
memory_search(query, pattern_type) - Forget:
memory_forget(key, scope)
attune-ai's memory system sits ABOVE Anthropic's native memory features. It provides security-classified storage, cross-agent pattern sharing, and a structured pattern lifecycle that native memory does not offer. Use the decision table below to determine which system to use for a given task.
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.
- 4d ago Changed · +17 lines 8d15733d6118
- 8d ago First seen · 281 lines · 38 tokens per session scan A cef801a991ad
memory-and-context is a skill published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 2,024 once invoked, about $0.0002 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
agent-carnet
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
taiyi-compress
A workflow tool for shrinking large coding-agent conversations and work files into shorter context notes. It can also coordinate separate agents for parallel development and create handoff notes for continuing work in a new session.
cross-task-learner
Enable agent loops to learn from similar past tasks and share patterns across loops.
ralph-memory
Manage Al semantic memory entries — list, query, and clear lessons learned across loop iterations.
reflection-injection
Inject relevant past reflections into agent context at iteration start so agents learn from prior mistakes without repeating them.