Acontext is an open-source memory layer for AI agents that records useful knowledge from agent runs as editable skill files. Agent builders use it to preserve, inspect, share, and reuse what agents learn across frameworks, and the catalogue includes hooks, skills, instructions, rules, an MCP, and a plugin for working with it.
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 memodb-io/Acontext --skill user-general-factsgit clone --depth 1 https://github.com/memodb-io/AcontextWrote 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/memodb-io/acontext/user-general-facts)<a href="https://agentmods.dev/skills/memodb-io/acontext/user-general-facts"><img src="https://agentmods.dev/badge/skills/memodb-io/acontext/user-general-facts/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/memodb-io/acontext/user-general-facts"><img src="https://agentmods.dev/badge/skills/memodb-io/acontext/user-general-facts.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 | $0.00015 | $0.00397 |
| Opus 5 | $0.00008 | $0.00198 |
| Sonnet 5 | $0.00003 | $0.00079 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
user-general-facts 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 9d 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.
What it actually says
User General Facts
Learn and recall general facts about the user — preferences, background, goals, and other persistent information that helps personalize interactions.
File Structure
Organize facts into topic-specific files named [TOPIC].md. Create a new file when a new category of facts is discovered; update the existing file when new facts are found for that topic.
File Format: [TOPIC].md
# [Topic Name]
- [third-person fact about the user, e.g. "The user prefers TypeScript"]
- [third-person fact about the user, e.g. "The user's name is Gus"]
Example Topics
coding-preferences.md— preferred languages, frameworks, code style conventionstech-stack.md— tools, services, and infrastructure the user works withcommunication-style.md— how the user prefers to interact (concise vs. detailed, etc.)work-context.md— role, team, projects, company detailsgoals.md— current objectives, priorities, long-term goals
Guidelines
- One topic per file — do not mix unrelated facts in the same file
- Use lowercase kebab-case for file names (e.g.,
coding-preferences.md) - Choose clear, broad topic names
- Update existing facts when corrections are provided — do not keep stale information
- Keep facts concise, objective, and actionable
- Only record facts explicitly stated or clearly demonstrated by the user — do not speculate
- Always use third-person pronouns when referring to the user. Write "The user prefers X" or "The user's name is Y", never "I prefer X" or "My name is Y". These files are read by agents who would mistake first-person "I" as referring to themselves.
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.
- 9d ago First seen · 39 lines · 15 tokens per session scan A c926a60f74fd
user-general-facts is a skill published in the GitHub repository memodb-io/Acontext (3,687 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 397 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
02-project-memory
Build the project's memory of its architecture, conventions, and decisions, and wire it into your AI tools. Use when the user wants to set up or refresh project memory, or rewire it into a tool. Not for editing one existing memory file.
10-learn
Capture durable project learnings. Use when the user wants to remember, record, or formalize a decision, convention, lesson, pitfall, reusable workflow, or review finding. Not for preferences or temporary notes.
writing
A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.
knowledge-base
Create and maintain a Markdown knowledge base that any AI agent can read, search, and update. Use when the user wants to start a knowledge base, add or update notes, organize docs/notes for an agent or LLM to consume, build an index of notes, or run a cleanup/maintenance pass on an existing MD knowledge base. Triggers…
task-agent-eliza-bridge
Use when spawning a Claude Code, Codex, Gemini, Aider, or other CLI task agent whose work needs parent Eliza runtime context. Covers the read-only loopback bridge for character, room, memory, and active workspace state.
aatmf-t04-memory-manipulation
AATMF T4 — Multi-Turn & Memory Manipulation. Persistent memory injection, conversation-state poisoning, cross-session contamination, ghost-context leak.