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/yonro/memory-os-cli/agentsnpx skills add yonro/memory-os-cli --skill agentsgit clone --depth 1 https://github.com/yonro/memory-os-cliWhat 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 | $0.00028 | $0.00307 |
| Opus 5 | $0.00014 | $0.00153 |
| Sonnet 5 | $0.00006 | $0.00061 |
| Haiku 4.5 | $0.00003 | $0.00031 |
Grade A, and why
agents 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 yesterday.
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
XMemo Memory
Use this skill when the task may depend on prior memory, durable project context, coding preferences, decisions, or follow-up actions.
Workflow
- Recall first when prior context could change the answer. Use XMemo search/recall/context tools before making assumptions about preferences or past decisions.
- Save only durable information that the user asks to remember or that is clearly useful across future sessions.
- Keep memory content concise, scoped, and useful. Prefer concrete facts, decisions, links to public docs, and action items over chat transcripts.
- For destructive memory actions, confirm the exact target before deleting, forgetting, or overwriting.
- If authorization fails, tell the user: "Reconnect XMemo through OAuth, or run
xmemo login, or visit https://xmemo.dev to set up your token." Do not request raw tokens in chat.
Good memory candidates
- Repository conventions and verified commands.
- Architecture decisions, release procedures, and deployment notes.
- User-approved preferences for code review, testing, documentation, or UX.
- TODOs and follow-ups that should be visible to future agents.
Avoid saving
- Secrets, credentials, OAuth codes, cookies, API keys, or token prefixes.
- Private customer data or sensitive personal data.
- Temporary debugging output that will not help future work.
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.
- yesterday First seen · 30 lines · 28 tokens per session scan A 92fc07dfbea7
agents is a skill published in the GitHub repository yonro/memory-os-cli (12 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 307 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
weasley-deepmind
AI 에이전트가 weasley-deepmind 기억 서버를 최대 효율로 활용하기 위한 기술 레퍼런스.
mnema
Use the Mnema MCP server to give the AI long-term, searchable memory. Use it whenever the user shares durable facts, preferences, decisions, or context worth recalling in future sessions. Mnema stores memories in a vector database and recalls them with semantic + hybrid search, with decay scoring and summarization so…
stickies
Capture and recall persistent sticky notes — decisions, blockers, todos, preferences, and context — that survive across Claude sessions, kept in a local SQLite store (no account, no API key). Use this skill whenever the user wants to remember something for later, jot a note, park a todo or follow-up, record a decision…
graphmind-planning
Декомпозиция сложной задачи в иерархию планов GraphMind по MCP. Создать P0-проблему (plancreatep0), предложить P1-подпланы для ревью (planproposep1/approvep1/rejectp1), декомпозировать в P2/P3, выдать P3 суб-агенту (planclaim), завершить с результатом (plancomplete). Использовать, когда задача большая, размытая или…
graphmind-memory
Работа с постоянной памятью GraphMind по MCP. Восстановить контекст проекта в начале работы (bootstrapmemory), сохранять шаги и решения по ходу (recordaction, proposenewmemory), консолидировать и сохранить в конце (flushsessionmemory). Использовать, когда нужна память между сессиями, семантический поиск по…
using-cortex-memory
Use when connected to a Cortex memory MCP server (tools named memorize, recall, recallabout, recalltimeline, listmemories, forget) — at session start, before asking the user for facts they may have shared before, after learning durable facts/preferences/decisions, when the user says "remember/recall/forget", or when…