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 kostya-pakhomov/graphmind --skill graphmind-memorygit clone --depth 1 https://github.com/kostya-pakhomov/graphmindWrote 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/kostya-pakhomov/graphmind/graphmind-memory)<a href="https://agentmods.dev/skills/kostya-pakhomov/graphmind/graphmind-memory"><img src="https://agentmods.dev/badge/skills/kostya-pakhomov/graphmind/graphmind-memory.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 | $0.00093 | $0.00607 |
| Opus 5 | $0.00046 | $0.00303 |
| Sonnet 5 | $0.00019 | $0.00121 |
| Haiku 4.5 | $0.00009 | $0.00061 |
Grade A, and why
graphmind-memory 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.
What it actually says
GraphMind — постоянная память по MCP
Навык подключает агента к общей памяти проекта. Требуется подключённый MCP-сервер graphmind (см. README плагина, раздел «Подключение»). Память живёт между сессиями и общая для нескольких агентов и людей: один накопил — остальные пользуются.
1. В начале работы — восстановить контекст
bootstrap_memory({ cwd: "<абсолютный путь проекта>", query: "<суть запроса пользователя>", depth: 1 })
Один вызов определяет рабочее пространство (workspace) по пути и делает семантический recall накопленного знания. Используй полученный контекст, не переспрашивай то, на что память уже ответила.
2. По ходу работы — сохранять
| Что | Вызов |
|---|---|
| Завершён значимый шаг | record_action({ summary }) |
| Факт/решение этого проекта | propose_new_memory({ level: "L2", node_type: "atom", content }) |
| Кросс-проектное решение | propose_new_memory({ level: "L2", node_type: "atom", scope: "global", content }) |
scope: "global" — только для общих паттернов (MCP, Docker, CI, конвенции языка/IDE, настройка хуков). Бизнес-логика конкретного приложения и статусы задач одного репозитория — без global.
3. Поиск по памяти
memory_query({ query: "<вопрос>" }) # гибридный: семантика (эмбеддинги) + ключевые слова
Дополнительно: get_chain — причинная цепочка от узла; find_contradictions — смысловые противоречия; list_memory — последние карточки.
4. В конце сессии — сохранить итог
flush_session_memory({ summary: "итог: что сделано, ключевые решения" })
Запреты
- Не полагаться на историю чата как на память — только через MCP graphmind.
- Не дублировать то, что уже есть в
AGENTS.md/KODIK.md— в память идут решения и статусы, которых нет в файлах.
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 · 46 lines · 93 tokens per session scan A 6ae22b894ef2
graphmind-memory is a skill published in the GitHub repository kostya-pakhomov/graphmind (2 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 607 once invoked, about $0.0005 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
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…
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…
plur-memory
Persistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.
plur-session-end
Extract durable learnings at the end of a session. Saves corrections, preferences, and codebase patterns as engrams — nothing ephemeral, nothing sensitive.
plur-memory
Your memory stays on your machine. No cloud, no tracking, no API key. PLUR makes your OpenClaw remember — and shares that memory with every other tool you use.
mnemo-cortex
Installs and wires Mnemo Cortex (local-first persistent memory) into OpenClaw and other MCP-capable agents. Use for cross-session recall, decision history, or multi-agent shared memory.