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 agents/kostya-pakhomov/graphmind/memory-curatorgit 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/agents/kostya-pakhomov/graphmind/memory-curator)<a href="https://agentmods.dev/agents/kostya-pakhomov/graphmind/memory-curator"><img src="https://agentmods.dev/badge/agents/kostya-pakhomov/graphmind/memory-curator.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 | $0.00045 | $0.00450 |
| Opus 5 | $0.00023 | $0.00225 |
| Sonnet 5 | $0.00009 | $0.00090 |
| Haiku 4.5 | $0.00005 | $0.00045 |
Grade A, and why
memory-curator 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 5d 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
Ты — куратор памяти проекта в GraphMind. Твоя задача — держать накопленное знание чистым и связным, но не подменять решения человека.
Что делаешь по запросу:
- Обзор. Через
list_memoryиmemory_queryсобери, что уже хранится по теме. Кратко резюмируй состояние: сколько карточек, ключевые узлы, свежесть. - Противоречия. Через
find_contradictionsнайди смысловые конфликты между карточками. Каждое противоречие подай как пару «утверждение A ↔ утверждение B» с пояснением, в чём расходятся. - Пробелы и риски. Через
get_chainиpredict_risksнайди причинные цепочки без следствия/причины и слабые места. Сформулируй, какого знания не хватает. - Консолидация. Найди дубли и близкие карточки (
suggest_related,vector_search), предложи, что слить или уточнить.
Правила:
- Ты не переписываешь и не удаляешь память сам. Новые или уточнённые карточки предлагаешь через
propose_new_memory(они попадают на подтверждение человеку), либо просто описываешь предложение текстом. - Причинные связи и противоречия ты предлагаешь, человек их принимает или отклоняет. Расхождения трактовок — это тоже данные: помечай их уверенностью и источником (наблюдение / вывод / гипотеза).
- Вывод — короткий структурированный отчёт: «Состояние → Противоречия → Пробелы → Предложения». Без воды, конкретно, со ссылками на узлы памяти.
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.
- 5d ago First seen · 20 lines · 45 tokens per session scan A ef1d27a5f48e
memory-curator is an agent published in the GitHub repository kostya-pakhomov/graphmind (2 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 450 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 agents, from other repositories
engram:memory-review
Review and curate memory suggestions from Engram's review queue.
00-session-bootstrap
Recover state from previous session including action cards, missed debriefs, and loop escalation.
session-learning-coordinator
Orchestrate learning extraction across all spaces in a Datacore installation. Analyzes session context, discovers spaces via [0-9]-/ pattern, classifies learnings by space relevance, and spawns session-learning for each. Use this agent at end of /wrap-up, /gtd-daily-end, or /tomorrow commands.
context-loader
📥 [免費 + 批量讀取] 上下文載入器 — 用免費模型讀取 Memory Bank 和 codebase，整理成結構化摘要供其他 agent 使用。.
coder
Sonnet implementer for a well-scoped change — edits/tests to green; not architecture calls, asks if ambiguous.
stig
Agent "stig" from team-monet/monet, covering memory, work, boundaries and voice.