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 saint4ai/onai-vibecoding-skills --skill memory-bankgit clone --depth 1 https://github.com/saint4ai/onai-vibecoding-skillsWrote 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/saint4ai/onai-vibecoding-skills/memory-bank)<a href="https://agentmods.dev/skills/saint4ai/onai-vibecoding-skills/memory-bank"><img src="https://agentmods.dev/badge/skills/saint4ai/onai-vibecoding-skills/memory-bank/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/saint4ai/onai-vibecoding-skills/memory-bank"><img src="https://agentmods.dev/badge/skills/saint4ai/onai-vibecoding-skills/memory-bank.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00064 | $0.00545 |
| Opus 5.5 | $0.00026 | $0.00218 |
| Sonnet 5.5 | $0.00013 | $0.00109 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
memory-bank 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 2mo 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
Memory Bank — память проекта
Агент помнит только текущий диалог. Закрыл — забыл. Memory Bank решает это: ты держишь память проекта в файлах, и агент читает их в начале работы. Так проект остаётся целым на любом масштабе и через месяцы.
Структура (папка memory-bank/ в проекте)
| Файл | Что хранит |
|---|---|
architecture.md |
Как устроен проект: модули, связи, внешние интеграции |
tech-stack.md |
Выбранный стек и почему именно он |
product-requirements.md |
Что строим, для кого, какие функции в MVP |
progress.md |
Журнал: что сделано после каждого шага (дата ✓ что — файлы — статус) |
decisions/ |
По одному файлу на важное решение: что выбрали и почему (чтобы не передумывать заново) |
features/ |
Заметки по отдельным фичам |
Правила
- Читай первым. В начале работы агент читает
memory-bank/— берёт контекст проекта, а не начинает с нуля. - Обновляй после каждого шага. Закончил кусок → допиши
progress.md(что сделал, какие файлы). Принял решение → запиши вdecisions/. - Коротко и по делу. Память — не свалка. Только то, что важно помнить дальше.
- Не дублируй ТЗ. Формальное ТЗ — отдельно (в
docs/), здесь — рабочая сводка и решения.
Как агент это использует
В CLAUDE.md проекта прописывается правило: «перед работой прочитай memory-bank/; после каждого шага обнови progress.md». Тогда даже новый чат или другой агент мгновенно входит в курс дела.
Шаблон пустых файлов — в папке
template/рядом. Скопируй в свой проект какmemory-bank/и заполняй по ходу.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 30 lines · 64 tokens per session scan A d9a13f2a24ea
memory-bank is a skill published in the GitHub repository saint4ai/onai-vibecoding-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 545 once invoked, about $0.0003 per session on Opus 5.5. 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.
memory-bank compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| memory-banksaint4ai/onai-vibecoding-skills | Skill | 2 | 4mo ago | MIT | A | 64 | Claude Code, Codex |
| knowledge-ingestopenclaw/openclaw | Skill | 394k | yesterday | MIT | A | 80 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| forgetasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 74 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| memoryopensquilla/opensquilla | Skill | 7.1k | 6d ago | Apache-2.0 | A | 44 | Claude Code, Codex |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 115 | Claude Code, Codex |