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.
git clone --depth 1 https://github.com/stereosam/stereo-vibe-publicWrote 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/commands/stereosam/stereo-vibe-public/save)<a href="https://agentmods.dev/commands/stereosam/stereo-vibe-public/save"><img src="https://agentmods.dev/badge/commands/stereosam/stereo-vibe-public/save/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/commands/stereosam/stereo-vibe-public/save"><img src="https://agentmods.dev/badge/commands/stereosam/stereo-vibe-public/save.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 | $0.00000 | $0.00442 |
| Opus 5 | $0.00000 | $0.00221 |
| Sonnet 5 | $0.00000 | $0.00088 |
| Haiku 4.5 | $0.00000 | $0.00044 |
Grade A, and why
save 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 8d 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
Выполни workflow "сохранись" из MEMORY.md (раздел «сохранись / save» — единственный источник шагов; здесь НЕ дублируем детали формата).
ЧТЕНИЕ (без SSH): прочитай актуальный блок из ЛОКАЛЬНОГО зеркала — файл <home>\YandexDisk\CLAUDE\claude_memory\MEMORY.md, раздел между строкой «**"сохранись"» и «Ждать команды». Текущее содержимое статус-файлов/session_log/grabli тоже читай из зеркала claude_memory/ (мгновенно). Если зеркала нет — фолбэк по SSH.
ШАГ 0 (перед сборкой спеки): ssh <user>@<your-server> "python3 /path/to/memory/save_prep.py [проект]" — read-only дайджест: Last saved, хвост session_log, max № grabli, Активные backlog (чтобы не забыть закрыть и не продублировать id).
ЗАПИСЬ — ОДНИМ заходом через помощник (не bespoke-скрипт, не несколько SSH): собери spec.json (поля: last_saved, session_log, grabli, backlog, sections — полный формат в docstring save_memory.py и MEMORY workflow) и:
ssh <user>@<your-server> "python3 /path/to/memory/save_memory.py" < spec.json
Помощник идемпотентен/атомарен: авто-месяц-сплит session_log, сквозная нумерация grabli, закрытие/добавление backlog. ТОЛЕРАНТЕН к формату (20.07): last_saved можно голой датой (обернёт в Last saved: .. сам), session_log без краевых | (достроит), backlog action add без id (авто max+1) — форматных отказов нет. Грабли — в grabli.md (НЕ в CLAUDE.md).
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.
- 8d ago First seen · 10 lines · 0 tokens per session scan A ba778c12f92b
save is a command published in the GitHub repository stereosam/stereo-vibe-public (1 stars, last pushed 25d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 442 tokens. 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 commands, from other repositories
ccr
CCR (Compressed Context with Retrieval) — recall the full original of context that greatcto compressed/filtered out, by its short id. The retrieval half of the compression layer.
tree-ring-update
Check for or install a verified Tree Ring Memory CLI update without changing installation scope.
tree-ring-certify
Generate Tree Ring harness or recall-quality evidence without confusing it with the full framework release suite.
tree-ring-recall
Recall durable Tree Ring Memory context before starting or resuming work.
tree-ring-status
Check receipt-backed Tree Ring harness readiness without claiming configuration is activation.
historial
Listar sesiones pasadas guardadas en el historial.