agentmods.dev

new

new is a command for Claude Code from stereosam/stereo-vibe-public. It costs 0 tokens per session (875 once invoked), scanned A, original, MIT.

A command that registers a new project in a shared memory file, assigning it the next free number and optionally recording its description and folder.

In plain words
What is it for?
Starting a project record, previewing the planned file changes, and creating the record after confirmation.
Why use it?
It keeps project names, numbers, and locations in one mapping instead of asking the user to track them manually.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions CLAUDE.md.

not rated 1repo 26d ago A scan 0 tokens original MIT

Good fit Starting a project record, previewing the planned file changes, and creating the record after confirmation.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/stereosam/stereo-vibe-public/new
View source ↗ stereosam/stereo-vibe-public
Install

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.

Clone the repo
git clone --depth 1 https://github.com/stereosam/stereo-vibe-public

Made for: Claude Code.

Wrote 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.

agentmods badge for new

README.md
[![agentmods](https://agentmods.dev/badge/commands/stereosam/stereo-vibe-public/new/github.svg)](https://agentmods.dev/commands/stereosam/stereo-vibe-public/new)
Your own site
<a href="https://agentmods.dev/commands/stereosam/stereo-vibe-public/new"><img src="https://agentmods.dev/badge/commands/stereosam/stereo-vibe-public/new/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.

agentmods 80×15 button for new

Your own site · 80×15
<a href="https://agentmods.dev/commands/stereosam/stereo-vibe-public/new"><img src="https://agentmods.dev/badge/commands/stereosam/stereo-vibe-public/new.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 875 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00875
Opus 5 $0.00000 $0.00438
Sonnet 5 $0.00000 $0.00175
Haiku 4.5 $0.00000 $0.00088

Measured 10d ago against content hash eb58f78cf745, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

new 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 10d 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.

commands/new.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Завести новый проект в памяти. Аргумент: $ARGUMENTS

Формат: /new <name> [| описание] — <name> в snake_case (строчная латиница/цифры/_). Пример: /new price_parser | парсер цен маркетплейсов для клиентов Если аргумента нет — спроси имя и (опц.) описание.

Источник карты номеров

Единственный источник — блок «## Маппинг проектов → директории» в MEMORY.md. CLAUDE.md и go.md на него лишь ссылаются, своих копий карты не держат. Номер НЕ спрашиваем — хелпер берёт младший свободный, сканируя маппинг (ретро/слитые номера числятся занятыми и не выдаются).

Шаги

  1. Превью (dry-run, ничего не пишет): 
    ssh <user>@<your-server> "python3 /path/to/memory/new_project.py --name <name> --desc '<описание>' --dry-run"
    Покажет: какой номер N присвоится, какие файлы создаст, что допишет в маппинг.
  2. Покажи пользователю план и жди подтверждения (создание файлов — по правилу confirm).
  3. Создание (тот же вызов без --dry-run): 
    ssh <user>@<your-server> "python3 /path/to/memory/new_project.py --name <name> --desc '<описание>'"
    Опц. флаги: --dir '<путь папки>' (если у проекта есть папка артефактов на ПК), --number N (номер вручную).
  4. Успех = [OK] проект N '<name>' заведён. Хелпер создал <name>_status.md + <name>_backlog.md, дописал строку в маппинг MEMORY.md, добавил строку в session_log.md. Синк раздаст вниз сам.
  5. Если [FAIL] — причина в выводе (имя занято / файл уже есть / номер занят). Ничего не перезатёрто. Поправь и повтори.

Поведение хелпера (гарантии)

  • Пишет ТОЛЬКО на VPS (/path/to/memory/). В локальное зеркало не пишем (оно receiveonly).
  • Идемпотентно/атомарно (tmp + os.replace). Повторный запуск с тем же именем → [FAIL], а не перезапись.
  • Не перезатирает существующие *_status.md/*_backlog.md без чтения — при коллизии останавливается.
  • Правила («не удалять/не редактировать без чтения» и пр.) в файлы проекта НЕ копирует — они в глобальном CLAUDE.md.

Шаблоны (что кладёт хелпер)

  • <name>_status.md: frontmatter (name/description/type: project) + разделы Что за проект / Где артефакты / Как устроено / Грабли.
  • <name>_backlog.md: заголовок + ## Активные (таблица # / Задача / Заметки, затравка N-1) + ## Changelog (DONE) (N-2 — «оформлен командой /new»). Формат таблицы — канон (26/29 бэклогов, парсится save_prep.py).

Read the full file on GitHub · 41 lines

Changes

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.

  1. 10d ago First seen · 41 lines · 0 tokens per session scan A eb58f78cf745

Subscribe to this mod's changes

new is a command published in the GitHub repository stereosam/stereo-vibe-public (1 stars, last pushed 26d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 875 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.

Claude CodeMemory and contextagent-memoryagentic-codingai-agentsbashclaude-md
Related

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.

avelikiy/great_cto · 36 tokens

tree-ring-recall

Recall durable Tree Ring Memory context before starting or resuming work.

TerminallyLazy/Tree-Ring-Memory · 12 tokens

tree-ring-update

Check for or install a verified Tree Ring Memory CLI update without changing installation scope.

TerminallyLazy/Tree-Ring-Memory · 15 tokens

tree-ring-certify

Generate Tree Ring harness or recall-quality evidence without confusing it with the full framework release suite.

TerminallyLazy/Tree-Ring-Memory · 17 tokens

tree-ring-status

Check receipt-backed Tree Ring harness readiness without claiming configuration is activation.

TerminallyLazy/Tree-Ring-Memory · 12 tokens

historial

Listar sesiones pasadas guardadas en el historial.

doncheli/don-cheli-sdd · 10 tokens