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/romarayt/raytsystem-public-os/overviewgit clone --depth 1 https://github.com/romarayt/raytsystem-public-osWrote 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/romarayt/raytsystem-public-os/overview)<a href="https://agentmods.dev/agents/romarayt/raytsystem-public-os/overview"><img src="https://agentmods.dev/badge/agents/romarayt/raytsystem-public-os/overview.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 | $0.00061 | $0.02037 |
| Opus 5 | $0.00030 | $0.01019 |
| Sonnet 5 | $0.00012 | $0.00407 |
| Haiku 4.5 | $0.00006 | $0.00204 |
Grade A, and why
overview 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Агенты и расширение: обзор
Что это
Расширяемость raytsystem держится на каталоге — наборе инертных определений, которые описывают, что система может делать, но сами по себе ничего не выполняют. Каталог собирается сервисом CatalogService (src/raytsystem/catalog.py) и включает пять видов объектов:
- packs — манифесты
packs/<имя>/pack.yaml, объединяющие агентов, навыки и разрешённые контексты; - agents — определения агентов
packs/<имя>/agents/<agent_id>.yaml; - skills — процедуры
skills/<имя>/SKILL.mdс YAML-фронтматтером; - instructions — три корневых документа:
AGENTS.md,WORK.md,CLAUDE.md; - adapters — реестр рантайм-адаптеров
config/runtime-adapters.yaml.
Два встроенных pack: core и starter.
Когда использовать
Читайте этот раздел, если хотите понять, откуда система берёт агентов и навыки, как проверяется их происхождение и почему наличие определения не даёт ему прав. Дальше — создание собственного расширения и жизненный цикл packs.
Каталог собирается только из фиксированных корней
CatalogService обходит только заранее заданные project-local каталоги: packs/, skills/, файл config/runtime-adapters.yaml и корневые AGENTS.md/WORK.md/CLAUDE.md. Это не сканирование всего диска — источники зафиксированы в коде.
При обходе действуют жёсткие ограничения (src/raytsystem/catalog.py):
- symlink запрещён: любой симлинк в корнях каталога — ошибка
CatalogError; - имена директорий обязаны совпадать с шаблоном
^[a-z][a-z0-9_-]{1,63}$; - размеры ограничены (определения — 512 КБ, документы — 1 МБ), YAML проверяется на глубину, число узлов, дубликаты ключей; якоря, алиасы и merge-ключи запрещены;
- каждый файл проходит проверку на секреты (
SecretScanner), которая «падает закрыто» при любой ошибке.
Имя файла агента обязано совпадать с его agent_id, а имя директории встроенного pack — с ожидаемым pack_id (например, core → pack_core, starter → pack_starter).
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 · 128 lines · 61 tokens per session scan A 1d6fe4f235d8
overview is an agent published in the GitHub repository romarayt/raytsystem-public-os (141 stars, last pushed 3d ago), licensed Apache-2.0. It adds 61 tokens to every session and 2,037 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
research-fetcher
Background content fetcher — fetches URLs, saves raw content, and verifies output. Use when a skill needs to delegate content extraction without synthesis.
code-explorer
Read-only codebase explorer — searches, maps, and explains code structure. Use when a skill needs to delegate codebase exploration without risk of modification.
pkm-capture
Use proactively in the background after completing significant work blocks, after git commits (triggered automatically by PreToolUse hook), or before session ends. Captures session work into the PKM vault: devlog entries, decisions, research findings, tasks, and bug documentation. Conservative — most exchanges produce…
vault-explorer
Use proactively when researching what the vault knows about a topic, before creating new notes, or when exploring existing knowledge and connections. Run in foreground — results inform the caller's next steps. Examples: Context: User asks about a topic before creating new content. user: "What does the vault already…
web-researcher
Searches the web for a specific research query and returns a compressed finding with cohort-diverse citations and source-type annotations. Use when the parent recipe needs current-web information — especially fast-moving landscape/tooling topics where model priors can't be trusted.
vault-researcher
Searches the vault for a specific research query and returns one best-match note with excerpt. Targeted mode only in Phase 1. Use when the parent recipe needs to pull vault context on a focused question; dispatch multiple instances in parallel for breadth.