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 yellow-hammer/skills-onescript --skill autumngit clone --depth 1 https://github.com/yellow-hammer/skills-onescriptWrote 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/yellow-hammer/skills-onescript/autumn)<a href="https://agentmods.dev/skills/yellow-hammer/skills-onescript/autumn"><img src="https://agentmods.dev/badge/skills/yellow-hammer/skills-onescript/autumn/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/yellow-hammer/skills-onescript/autumn"><img src="https://agentmods.dev/badge/skills/yellow-hammer/skills-onescript/autumn.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 | $0.00145 | $0.03143 |
| Opus 5.5 | $0.00058 | $0.01257 |
| Sonnet 5.5 | $0.00029 | $0.00629 |
| Haiku 4.5 | $0.00015 | $0.00314 |
Grade A, and why
autumn 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 1mo 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autumn (ОСень)
Фреймворк компонентных приложений для OneScript с Dependency Injection и Inversion of Control. Разрешает зависимости конструкторов автоматически: не нужно вручную создавать цепочки объектов и передавать параметры во все точки создания.
Ниже — autumn 5.0.2. На последней четвёрке, 4.3.15, эти же рецепты компилируются. Отдельной инструкции для четвёрки нет: versions/4.md только фиксирует, что поломки нет.
Версия
Версию бери из oscript_modules/autumn/opm-metadata.xml, элемент version. Если каталога модулей нет — из .ЗависитОт("autumn", "...") в packagedef. Мажор 4: прочитай versions/4.md и не выдумывай второе API. Мажор 5: достаточно этого файла и versions/5.md.
Описание аннотации, которой нет ниже, читай из поставки пакета: oscript_modules/autumn/src/internal/Классы/Аннотация*.os. В шапке класса написано, куда она ставится (конструктор, метод, поле, параметр) и приведён пример. Каталог docs в пакет не входит. Расширение файлов в поставке — .os.
Аналогии Spring Boot
Таблица только для узнавания аннотации. В коде пиши осенние имена. @Component и остальные аннотации Spring в языке нет, правила внедрения у Autumn другие: параметр конструктора без &Пластилин, &Деталька или &Блестяшка не внедряется, поле в ПриСозданииОбъекта ещё пустое.
| Autumn | Spring Boot |
|---|---|
&Желудь |
@Component |
&Дуб |
@Configuration |
&Завязь |
@Bean |
&Пластилин |
@Autowired |
&ФинальныйШтрих |
@PostConstruct |
&Напильник |
BeanPostProcessor |
&Деталька |
@Value |
&Табакерка |
ObjectProvider |
Душные имена
Пакет autumn-killjoy-flavour 1.3.0 даёт вторые имена тем же аннотациям. Подключай его, только если в проекте уже есть #Использовать autumn-killjoy-flavour. Без этой строки пиши осенние имена: &Желудь, &Пластилин, &Деталька. Английские аннотации Spring (@Component, @Autowired) в языке нет.
What ships with it
2 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.
- 1mo ago Changed · +119 lines · +74 tokens per session b2b8e911b38c
- 2mo ago First seen · 78 lines · 71 tokens per session scan A 90a248412d50
autumn is a skill published in the GitHub repository yellow-hammer/skills-onescript (41 stars, last pushed 1mo ago), licensed MIT. It adds 145 tokens to every session and 3,143 once invoked, about $0.0006 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 2026-08-30.
autumn compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| autumnyellow-hammer/skills-onescript | Skill | 41 | 1mo ago | MIT | A | 145 | Claude Code, Codex |
| omh-rustrlaope/oh-my-hermes | Skill | 5.2k | today | MIT | A | 74 | Claude Code, Codex |
| erlang-otp-behaviorsbenchflow-ai/skillsbench | Skill | 1.9k | 3d ago | Apache-2.0 | A | 52 | Claude Code, Codex |
| axiom-concurrencyCharlesWiltgen/Axiom | Skill | 1.3k | yesterday | MIT | A | 49 | Claude Code |
| tddcodewithmukesh/dotnet-claude-kit | Skill | 807 | 3d ago | MIT | A | 81 | Claude Code |
| splitting-oversized-modulesPostHog/posthog | Skill | 41k | today | none | A | 197 | Claude Code, Codex |
| precisemicroprediction/precise | Skill | 338 | 6d ago | MIT | A | 76 | Claude Code, Codex |