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 skills/ivanarama/onebase/merge-shepherdnpx skills add ivanarama/onebase --skill merge-shepherdgit clone --depth 1 https://github.com/ivanarama/onebaseWrote 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/ivanarama/onebase/merge-shepherd)<a href="https://agentmods.dev/skills/ivanarama/onebase/merge-shepherd"><img src="https://agentmods.dev/badge/skills/ivanarama/onebase/merge-shepherd.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 | $0.00064 | $0.00450 |
| Opus 5 | $0.00032 | $0.00225 |
| Sonnet 5 | $0.00013 | $0.00090 |
| Haiku 4.5 | $0.00006 | $0.00045 |
Grade A, and why
merge-shepherd 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 2d 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
Codex-адаптер мерж-очереди
- Сначала прочитать короткий общий маршрут
.claude/skills/merge-shepherd/SKILL.mdи использоватьpipelinectlиз задачи. - Следовать ей с обычным приоритетом инструкций Codex: слово
headlessне отменяет системные ограничения, безопасность или необходимость сообщить настоящий блокер. - До записи в GitHub проверить доступность
gh, действующую аутентификацию иgh api user --jq .login. Писать разрешено только отivanarama; иначе остановиться без изменений. Перед каждым изменением перечитать состояние PR; параллельный планировщик не считается заблокированным автоматически. - Считать
$merge-shepherdCodex-эквивалентом/merge-shepherd. Упоминания следующих этапов — только описание маршрута, не разрешение запускать их автоматически. - Разрешать пути от корня репозитория. Создавать worktree только по уникальному проверенному абсолютному пути и удалять лишь worktree текущего прогона; локальный
mainне трогать. - На Windows переводить
&&,sleepи REST-конвейеры в безопасные PowerShell-эквиваленты. Ожидать CI порциями не более 60 секунд и регулярно сообщать прогресс. - Полную процедуру
references/legacy-protocol.mdчитать только приaction=fallback; не загружать её в обычном tool-пути.
Детерминированная механика обычного пути живёт в pipelinectl; сложные состояния остаются в fallback-процедуре.
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.
- 2d ago Changed · -103 lines · -1 tokens per session d1689edcd99c
- 6d ago First seen · 120 lines · 65 tokens per session scan A 0b009218375b
merge-shepherd is a skill published in the GitHub repository ivanarama/onebase (90 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 450 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 skills, from other repositories
streamsql
当需要创建实时数据聚合/窗口统计、流式过滤转换、变化检测（CDC）、生命周期累计、元数据富化（流-表 JOIN）、CEP 模式识别（MATCHRECOGNIZE）等规则链时使用，或当使用 x/streamAggregator 和 x/streamTransform 组件时使用。包含 SQL 语法、窗口、分析函数、JOIN、CEP 和配置示例.
editing-model-diagrams
Creates, edits, reviews, and regenerates C4 architecture diagrams written with goa.design/model and the mdl CLI. Use when changing Model DSL, model.go or views.go files, system landscape, context, container, component, dynamic, or deployment views, element relationships, boundaries, layout, or generated SVG diagrams.
release-neva
Prepare a Neva GitHub release draft from merged PRs, previous release style, and local multi-platform artifacts. Use this for monthly release preparation in nevalang/neva.
release
Use when preparing or publishing an NGINX UI release, including version bumping with version.sh, release note drafting, release-prep commits, annotated tags, pushing dev and tags, and creating GitHub Releases with Announcements discussions.
gh-prerelease
Cut a GitHub prerelease off a specific commit — branch, bump version with just update-version, tag, push, and publish a prerelease.
release-kirocc
Guide the kirocc release process step by step: create release branch, write release notes, open PR, tag, and sync GitHub Release. Use this skill whenever the user wants to release a new version, cut a release, create a tag, bump version, or says /release-kirocc. Takes a version argument like /release-kirocc v0.1.0.