Borrowing it
Nothing to install: this file belongs to ivanarama/onebase. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ivanarama/onebase/main/.agents/skills/merge-shepherd/SKILL.mdgit 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/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/ivanarama/onebase/merge-shepherd"><img src="https://agentmods.dev/badge/skills/ivanarama/onebase/merge-shepherd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
- medium Agent Snooping · line 8 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 5.5 | $0.00026 | $0.00180 |
| Sonnet 5.5 | $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 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.
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.
- 1mo ago Changed · -103 lines · -1 tokens per session d1689edcd99c
- 2mo ago First seen · 120 lines · 65 tokens per session scan A 0b009218375b
merge-shepherd is a skill published in the GitHub repository ivanarama/onebase (135 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 450 once invoked, about $0.0003 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.
Other skills, from other repositories
conventional-git
Conventional Commits v1.0.0 branch naming and commit message standards for GitHub and GitLab projects. Use when creating branches, writing commits, generating commit messages, reviewing branch conventions, or setting up changelog automation. Apply when your project needs consistent git history, SemVer-driven releases…
octocat
Handles git and GitHub operations using the gh CLI. Use when the user asks about pull requests (PRs), GitHub issues, repo management, branching, merging, rebasing, cherry-picking, merge conflict resolution, commit history cleanup, pre-commit hook debugging, GitHub Actions workflows, or releases. Covers creating and…
release
Fully automate a release with version-bump and childhood.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.