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/contentrain/ai/contentrain-bulknpx skills add Contentrain/ai --skill contentrain-bulkgit clone --depth 1 https://github.com/Contentrain/aiWhat 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 | $0.00030 | $0.00796 |
| Opus 5 | $0.00015 | $0.00398 |
| Sonnet 5 | $0.00006 | $0.00159 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
contentrain-bulk 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.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Run Bulk Content Operations
Apply safe batch operations to existing content entries.
When to Use
Use this when the user wants to:
- copy one locale to another
- update status on many entries
- delete multiple collection entries
This skill is for existing content, not for schema design.
Steps
1. Inspect the Model
Call contentrain_status and contentrain_describe(model: "<model-id>") first.
Confirm:
- model kind
- whether
i18nis enabled - which locales are supported
2. Pick the Correct Bulk Operation
copy_locale: clone one locale to another for i18n-enabledcollection,singleton, ordictionarymodelsupdate_status: update metadata state — many entries at once forcollection, or the single record of asingleton/dictionarydelete_entries: remove many collection entries at once
3. Apply Safety Rules
- never use
copy_localeon non-i18n models update_statustakesentry_idsforcollectionmodels and rejects them forsingleton/dictionary— those have one meta record per locale, so omitentry_idsentirely. Document models are not supported (their meta is keyed by slug).delete_entriesis collection-onlyupdate_statusrewrites every supported locale unless you passlocale. Pass it when restoring one locale's status, or you will change the other's too.- confirm entry IDs before delete operations
- batch only related entries together
4. Execute with contentrain_bulk
Examples:
{
"operation": "copy_locale",
"model": "ui-labels",
"source_locale": "en",
"target_locale": "tr"
}
{
"operation": "update_status",
"model": "blog-post",
"entry_ids": ["post_001", "post_002"],
"status": "in_review"
}
Scoped to one locale — leaves every other locale's status untouched:
{
"operation": "update_status",
"model": "blog-post",
"entry_ids": ["post_001"],
"status": "published",
"locale": "tr"
}
A singleton or dictionary — one meta record, so no entry_ids:
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 First seen · 131 lines · 30 tokens per session scan A 65aa57570d55
contentrain-bulk is a skill published in the GitHub repository Contentrain/ai (4 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 796 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。.
inclusive-design
Use when working on inclusion, i18n/localization, global name/address forms, low-end devices, slow/metered networks, affordability, or first-time/low-confidence users; not WCAG/screen readers (see accessibility).
unreal-plugin-localization
翻译 UE 插件本地化 PO 文件。当用户要求本地化、翻译或国际化 Unreal Engine 插件时使用。 处理 GatherText 采集、PO 导出、AI 翻译、PO 导入和 locres 编译的完整流程。.
lov-image-translation-errata
核对截图中的原文与机翻,生成保留错误痕迹、给出正确译文且尽量维持原布局的勘误图;用于“图片翻译勘误”“指出机翻错误”和 create an in-image translation errata。.
lov-academic-translator
将英文论文、arXiv、期刊/会议文章及技术 PDF 翻译为中文 PDF 或可发布的中文 Markdown。用户提出“翻译英文 PDF”“翻译论文”“论文超级翻译官”“保留图片、公式和原版式”“原文译文对照”“页数对应”或“PDF 图文排版不要乱”时使用。.
appstore-metadata-localizer
App Store listing text: translate and market-adapt descriptions, keywords, What's New, names, subtitles, and privacy text across locales. Excludes non-translation edits, standalone release notes, and IAP/subscription names.