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 rules/contentstack/contentstack-agent-skills/08-cms-localizationgit clone --depth 1 https://github.com/contentstack/contentstack-agent-skillsWhat 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 | $0.00031 | $0.01017 |
| Opus 5 | $0.00015 | $0.00508 |
| Sonnet 5 | $0.00006 | $0.00203 |
| Haiku 4.5 | $0.00003 | $0.00102 |
Grade A, and why
08-cms-localization 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 yesterday.
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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contentstack Localization
Description
Advise developers on Contentstack localization: language setup, fallback chains, localized vs unlocalized entries, non-localizable fields, and multi-locale publishing.
When to Use
Use when developers ask about languages, fallback chains, localizing entries, non-localizable fields, or multi-locale publishing. Clarify whether the question concerns the CMS editorial experience or CDA delivery behavior.
User Problem
Developers need to design multilingual content delivery with correct fallback behavior, efficient editorial workflows, and minimal redundancy.
Success Criteria
Language hierarchy is correct and master language constraints are stated. Fallback behavior is explained clearly, including chain traversal. Field-level localization choices are practical and consistent. Multi-locale publishing guidance is accurate and actionable. Advice distinguishes editorial UI behavior from CDA behavior.
Expected Inputs
- Target languages and markets
- Fallback requirements
- Editorial workflow for translations
- Content shared across locales
Expected Outputs
- Language hierarchy recommendations
- Fallback chain design
- Non-localizable field guidance
- Publishing strategy for multiple locales
- CDA locale query guidance
Example User Requests
- How do I set up languages with fallback in Contentstack?
- What is the difference between a localized and unlocalized entry?
- Which fields should I mark as non-localizable?
- How do I publish content in multiple languages at once?
- What happens if a locale has no content?
Workflow Summary
Confirm target locales, markets, and whether the question is about CMS or CDA behavior. Explain master language constraints and design the fallback chain. Recommend which fields should remain non-localizable. Describe localized vs unlocalized entry behavior and editorial impact. Give CDA locale query guidance and multi-locale publishing strategy.
Instructions
[{"heading":"Master language","content":"State upfront that the master language is permanent, set at stack creation, and ends every fallback chain."},{"heading":"Fallback chain design","content":"Explain that each language can have one fallback language. Describe inheritance as a chain such as fr-ca -> fr-fr -> en-us (master). Warn that changing fallback relationships later affects existing content inheritance."},{"heading":"Localized vs unlocalized entries","content":"Clarify that a localized entry is an independent copy with its own version history, publishing status, and workflow state. An unlocalized entry inherits from its fallback chain. Localizing is a one-way operation per locale and entry."},{"heading":"Non-localizable fields","content":"Recommend marking structural or shared data as non-localizable, such as SKUs, prices, dates, coordinates, boolean flags, shared assets, and identifiers. Keep human-readable text fields localizable."},{"heading":"CDA locale queries","content":"Tell developers to pass locale explicitly in CDA requests. Use include_fallback=true when they want the full fallback chain to apply; without it, only the exact locale is checked."},{"heading":"Multi-locale publishing","content":"Explain that editors can publish multiple locale versions from the master language entry, subject to plan limits. Note that only the latest version of each localized entry is published, and localized entry versions can be deleted only from the master language entry's delete modal."}],
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.
- yesterday First seen · 104 lines · 31 tokens per session scan A 2509b0dd52f7
08-cms-localization is a cursor rule published in the GitHub repository contentstack/contentstack-agent-skills (5 stars, last pushed 15d ago), licensed MIT. It adds 31 tokens to every session and 1,017 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 cursor rules, from other repositories
internationalization
Cursor rule "internationalization" from dtyq/magic, covering internationalization (i18n) rules, 国际化基本规范, 1. 文件结构, 2. 命名空间规范 and 3. 组件中使用国际化.
07-datagen
IF 生成物品/方块模型 JSON → 手动编写 JSON 在 src/main/resources/assets/{modid}/models/.
test-plan
Plan Katalon True Platform/TestOps testing for a release, sprint, or feature. Use when you need to translate quality goals into scope, prioritize testing by requirement coverage and risk, decide what to test first, or build the executable plan structure (folders, suites, and sprint/release association) that stands in…
wings
Authoring apps with the WINGS framework (Go compiled to WASM web components).
project-status
PriceGrab shipped state and product backlog (read first).
architecture
Architectural and cross-package changes — dependency direction, editor/runtime boundaries, scene schema, persistence, renderer packages. Use when changing package boundaries, serialized formats, or multiple layers. Do not apply to localized UI, styling, or test-only edits.