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 commands/zgsm-ai/costrict/roo-translategit clone --depth 1 https://github.com/zgsm-ai/costrictWhat 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 | $0.00010 | $0.00449 |
| Opus 5 | $0.00005 | $0.00225 |
| Sonnet 5 | $0.00002 | $0.00090 |
| Haiku 4.5 | $0.00001 | $0.00045 |
Grade A, and why
roo-translate 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.
This is a copy
92% identical to roo-translate — 32 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Perform translation and localization tasks for the CoStrict extension. This command activates the translation workflow with comprehensive i18n guidelines.
Quick Start
-
Identify the translation scope:
- If a specific language code is provided (e.g.,
de,zh-CN), focus on that language - If
allis specified, translate to all supported languages - If a string key is provided, locate and translate that specific string
- If a file path is provided, work with that translation file
- If a specific language code is provided (e.g.,
-
Supported languages: ca, de, en, es, fr, hi, id, it, ja, ko, nl, pl, pt-BR, ru, tr, vi, zh-CN, zh-TW
-
Translation locations:
- Core Extension:
src/i18n/locales/ - WebView UI:
webview-ui/src/i18n/locales/
- Core Extension:
Workflow
-
If adding new strings:
- Add the English string first
- Ask for confirmation before translating to other languages
- Use
apply_difffor efficient file updates
-
If updating existing strings:
- Identify all affected language files
- Update English first, then propagate changes
-
Validate your changes:
node scripts/find-missing-translations.js
Key Guidelines
- Use informal speech (e.g., "du" not "Sie" in German)
- Keep technical terms like "token", "Prompt" in English
- Preserve all
{{variable}}placeholders exactly - Use
apply_diffinstead ofwrite_to_filefor existing files
Examples
/roo-translate de- Focus on German translations/roo-translate all welcome.title- Translate a specific key to all languages/roo-translate zh-CN src/i18n/locales/zh-CN/core.json- Work on specific file
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 · 51 lines · 10 tokens per session scan A c315ec1465d9
roo-translate is a command published in the GitHub repository zgsm-ai/costrict (4,397 stars, last pushed 13d ago), licensed Apache-2.0. It adds 10 tokens to every session and 449 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to roo-translate, differing in 32 lines, and is treated as a copy.
Other commands, from other repositories
bump-plugin
Bump changed plugin and marketplace version.
audit-adapters
Read the AI Stack Expert agent definition at .claude/agents/ai-stack-expert.md to understand your role, expertise, and methodology. Then execute the following audit workflow.
commit-push-pr
Run tests, commit current work, push, and open a PR.
init-deep
Initiates a repository traversal to create localized PIPELINE-CONTEXT.md hierarchical context files.
analyst-init
Before executing this command, CONFIRM these files exist and are readable.
codebase-detection
Before executing this command, CONFIRM these files exist and are readable.