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/ushibo/brigade/i18nnpx skills add ushibo/brigade --skill i18ngit clone --depth 1 https://github.com/ushibo/brigadeWrote 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/ushibo/brigade/i18n)<a href="https://agentmods.dev/skills/ushibo/brigade/i18n"><img src="https://agentmods.dev/badge/skills/ushibo/brigade/i18n.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 | $0.00050 | $0.00413 |
| Opus 5 | $0.00025 | $0.00206 |
| Sonnet 5 | $0.00010 | $0.00083 |
| Haiku 4.5 | $0.00005 | $0.00041 |
Grade A, and why
i18n 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 5d 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
i18n Rules
Shared JSON Files Are High-Conflict
i18n JSON files (en.json, ru.json, etc.) are modified by many tasks. When editing:
- Surgical edits only. Never rewrite the entire file or large blocks. Add/rename only the specific keys you need.
- Never delete keys unless the task explicitly requires it. Other code may reference them.
- Always add to ALL locale files simultaneously. If you add a key to
en.json, add it toru.jsontoo (and vice versa). - Verify key references before renaming.
grep -r "old.key.name" src/to find all usages. Update code references or keep the old key as alias.
Key Naming Convention
Use nested JSON objects with dot-path access:
{
"section": {
"subsection": {
"key": "Value"
}
}
}
Access: t("section.subsection.key")
Pattern: {feature}.{context}.{label|hint|tooltip|action}
Adding Keys Checklist
- Add key to ALL locale JSON files
- Use
{{ variable }}for interpolation:"greeting": "Hello, {{ name }}" - Run tests — i18n-dependent tests will catch missing keys
- Check for dead keys: search codebase for removed
t("...")calls
Worktree Warning
When working in a git worktree, your copy of i18n files may be outdated. Other tasks may have added keys to main after your branch point. Your edits must be additive only — never remove or reorder existing keys.
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.
- 5d ago First seen · 45 lines · 50 tokens per session scan A bab720339cd0
i18n is a skill published in the GitHub repository ushibo/brigade (1 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 413 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 2026-08-31.
Other skills, from other repositories
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
cost-model
Standardized cost-estimation framework for greatcto plans. Forces explicit LLM cost, infra cost, human-supervision time, and the (defensible) human-equivalent comparison. Output format is parsable by the board's /api/cost path — must follow exactly.
stack-baseline
The pinned default technology stack for SMB Product-Builder products. One source of truth so the architect, app-scaffolder, auth-engineer, and senior-dev never re-decide the stack per build — they build ON it. Covers framework, ORM/DB, auth, UI, payments/email/SMS, files, jobs, testing, hosting, and observability…
vertical-construction
Domain knowledge for the construction vertical (contractors, field crews) so architect and pm don't spec construction products naively. Covers the vocabulary (bid vs estimate, takeoff, retainage, change order, AIA G702/G703, lien waiver, draw schedule), the non-obvious money rules that incumbents like Procore price…
pm
Project manager for GitHub issues: brainstorm design approaches, create structured issues optimized for LLM agent teams, triage and recommend what to work on next, audit and clean up stale issues, or deep-validate a single issue against the codebase. Triggers: create issue, plan work, new task, project manager, write…
fec-motion-interaction
用于设计、实现或审查前端交互动效、页面转场、滚动动画、Framer Motion、GSAP、Lottie、CSS 动画、动效强度、动画性能、减少动效行为或兼具表现力与可访问性的 UI 动效。不要用于仅 SVG 路径绘制、Canvas/WebGL 渲染或普通 hover 状态;中文触发词包括 动效设计、交互动效、页面转场、滚动动画、Framer Motion、GSAP。.