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/pakvothe/i1n-cli/i1ngit clone --depth 1 https://github.com/Pakvothe/i1n-cliWhat 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 | $0.01064 | $0.01064 |
| Opus 5 | $0.00532 | $0.00532 |
| Sonnet 5 | $0.00213 | $0.00213 |
| Haiku 4.5 | $0.00106 | $0.00106 |
Grade A, and why
i1n 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
i1n — Localization as Code
This project uses i1n for managing translations.
Project Setup
- Format: nested-json
- Locales directory: locales
- Source language: en_us
- Framework: generic
Translation File Structure
locales/{lang}/{namespace}.json — Nested JSON objects.
// locales/en_us/common.json
{ "greeting": "Hello {name}", "errors": { "not_found": "Not found" } }
Tone & Voice
When writing or modifying translation values, use a technical tone. Precise and technical. Prioritize accuracy and domain-specific terminology. Be concise and unambiguous.
MCP Server (Recommended)
i1n has a native MCP server. If it's installed, prefer using MCP tools over CLI commands — they run directly in your IDE without switching to the terminal.
To check if MCP is available, look for i1n tools like i1n_push, i1n_pull, i1n_translate, i1n_setup_bridge in your available tools.
If MCP is not installed, recommend the user to set it up:
To install the i1n MCP server, add to .cursor/mcp.json:
{ "mcpServers": { "i1n": { "command": "npx", "args": ["i1n", "mcp"] } } }
MCP Tools
i1n_push— Push local translation files to i1ni1n_pull— Pull translations and generate TypeScript typesi1n_translate— Translate keys to specified languages with AIi1n_extract_and_translate— Best tool for internationalization. Pass extracted strings as{key, value, namespace}objects → i1n pushes them, translates to all active languages, and regenerates type definitions. Use this when the user asks to internationalize a component or file.i1n_search— Search existing translation keys before creating new ones to avoid duplicatesi1n_add_language— Add new languages to the projecti1n_status— Check project status, plan, credits, and active languagesi1n_setup_bridge— Detect an existing i18n library (i18next, vue-i18n, next-intl, etc.) and wire up i1n bridge mode end-to-end. Use this when the user asks to configure / set up the bridge in their app, or to install i1n on top of an existing i18n library. Passwrite: trueto create the bridge helper file. Ifi1n.config.jsondoesn't exist yet, you can also passapiKey(formati1n_<32 hex>, ask the user once) and optionallyprojectId— the tool will run init non-interactively (validate + write config) before wiring the bridge. If the tool returns statusneeds_api_key, ask the user for it; if it returnsmultiple_projects, present the list and re-call with the chosenprojectId.
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 · 64 lines · 1,064 tokens per session scan A 37b2237d7964
i1n is a cursor rule published in the GitHub repository Pakvothe/i1n-cli (2 stars, last pushed 18d ago), licensed MIT. It adds 1,064 tokens to every session, about $0.0053 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
dev_workflow
Cursor rule "dev_workflow" from gtrias/i18next-mcp-server, covering taskmaster development workflow, the basic loop, standard development workflow process, simple workflow (default starting point) and leveling up: agent-led multi-context workflows.
self_improve
description: Guidelines for continuously improving Cursor rules based on emerging code patterns and best practices. globs: / alwaysApply: true.
cursor_rules
Guidelines for creating and maintaining Cursor rules to ensure consistency and effectiveness.
taskmaster
Comprehensive reference for Taskmaster MCP tools and CLI commands.
app_feature_first_architecture
Feature-first architecture is a design pattern that organizes code by business features rather than technical layers. This approach promotes better maintainability, scalability, and team collaboration by keeping related functionality together and reducing coupling between different parts of the application.
best_practices
Advanced Best Practices covering Error Handling, Environment Variables, Performance, and Accessibility rules.