Data Formulator is an interactive workspace where AI agents connect to data sources, answer questions, and create visualizations. It is used to explore and analyze data while branching into related questions without losing the context of each investigative path.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/microsoft/data-formulatornpx agentmods add rules/microsoft/data-formulator/i18n-no-hardcoded-stringsWrote 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/rules/microsoft/data-formulator/i18n-no-hardcoded-strings)<a href="https://agentmods.dev/rules/microsoft/data-formulator/i18n-no-hardcoded-strings"><img src="https://agentmods.dev/badge/rules/microsoft/data-formulator/i18n-no-hardcoded-strings/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/microsoft/data-formulator/i18n-no-hardcoded-strings"><img src="https://agentmods.dev/badge/rules/microsoft/data-formulator/i18n-no-hardcoded-strings.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00688 | $0.00688 |
| Opus 5.5 | $0.00275 | $0.00275 |
| Sonnet 5.5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
i18n-no-hardcoded-strings 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 1mo 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
i18n: No Hardcoded UI Strings
All user-visible text in the frontend MUST go through the i18n system. Never hardcode Chinese, English, or any other language string directly in components.
How to Use
import { useTranslation } from 'react-i18next';
const { t } = useTranslation();
// ✅ GOOD
<Button>{t('common.save')}</Button>
<Tooltip content={t('chart.noData')} />
// ❌ BAD
<Button>保存</Button>
<Button>Save</Button>
<Tooltip content="No data available" />
Non-Component Contexts (thunks, utilities, helpers)
When you cannot use hooks (Redux thunks, plain .ts utilities, store helpers), import the i18n instance directly:
import i18n from '../i18n';
// ✅ GOOD — works outside React components
i18n.t('messages.rowLimitReached', { count: 20000 })
// ❌ BAD — hooks only work inside React function components
const { t } = useTranslation(); // will crash in a thunk
The same rule applies: every user-visible string must use i18n.t() with a translation key, never a hardcoded literal.
Translation Files
- English:
src/i18n/locales/en/<namespace>.json - Chinese:
src/i18n/locales/zh/<namespace>.json - Namespaces:
common,upload,chart,model,encoding,messages,navigation,dataLoading,errors
When adding a new key, add it to both en and zh locale files. Pick the namespace that fits; create a new namespace only if none applies.
What Counts as User-Visible
Must use t(): button labels, tooltips, placeholders, error messages, dialog titles, tab names, toast notifications, table headers, empty-state text.
May stay hardcoded: log messages (console.log), error messages thrown but never displayed, internal constants, CSS class names, test IDs.
Cross-stack sentinel values — strings shared between frontend and backend as identity markers (e.g. UNTITLED_SESSION in dfSlice.ts used by both Redux state and backend workspace API) must NOT be translated. They are internal constants, not display text. Translate them only at the UI rendering layer by mapping the sentinel to t('...').
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.
- 1mo ago First seen · 75 lines · 688 tokens per session scan A d64d3af9496c
i18n-no-hardcoded-strings is a cursor rule published in the GitHub repository microsoft/data-formulator (17,610 stars, last pushed today), licensed MIT. It adds 688 tokens to every session, about $0.0028 per session on Opus 5.5. 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 2026-08-30.
Other cursor rules, from other repositories
internationalization
A set of rules for internationalization, the practice of adapting an application for multiple languages and regions. It covers file structure, translation namespaces, and using translations in components.
cmd-moodle-mustache-lint
Lint Mustache templates for accessibility, security, hard-coded strings, and Moodle template conventions. (invoke by typing: @moodle-mustache-lint).
chinese-language
A language rule that requires replies, comments, and commit messages to use Simplified Chinese unless another language is requested.
rtl-right-to-left-i18n-cursorrules-prompt-file
Cursor rule "rtl-right-to-left-i18n-cursorrules-prompt-file" from XD3an/awesome-ai-coding-all-in-one, covering rtl (right-to-left) development rules, core rules, 1. logical css properties, 2. tailwind css logical classes and 3. react native logical properties.
uninettuno-monografia
Regole UNINETTUNO per tesi TRIENNALE in italiano, con termini tecnici inglesi ammessi.
report
A set of rules for generating HTML dashboards that present data and analysis in Korean. It defines the required page structure, visual libraries, fonts, and report content.