What is language-injection-conventions?

A set of rules for choosing a user's language in prompts sent to a language model and in fixed messages shown by a Python application. It defines where language instructions belong and how new languages are added.

Use it when building multilingual AI agents, code-generation endpoints, API routes, or Python-generated UI messages.

It prevents inconsistent translations, duplicate instructions, and accidental language changes in internal calls that users never see.

language-injection-conventions — Cursor rule by microsoft

Install

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.

agentmods

npx agentmods add rules/microsoft/data-formulator/language-injection-conventions

Clone the repo

git clone --depth 1 https://github.com/microsoft/data-formulator

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.

When invoked 537 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.00537
Opus 5	$0.00000	$0.00269
Sonnet 5	$0.00000	$0.00107
Haiku 4.5	$0.00000	$0.00054

Measured 2d ago against content hash 11e79d25ce18, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

language-injection-conventions 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.

.cursor/rules/language-injection-conventions.mdc · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Language Injection Conventions

Language flows per-request: Frontend i18n → Accept-Language header → get_language_instruction() → system prompt.

LLM Prompt Language Injection

User-facing LLM output MUST inject language via get_language_instruction(mode=...) in the route handler.
Mode selection: "full" for text-heavy agents, "compact" for code-generation agents and short-text endpoints.
Inject into system prompt only — use inject_language_instruction() from agent_language.py. Never inject into user messages.
Do NOT inject for non-user-facing calls (health checks, internal tool calls).
Do NOT duplicate — if upstream messages already contain language instruction, skip.
Do NOT use env vars, global interceptors, or hardcoded language strings (e.g. "回答请使用中文") — route handlers should use get_language_instruction(mode=...).
New language? Add to LANGUAGE_DISPLAY_NAMES in agents/agent_language.py and add locale files in src/i18n/locales/<lang>/.

Python-Side User-Visible Messages (message_code pattern)

For fixed strings in Python that are shown in the UI (error messages, clarify options, completion summaries), do NOT translate in Python. Instead:

Keep the English string as the default value.
Add a message_code (or content_code, error_code, summary_code) field with a key like "agent.someKey".
Optionally add message_params for interpolation.
The frontend translates using translateBackend(fallback, code, params) from src/app/utils.tsx.
Add the translation key to src/i18n/locales/{en,zh}/messages.json under the agent section.

# ✅ GOOD — backend returns code, frontend translates
yield {
    "type": "error",
    "message": "Output DataFrame is empty (0 rows).",
    "message_code": "agent.emptyDataframe",
}

# ❌ BAD — backend-side translation dict
yield {"message": translate_in_python("empty_df", lang)}

For detailed architecture and anti-pattern explanations, see docs/dev-guides/6-i18n-language-injection.md.

Read the full file on GitHub · 44 lines

Changes

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 · 44 lines · 0 tokens per session scan A 11e79d25ce18

Subscribe to this mod's changes

language-injection-conventions is a cursor rule published in the GitHub repository microsoft/data-formulator (17,048 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 537 tokens. 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.

Backend and APIs Frontend Security

language-injection-conventions

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Language Injection Conventions

LLM Prompt Language Injection

Python-Side User-Visible Messages (message_code pattern)

What this file has done since we first saw it

Other cursor rules, from other repositories

angular-20

dev-standard

typescript

coolify-ai-docs

python_lib

specs