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/fatihguner/foreman/language-commandgit clone --depth 1 https://github.com/fatihguner/foremanWhat 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 | $0.00030 | $0.01763 |
| Opus 5 | $0.00015 | $0.00881 |
| Sonnet 5 | $0.00006 | $0.00353 |
| Haiku 4.5 | $0.00003 | $0.00176 |
Grade A, and why
language-mode-commands 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/language
Sets the language for all system outputs. Every response — skill applications, diagnostic questions, playbook instructions, output templates, system messages — switches to the specified language. Internal processing remains in English; the system thinks in English but speaks in the target language.
/language [language]
Description
Sets the output language. Accepts full language names (case-insensitive) or ISO 639-1 codes. The change takes effect immediately and persists across sessions.
Syntax
/language [language-name-or-code]
Accepted Inputs
| Input | Resolved Language |
|---|---|
english, en, default |
English |
turkish, tr, türkçe |
Turkish |
spanish, es, español |
Spanish |
french, fr, français |
French |
german, de, deutsch |
German |
portuguese, pt, português |
Portuguese (Brazilian default) |
japanese, ja, 日本語 |
Japanese |
chinese, zh, 中文 |
Chinese (Simplified default) |
korean, ko, 한국어 |
Korean |
arabic, ar, العربية |
Arabic (MSA) |
dutch, nl, nederlands |
Dutch |
italian, it, italiano |
Italian |
russian, ru, русский |
Russian |
hindi, hi, हिन्दी |
Hindi |
pt-br, brazilian portuguese |
Portuguese (Brazilian) |
pt-pt, european portuguese |
Portuguese (European) |
zh-tw, traditional chinese |
Chinese (Traditional) |
| Any other model-supported language | Attempted — quality depends on model fluency |
Examples
Example 1: Switch to Turkish
User: /language turkish
System: Dil Türkçe olarak ayarlandı. Bundan sonraki tüm çıktılar
Türkçe olarak sunulacak. Komut sözdizimi (/apply, /diagnose, /run)
İngilizce kalacaktır.
İngilizce'ye dönmek için: /language default
Example 2: Switch to Spanish
User: /language es
System: Idioma configurado a español. Todas las respuestas del sistema
se entregarán en español a partir de ahora. La sintaxis de los comandos
(/apply, /diagnose, /run) permanece en inglés.
Para volver al inglés: /language default
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 · 228 lines · 30 tokens per session scan A 3e9374e7104f
language-mode-commands is a command published in the GitHub repository fatihguner/foreman (47 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 1,763 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
bug-report
Draft a bug-report issue title + body from the user's prompt and the current conversation context, then print a GitHub Issues URL with both URL-encoded into ?title=&body=. The user reviews on github.com and clicks Submit; the plugin does not auto-submit.
prompt
System instructions for writing effective prompts. Apply when generating commands, skills, agents, or any LLM instructions.
sdlc-implement
Standalone issue implementation with Ralph Loop — implements a single Linear issue or free-form spec using fullstack-engineer + self-correcting retry loop.
sdlc
Master orchestrator for the complete 5-phase SDLC pipeline. Runs all phases sequentially with approval gates and handoffs between each phase. Organizes artifacts into handoffs/, docs/, and projects/ directories.
doctor
Check the Modellix CLI install, credential resolution, API connectivity, and balance.
tasks
Inspect Modellix task status and recover tasks after a timeout or unknown submission.