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/markmhendrickson/ateles/languagenpx skills add markmhendrickson/ateles --skill languagegit clone --depth 1 https://github.com/markmhendrickson/atelesWhat 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 | $0.00025 | $0.00832 |
| Opus 5 | $0.00013 | $0.00416 |
| Sonnet 5 | $0.00005 | $0.00166 |
| Haiku 4.5 | $0.00003 | $0.00083 |
Grade A, and why
language 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
language
Purpose
Define how /language requests process user text for fluency verification and translation (English, Spanish, Catalan).
Scope
Applies when the user invokes /language in this repository. Covers trigger logic, fluency checks, and translation steps.
Trigger logic
If the prompt starts with "Question: " (or equivalent in other languages), treat it as a question to answer directly. Do not treat as raw text for fluency/translation.
Equivalent question prefixes:
- English: "Question: ", "Query: "
- Spanish: "Pregunta: ", "Consulta: "
- Catalan: "Pregunta: ", "Consulta: "
Otherwise, treat the remaining text as raw text for fluency verification and translation.
Processing steps (for raw text)
1) Fluency verification
- Determine source language (English, Spanish, or Catalan)
- Verify fluency and naturalness in that language
- If corrections are needed, provide corrected text plus brief explanation for each change
- If already fluent, confirm and optionally suggest refinements
2) Translate to other languages
- Translate corrected text into the other two supported languages
- Supported languages: English, Spanish, Catalan
- Adapt wording for Barcelona, Spain (register, vocabulary, regional conventions)
3) Output format
For each translation include:
a. Translation text
The translated phrase/sentence.
b. Phonetics
- Provide IPA/simple phonetic transcription below each non-English translation
- For Catalan: include phonetics
- For Spanish: omit phonetics
c. Phonetics symbol guide
Include a phonetics reference link such as:
[IPA chart](https://www.internationalphoneticassociation.org/content/ipa-chart)
d. Google Translate link
Add GT link per translation, for example:
[GT](https://translate.google.com/?sl=en&tl=es&text=ENCODED_TEXT)
e. Regional relevance (mandatory)
Include a short note with:
- Primary region (for example Barcelona, Spain; Peninsular Spanish; Central Catalan)
- Register/context (formal, informal, neutral, literary, colloquial)
- Where phrase is more/less common (for example common in Spain, more typical in Latin America)
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 · 110 lines · 25 tokens per session scan A d087d82ac884
language is a skill published in the GitHub repository markmhendrickson/ateles (5 stars, last pushed 5d ago), licensed MIT. It adds 25 tokens to every session and 832 once invoked, about $0.0001 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
translate
다국어 번역 및 로컬라이제이션 (literal|natural|localize).
genpark-workspace-skill
GenPark skill for utilizing GenPark Workspace 4.0 features, including Claw for Desktop, MS Office Integration, Speakly Live Translation, and OpenCode workflows.
ai-work-market
Use when an AI agent needs to receive USDC payment for work that takes more than one minute — market research, code review, translations, dataset annotation, logo design. The buyer escrows USDC, the seller delivers proof, the buyer releases or disputes. Use for work contracts, NOT for atomic sub-minute pay-per-call…
odoo-18.0
Odoo 18 development reference for Python models and ORM (search, domain, readgroup, compute fields), XML/CSV data and views, OWL/JS client code, QWeb reports, security (ACL, record rules, groups), cron and server actions, migrations and module upgrades, tests, i18n, and performance. Use this skill whenever work…
apple-design
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading)…
omnicaptions-translate
Context-aware caption translation skill for SRT/VTT/ASS with bilingual output and optional Gemini CLI fallback.