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 skills add ntaffzii/Skill-Agents --skill thai-translategit clone --depth 1 https://github.com/ntaffzii/Skill-AgentsWrote 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/skills/ntaffzii/skill-agents/thai-translate)<a href="https://agentmods.dev/skills/ntaffzii/skill-agents/thai-translate"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/thai-translate/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/skills/ntaffzii/skill-agents/thai-translate"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/thai-translate.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 | $0.00113 | $0.01262 |
| Opus 5 | $0.00056 | $0.00631 |
| Sonnet 5 | $0.00023 | $0.00252 |
| Haiku 4.5 | $0.00011 | $0.00126 |
Grade A, and why
thai-translate 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 10d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thai ⇄ English Translation
Overview
English "you" and "I" are register-neutral; Thai is not. A literal translator maps "you" to คุณ everywhere, but a Thai speaker chooses among คุณ/ท่าน/พี่/น้อง/เธอ (and drops the pronoun entirely in many sentences) based on relative age, social distance, and formality — getting this wrong doesn't just sound stiff, it can read as rude or oddly intimate. This skill is the register/pronoun decision layer on top of translation, not a dictionary.
When to use
- แปล EN → TH หรือ TH → EN ที่มีบริบทของความสัมพันธ์ระหว่างผู้พูด-ผู้ฟัง (ลูกค้า, เพื่อนร่วมงาน, ผู้บังคับบัญชา, คนแปลกหน้า)
- แปลเอกสารที่ต้องคง tone (ทางการ/กึ่งทางการ/กันเอง)
- Translating dialogue, marketing copy, or correspondence where "who is speaking to whom" changes the correct pronoun and sentence-final particle
- Deciding whether a literal translation of an idiom will land, or needs a Thai-native equivalent instead
When NOT to use
- Machine-readable text with no human register (code, JSON keys, log messages) — plain literal translation is correct here, don't add pronouns or particles that don't belong
- The task is really
thai-government-form(formal letter salutation hierarchy) orthai-customer-service(apology-ladder register for support replies) — those skills have more specific register rules than general translation guidance; use them instead when the context matches
Core knowledge
Pronoun choice for "you" (2nd person) — pick by relationship, not by default:
| Thai | Register / relationship |
|---|---|
| คุณ | Neutral-polite default between adults who aren't close — safest default for a stranger or professional context without a clearer signal |
| ท่าน | High formal/respectful — addressing someone senior, a customer in very formal business writing, or in official documents |
| พี่ / น้อง | Used when relative age is known and the relationship is warm/informal — พี่ to someone older, น้อง to someone younger; wrong direction reads as presumptuous or oddly casual |
| เธอ | Informal, used among peers or by an older speaker to a clearly younger one; too casual for a stranger or professional context |
| Name / title + name | Common substitute for "you" in Thai — often more natural than any pronoun, especially in professional writing |
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.
- 10d ago First seen · 58 lines · 113 tokens per session scan A 81ad2a160a8f
thai-translate is a skill published in the GitHub repository ntaffzii/Skill-Agents (4 stars, last pushed yesterday), licensed MIT. It adds 113 tokens to every session and 1,262 once invoked, about $0.0006 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
auto-research
Research uncertain questions with an explicit, user-approved web search or ChatGPT consultation, then present options and wait for implementation approval.
harden
Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.
pake
Package any website or local web build into a lightweight desktop app using Pake (Tauri/Rust). Use when the user wants to: wrap a URL as a native app, build a desktop app from a website or a local dist/ folder, use Pake CLI to package a page, set up proxy for a packaged app, customize app icons or bundle IDs, or…
acceptance
End-to-end verification and self-evidence for a delivery in any repository, with or without a preconfigured verify plan. Discover an existing plan when one was handed to this run; otherwise author checks and publish a standalone acceptance. Pick the proving surface (CLI / web / desktop / iOS Simulator), drive the real…
therapeutic-ifs
Unified inner work engine: Schema deconstruction (diagnosis) + IFS therapy (treatment). Absorbs: schema-deconstruction.
dashboard-builder
Build self-contained interactive HTML dashboards with charts, filters, and tables. Generates a single browser-openable file — no server or dependencies required.