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 Boom-Vitt/claude-thai-skills --skill thai-text-processinggit clone --depth 1 https://github.com/Boom-Vitt/claude-thai-skillsWrote 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/boom-vitt/claude-thai-skills/thai-text-processing)<a href="https://agentmods.dev/skills/boom-vitt/claude-thai-skills/thai-text-processing"><img src="https://agentmods.dev/badge/skills/boom-vitt/claude-thai-skills/thai-text-processing/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/boom-vitt/claude-thai-skills/thai-text-processing"><img src="https://agentmods.dev/badge/skills/boom-vitt/claude-thai-skills/thai-text-processing.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 | $0.00193 | $0.03251 |
| Opus 5 | $0.00097 | $0.01625 |
| Sonnet 5 | $0.00039 | $0.00650 |
| Haiku 4.5 | $0.00019 | $0.00325 |
Grade A, and why
thai-text-processing 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 12d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thai Text Processing (ประมวลผลข้อความภาษาไทยในโค้ด)
Overview
Thai is written without spaces between words, uses combining tone marks, and does not sort by codepoint. Naive code that works for English silently corrupts Thai: "ฉันกินข้าว".split(" ") returns one token, ORDER BY name puts vowels in the wrong place, and LEFT(name, 20) may chop a syllable mid-character and render ◌. This skill is the checklist of things to fix.
When to use
- ตัดคำภาษาไทย (segmentation) สำหรับ search, autocomplete, n-grams
- Unicode normalization (NFC) ก่อนเก็บ / เทียบสตริง
- จัดเรียง (sort / collate) ชื่อภาษาไทยใน DB หรือ list
- ทำ romanization สำหรับ slug, passport-style spelling, academic citation
- ตั้งค่า full-text search index ใน ES / Postgres / MySQL
- ตัดข้อความ (truncate) แบบไม่ทำให้ glyph แตก
- เลือกไลบรารี: PyThaiNLP vs ICU vs nlpO3 vs Lucene Thai analyzer
1. The core problem: no spaces
"ฉันกินข้าว".split(" ") # ["ฉันกินข้าว"] ← one mega-token
This breaks:
- full-text search (
ILIKE '%กิน%'mostly works,ILIKE '%ข้าว%'mostly works, but ranking, stemming, autocomplete all need proper tokens) - word counting / "how long is this in words"
- text wrap / hyphenation
- n-gram features for ML
- highlight-on-search snippets
You must run a segmenter before any token-based operation.
2. Word segmentation toolkit
| Tool | Language | Notes |
|---|---|---|
PyThaiNLP word_tokenize |
Python | De-facto default. Engines: newmm (default, dict-based), longest, attacut (CNN), deepcut (LSTM, slow but accurate) |
| nlpO3 | Python via Rust | Fast newmm-style; permissive license |
ICU BreakIterator |
C / Java / Python (pyicu) |
Built into many platforms; decent for word-break |
| thai-segmenter | TypeScript | Browser-friendly; dictionary-based |
| Lucene Thai analyzer | Java | Use for Elasticsearch / OpenSearch indexing |
| SentencePiece / BPE | Any | For ML training; not for human-facing tokens |
Picking rules of thumb:
- Server Python: PyThaiNLP
newmm(good enough, fast, MIT) - Need higher recall on OOV / colloquial:
attacutordeepcut(slower) - Frontend JS:
thai-segmenteror call ICU via WebAssembly - Search index: dedicated Thai analyzer in ES (
thaitokenizer) — do not segment client-side and ship tokens to ES - Production at scale: nlpO3 for raw throughput
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 212 lines · 0 tokens per session scan A 09050003c41e
thai-text-processing is a skill published in the GitHub repository Boom-Vitt/claude-thai-skills (52 stars, last pushed 3mo ago), licensed MIT. It adds 193 tokens to every session and 3,251 once invoked, about $0.0010 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 skills, from other repositories
globalize-now-cli-use
Manage Globalize translation resources using the CLI. Use this skill when the user asks to create a translation project, add or remove languages, connect a GitHub or GitLab repository, manage glossaries or style guides, invite team members, manage API keys, or perform any Globalize platform operation. Also use when…
globalize-now-project-setup
Create a Globalize translation project, connect a GitHub or GitLab repository, and set catalog file patterns. Use this skill when the user asks to create a Globalize project, connect their repo to Globalize, or wire their translation catalogs to the Globalize platform. Assumes the Globalize CLI is already installed…
css-i18n
Audit and convert CSS to use logical properties for RTL/bidirectional layout support. Use when the user asks to "make CSS RTL-safe", "use logical properties", "replace left/right with start/end", "audit CSS for i18n", "CSS internationalization", "fix CSS for RTL", "convert to logical properties", or when setting up…
globalize-now-account-setup
Install the Globalize CLI, authenticate, and verify your organization. Use this skill when the user asks to set up Globalize, install the Globalize CLI, sign in or authenticate with Globalize, or connect their Globalize account. Also use when the user mentions @globalize-now/cli-client or globalise-now-cli and needs…
lovable-i18n
Add multi-language support (i18n) to this Lovable app using Lingui. Use when the user asks to add i18n, internationalization, localization, or translations — "translate my app", "make my app multilingual", "add Spanish/French/German support", "add a language switcher", "support multiple languages", or "connect…
globalize-guide
Drive the full internationalization journey for a project — detect the stack, recommend a library, set up the chosen library, wrap existing strings, and connect a translation platform (Globalize.now, default-on). Use when the user asks to add or configure i18n, internationalization, localization, multi-language…