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-pdpagit 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-pdpa)<a href="https://agentmods.dev/skills/ntaffzii/skill-agents/thai-pdpa"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/thai-pdpa/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-pdpa"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/thai-pdpa.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 | $0.00135 | $0.01238 |
| Opus 5 | $0.00068 | $0.00619 |
| Sonnet 5 | $0.00027 | $0.00248 |
| Haiku 4.5 | $0.00014 | $0.00124 |
Grade A, and why
thai-pdpa 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thai PDPA (พ.ร.บ.คุ้มครองข้อมูลส่วนบุคคล พ.ศ. 2562)
Overview
A generic privacy notice translated from a GDPR template misses PDPA-specific requirements — most commonly, PDPA requires consent to be opt-in with no pre-checked boxes, and consent for non-essential purposes must be separable from the general terms of service. A model without this skill tends to produce a GDPR notice with Thai words substituted in, which reads as compliant but isn't structurally aligned with PDPA's consent mechanics.
Not legal advice. This skill drafts structure and language; it does not replace review by a lawyer or the organization's DPO before publishing a real privacy notice or consent flow.
When to use
- เขียน privacy notice / นโยบายความเป็นส่วนตัว สำหรับเว็บไซต์หรือแอป
- ออกแบบ consent banner / cookie consent ที่ไม่ติ๊ก checkbox ไว้ล่วงหน้า
- ตรวจสอบว่าข้อความขอความยินยอมที่มีอยู่เข้าข่าย dark pattern หรือไม่
- อธิบายสิทธิของเจ้าของข้อมูลส่วนบุคคลภายใต้ PDPA
When NOT to use
- Pure GDPR compliance work with no Thai data subjects — PDPA and GDPR overlap heavily (both are consent/rights-based frameworks) but have different specific requirements; don't cross-apply without checking
- The task needs a legally binding data processing agreement (DPA) between controller and processor — that's a contract-drafting task requiring a lawyer, not a template-fill task
Core knowledge
- PDPA = พระราชบัญญัติคุ้มครองข้อมูลส่วนบุคคล พ.ศ. 2562, in full enforcement since 1 June 2022 (after delayed effective dates for earlier compliance deadlines). Regulator is the PDPC (คณะกรรมการคุ้มครองข้อมูลส่วนบุคคล) via its office, the สคส.
- Valid consent must be: freely given, specific to each purpose, informed (clear language, not buried in T&Cs), and given by a clear affirmative action. No pre-ticked checkboxes — this is the single most commonly violated rule in copy-pasted GDPR templates.
- Sensitive personal data (มาตรา 26) — race/ethnicity, political opinion, religious belief, sexual behavior, criminal record, health data, disability, union membership, genetic/biometric data — requires explicit consent (a higher bar than general consent) or a specific statutory exemption. Do not lump sensitive-data consent into the same checkbox as general data processing.
- Legal bases beyond consent exist (contract performance, legitimate interest, legal obligation, vital interest, public task) — not every data use needs a consent checkbox; a privacy notice should state the correct basis per purpose, not default everything to "consent."
- Data subject rights: access, rectification, erasure, restriction of processing, data portability, objection, and withdrawal of consent. Withdrawal must be as easy as giving consent — a "call our office to unsubscribe" flow for something that was a one-click opt-in is itself a compliance gap.
- Cross-border transfer: transferring personal data outside Thailand requires the destination to have adequate protection standards or additional safeguards (e.g. contractual clauses, consent) — flag this explicitly if the notice covers a foreign-hosted service.
- Enforcement: administrative fines, criminal penalties for certain violations involving sensitive data, and civil liability including punitive damages are all possible under PDPA — this is a real regulatory regime, not a symbolic one, which is why the disclaimer in this skill is load-bearing.
What ships with it
2 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.
- 10d ago First seen · 56 lines · 135 tokens per session scan A edc73ea21582
thai-pdpa is a skill published in the GitHub repository ntaffzii/Skill-Agents (4 stars, last pushed 2d ago), licensed MIT. It adds 135 tokens to every session and 1,238 once invoked, about $0.0007 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
bionic-safety-net
Unified survival infrastructure: health, finance, legal safety, circuit breakers, and structural protection against all ruin classes. The last line of defense.
counterparty-guard
A Russian business-counterparty check based on an identification number called an INN. It gathers public records about a company or sole proprietor and presents deal-risk signals.
contract-review
A contract-checking tool for Russian law, aimed at small businesses without an in-house lawyer. It reviews supply, service, contractor, NDA, and SaaS agreements and explains risky or missing terms in plain language.
tax-calendar-proactive
A proactive tax calendar for Russian individual entrepreneurs and small limited companies. From a few business details, it identifies upcoming deadlines, estimated payments, and important thresholds such as VAT and the simplified-tax-system limit.
review-contract
A Russian-law contract review guide that explains agreements in plain language, identifies red flags, and prepares marked-up DOCX or PDF revisions. It uses the Russian Civil Code as its legal basis.
tax-prep
A tax-period preparation workflow for Russia’s simplified tax system (УСН), including selected calculations and a package for an accountant.