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 kyleoliveiro/sg-gov-skills --skill data-protectiongit clone --depth 1 https://github.com/kyleoliveiro/sg-gov-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/kyleoliveiro/sg-gov-skills/data-protection)<a href="https://agentmods.dev/skills/kyleoliveiro/sg-gov-skills/data-protection"><img src="https://agentmods.dev/badge/skills/kyleoliveiro/sg-gov-skills/data-protection/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/kyleoliveiro/sg-gov-skills/data-protection"><img src="https://agentmods.dev/badge/skills/kyleoliveiro/sg-gov-skills/data-protection.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 | $0.00209 | $0.02900 |
| Opus 5 | $0.00105 | $0.01450 |
| Sonnet 5 | $0.00042 | $0.00580 |
| Haiku 4.5 | $0.00021 | $0.00290 |
Grade A, and why
data-protection 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
data-protection: DP controls for SG government systems
You are building or auditing how a system stores, moves, and disposes of government data against the ICT&SS Policy Reform Data Protection family (DP-1..DP-8): where data may reside, encryption at rest and in transit, the cloud tenancy it lives in, sanitising and destroying the media it touched, preventing loss in flight, and telling users what classification they may put in.
Two facts anchor everything:
- DP-1 (data residency) sits in the Level-0 spine of every published SSP — mandatory, no deviation path, for cloud and on-prem alike. Residency is the one control you cannot trade away, and it fails quietly: a cross-region replica, an overseas DR target, or a managed service that processes in another region breaches it without any code change.
- The data classification determines the strength of everything else. Confirm the maximum classification (and sensitivity tier) with the data owner before assessing any DP control — "we think it's just OPEN data" is where breaches start.
What this family is not about
- Encryption algorithms and key management are CK (secure-coding-as). DP-2/DP-3 say that data at rest and in transit must be encrypted; the CK family owns how — the approved algorithms, key storage, and rotation. A weak cipher or a mishandled key is a CK finding, not a DP one.
- GenAI input safeguards are the Gen-AI overlay (gen-ai-security). For GenAI features, DLP on uploads is GA-6 and the classification disclosure at model inputs is DP-8 as shipped with that overlay. This skill owns DP-8 for ordinary internal applications and DP-7 for general data flows.
- Backups are BR (resiliency-recovery), access logs are LM (logging-monitoring). DP-1 still constrains where backups and logs may reside, but their lifecycle belongs to those families.
- The PDPA trap. Singapore public agencies are excluded from the PDPA; the public sector regime is the Public Sector (Governance) Act (PSGA) plus the ICT&SS/IM8 policies themselves — with criminal penalties for unauthorised disclosure or misuse of data by public officers. "The PDPA doesn't apply to us" is true and changes nothing about these obligations; vendors additionally carry them by contract. Never let a PDPA-exclusion claim excuse a DP control. (Context, not legal advice — route legal questions to the agency's counsel.)
What ships with it
7 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 · 203 lines · 209 tokens per session scan A 6639ab7f7353
data-protection is a skill published in the GitHub repository kyleoliveiro/sg-gov-skills (16 stars, last pushed 1mo ago), licensed MIT. It adds 209 tokens to every session and 2,900 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…