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 access-controlgit 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/access-control)<a href="https://agentmods.dev/skills/kyleoliveiro/sg-gov-skills/access-control"><img src="https://agentmods.dev/badge/skills/kyleoliveiro/sg-gov-skills/access-control/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/access-control"><img src="https://agentmods.dev/badge/skills/kyleoliveiro/sg-gov-skills/access-control.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 | $0.00204 | $0.03444 |
| Opus 5 | $0.00102 | $0.01722 |
| Sonnet 5 | $0.00041 | $0.00689 |
| Haiku 4.5 | $0.00020 | $0.00344 |
Grade A, and why
access-control 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
access-control: AC controls for SG government systems
You are setting up or auditing who and what can access a system, with which credentials, from which devices, and for how long against the ICT&SS Policy Reform Access Control family (AC-1..AC-16) — the family that governs accounts, identity, authentication, and privilege from creation to removal.
Three facts anchor everything:
- Medium-Risk Cloud puts AC-2, AC-3, AC-5, AC-6 at Level 0 — MFA for privileged accounts, disabling inactive/expired accounts, hardened endpoints for remote admin access, and changing default credentials are mandatory with no deviation path the moment a system handles Confidential / Sensitive High data. High-Risk Cloud CII adds AC-1 (least privilege) to Level 0. These are hygiene controls that lose their deviation path exactly when data sensitivity rises.
- Identity is split by audience. Public users needing high identity assurance use Singpass/Corppass MFA (AC-7); agency and internal users use Government-managed SSO such as WOG AAD (AC-7's recommendation, enforced through AC-12 SSO with MFA at the IdP). Building a bespoke login for either audience is the finding, not an implementation choice.
- Least privilege is grounded in the inventory. AC-1's statement grants minimum permissions "based on the account inventory implemented" — without the AC-14 inventory of accounts and access rights, deny-by-default has nothing authoritative to check grants against. Inventory first, then scope.
What this family is not about
- Application-layer auth mechanics are AS (secure-coding-as): password policy (AS-5), salted hashing (AS-6), per-request authorisation checks in code (AS-7), secrets storage (AS-8), login rate limiting (AS-4), session timeouts (AS-11). AC owns account and identity governance — a weak password hash is an AS-6 finding; an account nobody disabled is AC-3.
- Logging account and access changes is LM (logging-monitoring): LM-4/LM-7 capture account, access-rights, and authentication events; UEBA over account behaviour is LM-20. AC-16's compensating "audit logging and alerting" runs on LM machinery.
- Network position is NS. Firewalls, segmentation, and subnet ACLs are Network Security; AC-10 is precisely about not trusting network position — identity and device posture replace VPN reachability.
- Singpass/Corppass integration is its own skill. The login plumbing and TX-6 Myinfo pre-fill live in singpass / corppass; sg-service-shell only owns the surrounding DSS page shell (where the button sits). AC-7 is the cybersecurity-side mandate to use Singpass/Corppass MFA at all.
- Pipeline hardening is SD/SC (secure-pipeline). CI deploy keys fall under AC-13 rotation, but protected branches and CI gates are Secure Development.
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 · 228 lines · 204 tokens per session scan A 182ab7e93668
access-control is a skill published in the GitHub repository kyleoliveiro/sg-gov-skills (16 stars, last pushed 1mo ago), licensed MIT. It adds 204 tokens to every session and 3,444 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…