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 jusso-dev/awesome-Australian-compliance --skill essential-eightgit clone --depth 1 https://github.com/jusso-dev/awesome-Australian-complianceWrote 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/jusso-dev/awesome-australian-compliance/essential-eight)<a href="https://agentmods.dev/skills/jusso-dev/awesome-australian-compliance/essential-eight"><img src="https://agentmods.dev/badge/skills/jusso-dev/awesome-australian-compliance/essential-eight/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/jusso-dev/awesome-australian-compliance/essential-eight"><img src="https://agentmods.dev/badge/skills/jusso-dev/awesome-australian-compliance/essential-eight.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 | $0.00243 | $0.02227 |
| Opus 5 | $0.00121 | $0.01113 |
| Sonnet 5 | $0.00049 | $0.00445 |
| Haiku 4.5 | $0.00024 | $0.00223 |
Grade A, and why
essential-eight 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Essential Eight
The Essential Eight is the ACSC's prioritised set of mitigation strategies for protecting internet-connected information technology networks. Each strategy has three Maturity Levels (ML1, ML2, ML3) representing increasing alignment against tradecraft of increasing sophistication. This skill helps an agent audit, design and document systems against the Essential Eight at PROTECTED or below.
When to use this skill
- The user asks for an Essential Eight audit, gap assessment, or maturity uplift plan.
- The user asks "is this repository / system / agency compliant at ML1 / ML2 / ML3".
- The user is writing an SSP, SoA or risk register that references E8 strategies.
- The user is mapping ISO 27001, NIST or CIS controls to Australian government expectations.
- The user is preparing for an IRAP assessment and needs E8 evidence collated.
- The codebase contains application allowlisting policies, patching automation, MFA wiring or backup tooling and the user wants those reviewed against the E8.
- The user explicitly mentions ACSC, cyber.gov.au, the Maturity Model, or the Assessment Process Guide.
Do not use this skill for general "is my app secure" questions. Use it when the Essential Eight is the specific lens the user is asking for, or when the user is producing artefacts that an IRAP assessor or ACSC reader will consume.
What this skill knows
- The eight mitigation strategies, in the order the ACSC publishes them:
- Application control
- Patch applications
- Configure Microsoft Office macro settings
- User application hardening
- Restrict administrative privileges
- Patch operating systems
- Multi-factor authentication
- Regular backups
- The three Maturity Levels and what differentiates them: ML1 mitigates commodity tradecraft,
ML2 mitigates tradecraft that invests more effort in target selection, ML3 mitigates
tradecraft that is adaptive and less reliant on public tools. The detail per strategy lives
in
maturity-levels/ml1.md,maturity-levels/ml2.md,maturity-levels/ml3.md. - The Essential Eight Assessment Process Guide (APG) methodology: scope, evidence types, sampling, and how assessors weight implementation, design and operation.
- Per-control implementation patterns and detection heuristics in
controls/*.md. - Three worked examples in
examples/: a Windows AppLocker / WDAC baseline, a macOS Gatekeeper and notarisation baseline, and a Linux fapolicyd baseline. - An audit checklist in
audit-checklists/that produces a per-control finding with evidence, gap, and a remediation that an engineer can action.
What ships with it
15 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.
- audit-checklists/e8-audit-checklist.md 11 KB
- controls/application-control.md 8.1 KB
- controls/ms-office-macros.md 5.8 KB
- controls/multi-factor-authentication.md 6.1 KB
- controls/patch-applications.md 6.9 KB
- controls/patch-operating-systems.md 6.2 KB
- controls/regular-backups.md 6.9 KB
- controls/restrict-admin-privileges.md 7.0 KB
- controls/user-application-hardening.md 6.0 KB
- examples/linux-fapolicyd.md 6.0 KB
- examples/macos-gatekeeper-notarisation.md 5.7 KB
- examples/windows-applocker-wdac.md 7.1 KB
- maturity-levels/ml1.md 4.7 KB
- maturity-levels/ml2.md 4.6 KB
- maturity-levels/ml3.md 4.6 KB
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 · 154 lines · 243 tokens per session scan A 5d66c15087e8
essential-eight is a skill published in the GitHub repository jusso-dev/awesome-Australian-compliance (2 stars, last pushed 1mo ago), licensed MIT. It adds 243 tokens to every session and 2,227 once invoked, about $0.0012 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
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…