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 irapgit 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/irap)<a href="https://agentmods.dev/skills/jusso-dev/awesome-australian-compliance/irap"><img src="https://agentmods.dev/badge/skills/jusso-dev/awesome-australian-compliance/irap/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/irap"><img src="https://agentmods.dev/badge/skills/jusso-dev/awesome-australian-compliance/irap.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 | $0.00361 | $0.02714 |
| Opus 5 | $0.00180 | $0.01357 |
| Sonnet 5 | $0.00072 | $0.00543 |
| Haiku 4.5 | $0.00036 | $0.00271 |
Grade A, and why
irap 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IRAP - Information Security Registered Assessors Program
IRAP is the Australian Signals Directorate's programme that registers independent assessors to evaluate ICT systems and services against the Information Security Manual (ISM). The current authoritative methodology is the IRAP Common Assessment Framework (CAF) v1.0, April 2025, which replaced the earlier IRAP assessment process guide.
An IRAP assessment is not a certification. IRAP assessors do not certify, accredit, endorse, register or authorise systems. They identify security strengths and weaknesses so that an authorising officer can make a risk-based authorisation decision.
The minimum deliverables of an IRAP assessment are:
- IRAP Security Assessment Report (or IRAP Cloud Security Assessment Report) intended for authorising officers, system owners and risk owners.
- Controls Matrix (or Cloud Controls Matrix) intended for technical personnel and system administrators.
When to use this skill
- The user is preparing for, or responding to, an IRAP assessment.
- The user is writing an SSP, an SoA, a security risk management plan, or other Stage 1 inputs the assessor will request.
- The user is mapping shared responsibilities between a cloud or SaaS provider and the consumer agency.
- The user is reading an existing IRAP report from a provider and asking what to inherit, what to verify and what is theirs to implement.
- The user is preparing for an authorising officer's risk-based decision based on an IRAP report.
- The user is asking about a specific IRAP Assessment Requirement (IRAP-AR-XXXX).
- The codebase or estate contains artefacts the assessor will sample: IaC, IdP exports, monitoring config, DevSecOps pipelines, evidence packs.
What this skill knows
- The four CAF stages: Plan and prepare, Define the assessment boundary, Assess the controls, Produce the IRAP assessment report.
- The 46 IRAP Assessment Requirements (IRAP-AR-0001 through IRAP-AR-0046) grouped
under the CAF's seven quality standards (Report quality and terminology, Assessment
process and frameworks, Evidence gathering, Coverage, Objectivity, Technical accuracy
and completeness, Assessment integrity). See
./quality-standards.md. - The seven implementation outcomes and the rules around their use. See
./implementation-outcomes.md. - The four-tier evidence quality model (Excellent, Good, Fair, Poor) and the
assessment-degree matrix (Basic, Focused, Comprehensive). See
./evidence-quality.md. - The four sampling methodologies (Random, Stratified, Risk-based, Systematic). See
./sampling.md. - The distinction between assessment boundary and authorisation boundary, and
layered assessments. See
./boundaries.md. - The mandatory Conflict of Interest declaration to ASD IRAP via the Partner Portal, submitted at least 7 business days before commencement (IRAP-AR-0008 and -0009), and the obligation to update it throughout the engagement (IRAP-AR-0010).
- The role of the system authoriser (the agency that authorises the system based on the IRAP outcome) and the explicit prohibition on the assessor rating risk or making authorisation statements (IRAP-AR-0033, IRAP-AR-0041).
- The ISM-release-handling rule: use the latest ISM at start (IRAP-AR-0014); if 2 ISM releases lapse during the engagement, conduct a delta assessment (IRAP-AR-0015).
What ships with it
13 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.
- assessment-workflow.md 17 KB
- boundaries.md 7.2 KB
- engagement-letter-template.md 6.9 KB
- evidence-quality.md 5.1 KB
- examples/finding-response-register.md 4.7 KB
- examples/prescreening-questionnaire.md 9.9 KB
- examples/scoping-document.md 3.6 KB
- implementation-outcomes.md 5.5 KB
- organisational-intake.md 11 KB
- quality-standards.md 9.8 KB
- sampling.md 4.7 KB
- soa-template.md 3.7 KB
- ssp-template.md 6.7 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 · 173 lines · 361 tokens per session scan A 3fea67bd821c
irap is a skill published in the GitHub repository jusso-dev/awesome-Australian-compliance (2 stars, last pushed 1mo ago), licensed MIT. It adds 361 tokens to every session and 2,714 once invoked, about $0.0018 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
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
nda-review
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…