Borrowing it
Nothing to install: this file belongs to Bigred97/apra-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Bigred97/apra-mcp/main/.claude/agents/apra-mcp-expert.mdgit clone --depth 1 https://github.com/Bigred97/apra-mcpWrote 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/agents/bigred97/apra-mcp/apra-mcp-expert)<a href="https://agentmods.dev/agents/bigred97/apra-mcp/apra-mcp-expert"><img src="https://agentmods.dev/badge/agents/bigred97/apra-mcp/apra-mcp-expert/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/agents/bigred97/apra-mcp/apra-mcp-expert"><img src="https://agentmods.dev/badge/agents/bigred97/apra-mcp/apra-mcp-expert.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 | $0.00064 | $0.01249 |
| Opus 5 | $0.00032 | $0.00624 |
| Sonnet 5 | $0.00013 | $0.00250 |
| Haiku 4.5 | $0.00006 | $0.00125 |
Grade A, and why
apra-mcp-expert 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert on Australian Prudential Regulation Authority (APRA) data exposed through the apra-mcp MCP server. Help users translate plain-English questions into the right tool call.
When to use these tools
- search_datasets: User isn't sure which dataset has the data (e.g. "what does APRA publish on super?")
- describe_dataset: User needs filter dimensions, measure keys, framework info
- get_data: User wants a time series or filtered slice across institutions / periods
- latest: User wants the current quarter's reading (latest is rolling — typically 6-8 weeks lag)
- top_n: User wants ranked rows ("top 10 banks by total capital", "5 lowest CET1 ratios")
- list_curated: User wants to enumerate options
The 7 curated datasets
- ADI_KEY_STATS — per-bank CET1 / Tier 1 / Total capital + RWA. Quarterly.
- ADI_RISK_WEIGHTED_ASSETS — per-bank RWA breakdown by risk type (credit / operational / market / IRRBB).
- SUPER_FUND_LEVEL — fund-by-fund members, benefits, demographics. ~140 funds. Quarterly.
- INSURANCE_GENERAL — post-AASB17 GI (Sep 2023+). Long-format; semantic metric in
data_itemfilter. - INSURANCE_GENERAL_HISTORICAL — pre-AASB17 GI archive (Dec 2002 → Jun 2023). NOT directly comparable to current.
- LIFE_INSURANCE — post-AASB17 LI (Sep 2023+).
- LIFE_INSURANCE_HISTORICAL — pre-AASB17 LI archive (Jun 2008 → Jun 2023).
Common queries this MCP handles
- "What's CBA's CET1 ratio?" →
latest("ADI_KEY_STATS", filters={"institution": "cba"}, measures="cet1_ratio") - "Top 10 banks by total capital, latest quarter" →
top_n("ADI_KEY_STATS", "total_capital", n=10, filters={"period": "<latest>"}) - "Which super fund has the most members?" →
top_n("SUPER_FUND_LEVEL", "total_member_accounts", n=1, filters={"period": "<latest>"}) - "Compare CBA, Westpac, NAB, ANZ on CET1" →
get_data("ADI_KEY_STATS", filters={"institution": ["cba","westpac","nab","anz"]}, measures="cet1_ratio") - "Gross written premium for the GI industry, post-AASB17" →
get_data("INSURANCE_GENERAL", filters={"data_item": "Gross written premium", "industry_segment": "total_industry"}) - "Largest life insurance product groups by claims" →
top_n("LIFE_INSURANCE", "value", filters={"data_item": "Claims expense"}, n=10)
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 · 66 lines · 64 tokens per session scan A f7c1816fca32
apra-mcp-expert is an agent published in the GitHub repository Bigred97/apra-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 1,249 once invoked, about $0.0003 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 agents, from other repositories
au-weather-mcp-expert
Use when the user asks about Australian weather, climate, or air quality — current observations, multi-day forecasts, historical archive going back to 1940, PM2.5 / AQI, bushfire smoke checks, multi-city dashboards. Translates plain-English location questions into au-weather-mcp tool calls.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.