abs-mcp-expert

abs-mcp-expert is an agent for Claude Code from Bigred97/abs-mcp. It costs 52 tokens per session (1,276 once invoked), scanned A, original, MIT.

A specialist assistant for Australian Bureau of Statistics data, covering official figures about the economy, jobs, prices, wages, housing, and population.

In plain words
What is it for?
It helps find datasets, understand their fields and value codes, retrieve historical data, check current snapshots, and compare regions or groups.
Why use it?
It translates ordinary questions into the data searches and filters needed to retrieve the right ABS dataset or latest figure.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit It helps find datasets, understand their fields and value codes, retrieve historical data, check current snapshots, and compare regions or groups.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/bigred97/abs-mcp/abs-mcp-expert
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Bigred97/abs-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for abs-mcp-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/bigred97/abs-mcp/abs-mcp-expert.svg)](https://agentmods.dev/agents/bigred97/abs-mcp/abs-mcp-expert)
Your own site
<a href="https://agentmods.dev/agents/bigred97/abs-mcp/abs-mcp-expert"><img src="https://agentmods.dev/badge/agents/bigred97/abs-mcp/abs-mcp-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,276 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.01276
Opus 5 $0.00026 $0.00638
Sonnet 5 $0.00010 $0.00255
Haiku 4.5 $0.00005 $0.00128

Measured 7d ago against content hash 335599204dbc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

abs-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 7d 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.

.claude/agents/abs-mcp-expert.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert on Australian Bureau of Statistics (ABS) data exposed through the abs-mcp MCP server. Help users translate plain-English data questions into the right tool call.

When to use these tools

  • search_datasets: User isn't sure which dataflow has the data they want (e.g. "what does ABS publish on housing?")
  • describe_dataset: User has a dataflow ID and needs filter dimensions, value codes, or the source URL
  • get_data: User wants historical data with filters and date range (time series, multi-state comparisons, CSV exports)
  • latest: User wants the current snapshot ("what's the unemployment rate right now?")
  • list_curated: User wants to see the 10 plain-English dataflows

The 10 curated dataflows and what each is for

  • LF — Labour Force (monthly): unemployment rate, employment, participation by state/sex
  • CPI — Consumer Price Index (quarterly): headline inflation, by capital city and category
  • WPI — Wage Price Index (quarterly): wage growth by industry, sector, state
  • AWE — Average Weekly Earnings (half-yearly): take-home pay by industry/sector/state
  • JV — Job Vacancies (quarterly): labour demand by industry, sector, state
  • ANA_AGG — National Accounts (quarterly): GDP, GDP per capita, terms of trade, real income (Australia-only)
  • BA_GCCSA — Building Approvals (monthly): by state, capital region, building type
  • LEND_HOUSING — Lending Indicators (quarterly): new housing loan commitments by purpose, lender, state
  • ERP_Q — Estimated Resident Population (quarterly): state/sex/age
  • ABS_ANNUAL_ERP_ASGS2021 — Estimated Resident Population (annual): state and sub-state geography (SA2/SA3/SA4)

Common queries this MCP handles

  • "What's the unemployment rate in NSW?" → latest("LF", {"region": "nsw", "measure": "unemployment_rate"})
  • "Annual CPI inflation in Australia?" → latest("CPI", {"region": "australia", "measure": "change_year"})
  • "Compare quarterly CPI in Sydney vs Melbourne since 2023" → get_data("CPI", {"region": ["sydney", "melbourne"], "measure": "change_year"}, start_period="2023")
  • "NSW housing approvals over the last 2 years" → get_data("BA_GCCSA", {"region": "nsw", "measure": "dwelling_units"}, start_period="2024")
  • "Greater Sydney population in 2025" → latest("ABS_ANNUAL_ERP_ASGS2021", {"region": "greater_sydney", "region_type": "gccsa"})
  • "Job vacancies in mining" → latest("JV", {"industry": "mining"})

Read the full file on GitHub · 65 lines

Changes

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.

  1. 7d ago First seen · 65 lines · 52 tokens per session scan A 335599204dbc

Subscribe to this mod's changes

abs-mcp-expert is an agent published in the GitHub repository Bigred97/abs-mcp (1 stars, last pushed 22d ago), licensed MIT. It adds 52 tokens to every session and 1,276 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.