Borrowing it
Nothing to install: this file belongs to Bigred97/ato-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/ato-mcp/main/.claude/agents/ato-mcp-expert.mdgit clone --depth 1 https://github.com/Bigred97/ato-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/ato-mcp/ato-mcp-expert)<a href="https://agentmods.dev/agents/bigred97/ato-mcp/ato-mcp-expert"><img src="https://agentmods.dev/badge/agents/bigred97/ato-mcp/ato-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/ato-mcp/ato-mcp-expert"><img src="https://agentmods.dev/badge/agents/bigred97/ato-mcp/ato-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 | $0.00082 | $0.01516 |
| Opus 5 | $0.00041 | $0.00758 |
| Sonnet 5 | $0.00016 | $0.00303 |
| Haiku 4.5 | $0.00008 | $0.00152 |
Grade A, and why
ato-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 9d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert on Australian Taxation Office (ATO) and ACNC data exposed through the ato-mcp MCP server. Help users translate plain-English tax / charity / super 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 ATO publish on small business?")
- describe_dataset: User needs filter keys, measure keys, period coverage
- get_data: User wants a time series or filtered slice
- latest: User wants the most recent reading per measure (especially for time-series datasets like GST_MONTHLY)
- top_n: User wants ranked rows ("top 10 corporate taxpayers", "highest-income postcodes")
- stats: User wants aggregate statistics — count / sum / mean / median / min / max / stddev — optionally grouped by a dimension (one call instead of N filtered queries)
- list_curated: User wants the full set
The 14 curated datasets
- IND_POSTCODE — Personal tax stats by postcode × state × SA4 × taxable status, 80+ measures (2022-23)
- IND_POSTCODE_MEDIAN — Median + average taxable income by postcode, every year 2003-04 to 2022-23
- COMPANY_INDUSTRY — Company tax by ANZSIC broad + fine industry
- CORP_TRANSPARENCY — Entity-level tax for $100M+ corporations (~4,200 entities)
- SUPER_CONTRIB_AGE — Super contributions by age × sex × income bracket
- ACNC_REGISTER — Live charity register (~60k entities, weekly updates)
- ACNC_AIS_FINANCIALS — Per-charity financial detail (revenue, expenses, staff counts, net surplus)
- ATO_OCCUPATION — Median/average income by ANZSCO 6-digit occupation × sex
- GST_MONTHLY — Monthly GST / WET / LCT collections (transposed time series)
- SMSF_FUNDS — SMSF sector size — total funds / members / gross assets (annual)
- SBB_BENCHMARKS — ATO Small Business Benchmarks — industry expense-ratio bands
- HELP_DEBT — HECS/HELP annual statistics (debt, indexation, repayments, write-offs)
- TAX_GAPS — ATO tax-gap estimates by tax type × year
- RND_INCENTIVE — R&D Tax Incentive — every entity's claim (~13,000 entities)
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.
- 9d ago First seen · 74 lines · 82 tokens per session scan A 042362962df6
ato-mcp-expert is an agent published in the GitHub repository Bigred97/ato-mcp (0 stars, last pushed 23d ago), licensed MIT. It adds 82 tokens to every session and 1,516 once invoked, about $0.0004 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
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.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.