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 agentmods add instructions/bigred97/abs-mcp/claude-mdgit clone --depth 1 https://github.com/Bigred97/abs-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/instructions/bigred97/abs-mcp/claude-md)<a href="https://agentmods.dev/instructions/bigred97/abs-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/bigred97/abs-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.02085 | $0.02085 |
| Opus 5 | $0.01043 | $0.01043 |
| Sonnet 5 | $0.00417 | $0.00417 |
| Haiku 4.5 | $0.00209 | $0.00209 |
Grade A, and why
abs-mcp CLAUDE.md 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 5d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
abs-mcp
Sister MCP in the Australian Public Data stack. See ../CLAUDE.md for
portfolio-wide conventions; this file captures repo-specific details
plus the cross-sister discipline.
Source
| Source agency | Australian Bureau of Statistics (ABS) |
| Source URL | https://data.api.abs.gov.au/ |
| Data format | SDMX-XML 2.1 via the ABS Data API |
| Licence | CC-BY 4.0 International |
| Licence URL | https://creativecommons.org/licenses/by/4.0/ |
| Python module | abs_mcp |
| PyPI package | abs-mcp |
| GitHub | https://github.com/Bigred97/abs-mcp |
Curated datasets
LF · CPI (quarterly, cat 6401.0, headline inflation) · CPI_MONTHLY (monthly indicator with sub-categories + cities) · WPI · PPI_FD · JV · AWE · ANA_AGG · BA_GCCSA · BUILDING_APPROVALS · BUILDING_ACTIVITY (cat 8752.0, quarterly dwelling completions/commencements) · NOM · ABS_NOM_VISA_CY · LEND_HOUSING · ERP_Q · ABS_ANNUAL_ERP_ASGS2021 · C21_G01_POA · C21_G02_SA2 · C21_G02_POA · RT (historical, ceased Jul 2025) · HSI_M (live RT replacement)
CPI ↔ CPI_MONTHLY: the curated CPI dataset uses sdmx_dataflow_id: CPI_Q
indirection — customer-facing CPI resolves to ABS's quarterly cat 6401.0
product (so periods join WPI, ANA_AGG, PPI_FD on the quarterly grid).
Customers who want the monthly indicator (sub-category breakdown, per-city
series, faster cadence) call CPI_MONTHLY which maps to the SDMX CPI
dataflow keyed by FREQ=M. NOTE (2026): the old standalone CPI_M indicator
dataflow (cat 6484.0) FROZE at 2025-09 when ABS relaunched the complete
monthly CPI inside the main CPI dataflow; CPI_MONTHLY was re-pointed at
CPI (FREQ=M) in 0.12.1/0.13.0 so it stays current. Do NOT revert to CPI_M.
BUILDING_APPROVALS (leading, monthly, cat 8731.0) ↔ BUILDING_ACTIVITY (trailing, quarterly, cat 8752.0): approvals are the pipeline, activity is the delivered stock (completions). Pair both + NOM for the housing supply-vs-migration story.
Repo-specific module set
Required (every sister): server.py, models.py, curated.py, client.py, cache.py, shaping.py, data/curated/*.yaml
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.
- 5d ago First seen · 142 lines · 2,085 tokens per session scan A 9cf5c8310e13
abs-mcp CLAUDE.md is an instructions file published in the GitHub repository Bigred97/abs-mcp (0 stars, last pushed 19d ago), licensed MIT. It adds 2,085 tokens to every session, about $0.0104 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 instructions, from other repositories
ausdata-mcp-client CLAUDE.md
Claude Code instructions for Bigred97/ausdata-mcp-client, covering ausdata-mcp — typescript mcp client, critical — distinction from ausdata-mcp (python), typescript + mcp sdk rationale, architecture and tool surface.
apra-mcp CLAUDE.md
Claude Code instructions for Bigred97/apra-mcp, covering apra-mcp, source, curated datasets (13), repo-specific module set and repo-specific gotchas.
aihw-mcp CLAUDE.md
Claude Code instructions for Bigred97/aihw-mcp, covering aihw-mcp, source, curated datasets (8), repo-specific module set and repo-specific gotchas.
ato-mcp CLAUDE.md
Claude Code instructions for Bigred97/ato-mcp, covering ato-mcp, source, curated datasets (16), repo-specific module set and repo-specific gotchas.
rba-mcp CLAUDE.md
Claude Code instructions for Bigred97/rba-mcp, covering rba-mcp, source, curated datasets (15), repo-specific module set and repo-specific gotchas.
aemo-mcp CLAUDE.md
Claude Code instructions for Bigred97/aemo-mcp, covering aemo-mcp, source, curated datasets (10), repo-specific module set and repo-specific gotchas.