agentmods.dev

asic-mcp CLAUDE.md

asic-mcp CLAUDE.md is an instructions file for Claude Code from Bigred97/asic-mcp. It costs 1,874 tokens per session, scanned A, a copy of ato-mcp CLAUDE.md, MIT.

Project-specific instructions for an MCP server connected to Australian Securities and Investments Commission public datasets. MCP is a standard way for software tools to provide data to an agent.

In plain words
What is it for?
Use them when developing or maintaining the ASIC public-data server and its Python package.
Why use it?
They document the data sources, formats, licences, curated datasets, required modules, and repository-specific cautions.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

not rated 0 19d ago A scan 1,874 tokens copy · 86% MIT
View the source file Bigred97/asic-mcp pypi.org
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.

agentmods
npx agentmods add instructions/bigred97/asic-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/Bigred97/asic-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 asic-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/bigred97/asic-mcp/claude-md.svg)](https://agentmods.dev/instructions/bigred97/asic-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/bigred97/asic-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/bigred97/asic-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,874 This file is loaded in full into every session.
When invoked 1,874 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 86% copy Near-identical to another mod 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 $0.01874 $0.01874
Opus 5 $0.00937 $0.00937
Sonnet 5 $0.00375 $0.00375
Haiku 4.5 $0.00187 $0.00187

Measured 5d ago against content hash 9c3eb037b3b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

asic-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.

Origin

This is a copy

86% identical to ato-mcp CLAUDE.md — 44 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

asic-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 Securities and Investments Commission (ASIC), via data.gov.au
Source URL https://data.gov.au/dataset/?organisation=australian-securities-investments-commission
Data format CSV (large registers) via CKAN-discovered URLs on data.gov.au
Licence CC-BY 3.0 Australia
Licence URL https://creativecommons.org/licenses/by/3.0/au/
Python module asic_mcp
PyPI package asic-mcp
GitHub https://github.com/Bigred97/asic-mcp

Curated datasets (13)

ASIC_FINANCIAL_ADVISERS · ASIC_AFS_LICENSEE · ASIC_AFS_AUTH_REP · ASIC_CREDIT_LICENSEE · ASIC_BANNED_PERSONS · ASIC_BANNED_ORGS · ASIC_LIQUIDATOR · ASIC_COMPANIES · ASIC_BUSINESS_NAMES · ASIC_CREDIT_REPRESENTATIVE · ASIC_AUDITORS · ASIC_SHORT_POSITIONS · ASIC_SMSF_AUDITORS

Repo-specific module set

Required (every sister): server.py, models.py, curated.py, client.py, cache.py, shaping.py, data/curated/*.yaml

Repo-specific extras:

  • parsing.py — large-CSV streaming reader (ASIC_AFS_AUTH_REP is ~50MB)
  • discovery.py — CKAN auto-discovery
  • catalog.py — search ranking

Repo-specific gotchas

  • Registers are flat snapshots, NOT time series. latest() would have dumped 359k+ rows by default; v0.1.1+ caps via limit=50 with DataResponse.truncated_at preserving original count.
  • Updated weekly by ASIC. stale threshold is 14 days for these registers.
  • Always pass filters (licensee_name, adviser_number, current_status) when possible — full-register dumps are last-resort.
  • top_n is intentionally absent. ASIC registers are flat entity snapshots (one row per licensee/adviser/banned-person). They don't have a numeric measure to rank by; "top 10 financial advisers" isn't a meaningful query. The latest(... limit=N) parameter already serves the "give me the first N rows matching these filters" use case. If a downstream caller wants alphabetical ranking, they can sort the records client-side.

Read the full file on GitHub · 134 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. 5d ago First seen · 134 lines · 1,874 tokens per session scan A 9c3eb037b3b8

Subscribe to this mod's changes

asic-mcp CLAUDE.md is an instructions file published in the GitHub repository Bigred97/asic-mcp (0 stars, last pushed 19d ago), licensed MIT. It adds 1,874 tokens to every session, about $0.0094 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to ato-mcp CLAUDE.md, differing in 44 lines, and is treated as a copy.

Building agentsResearchai-agentsasicaustraliamcpmcp-servermodel-context-protocol
Related

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.

Bigred97/ausdata-mcp-client · 1,756 tokens

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.

Bigred97/apra-mcp · 1,561 tokens

abs-mcp CLAUDE.md

Claude Code instructions for Bigred97/abs-mcp, covering abs-mcp, source, curated datasets, repo-specific module set and repo-specific gotchas.

Bigred97/abs-mcp · 2,085 tokens

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.

Bigred97/aihw-mcp · 1,739 tokens

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.

Bigred97/ato-mcp · 1,785 tokens

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.

Bigred97/rba-mcp · 1,916 tokens