aus-accounting-mcp: Instructions file for Codex

AGENTS.md

aus-accounting-mcp AGENTS.md is an instructions file for Codex, OpenCode from ryanduguid/aus-accounting-mcp. It costs 434 tokens per session, scanned A, original, MIT.

A set of instructions for agents working on an Australian accounting MCP project. MCP is a standard way for an AI agent to call external tools and services.

In plain words
What is it for?
Use it to guide code changes, run the project's checks, handle money values safely, and preserve limits around ATO benchmarks, Payday Super, and certain Division 7A loan reviews.
Why use it?
It prevents agents from rewriting legal calculations, using client data in examples, inventing financial facts, or hiding warnings that require human review.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is ryanduguid/aus-accounting-mcp's own configuration. It tells Codex and OpenCode how to work on aus-accounting-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything aus-accounting-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ryanduguid/aus-accounting-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.

Copy the file
curl -O https://raw.githubusercontent.com/ryanduguid/aus-accounting-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/ryanduguid/aus-accounting-mcp

Made for: Codex, OpenCode.

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 aus-accounting-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ryanduguid/aus-accounting-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/ryanduguid/aus-accounting-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ryanduguid/aus-accounting-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ryanduguid/aus-accounting-mcp/agents-md/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.

agentmods 80×15 button for aus-accounting-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ryanduguid/aus-accounting-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ryanduguid/aus-accounting-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 434 This file is loaded in full into every session.
When invoked 434 The same file — it is already loaded in full.
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 $0.00434 $0.00434
Opus 5 $0.00217 $0.00217
Sonnet 5 $0.00087 $0.00087
Haiku 4.5 $0.00043 $0.00043

Measured 8d ago against content hash 2951f13e7cb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

aus-accounting-mcp AGENTS.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 8d 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.

AGENTS.md · 44 lines

What it actually says

Agent instructions

This package is an MCP facade. Keep statutory calculations in the delegated payday-super-checker, ato-benchmark-compare and div7a-loan-review engines; adapters may validate, translate and serialise, but must not reimplement their law or datasets.

  • Keep Division 7A limited to the delegated engine's reviewed s 109N and s 109E scope; refuse unsupported matters.
  • Keep repository fixtures and demonstrations synthetic-only; never add client data or present a fixture as a lodgment.
  • Route all MCP-boundary money parsing through aus_accounting_mcp.money; preserve finite decimal strings and the domain limits.
  • Never invent current rates, thresholds, law dates, source dates or missing facts. Mutable facts and citations remain owned by the delegated engines and official sources.
  • Preserve visible warnings, refusals, engine versions, no-advice language and the need for human review before consequential accounting action.

CI gates

These are the current commands in .github/workflows/ci.yml:

uv run --locked --extra dev pytest -q
uv run --locked --extra dev ruff check aus_accounting_mcp tests
uv run --locked --extra dev mypy aus_accounting_mcp

Supplementary local and release-readiness checks

These checks are not CI gates. Use them when their affected artifact changes:

uv sync --locked --extra dev
uv run --locked --extra dev python -m build
uv run --locked aus-accounting-mcp-demo
uv run --locked --extra dev python scripts/render_demo_image.py docs/quick-proof.txt docs/quick-proof.webp
uv run --locked --extra dev pytest -q tests/test_demo.py tests/test_demo_media.py tests/test_compatibility.py tests/test_engine_versions.py

Keep docs/quick-proof.txt as the accessible source of truth for docs/quick-proof.webp. Route publication through the existing release workflows; do not publish, tag, or change public metadata without explicit approval.

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. 8d ago Changed · -1 lines · -14 tokens per session 2951f13e7cb3
  2. 9d ago First seen · 45 lines · 448 tokens per session scan A 767d9bf4a70a

Subscribe to this mod's changes

aus-accounting-mcp AGENTS.md is an instructions file published in the GitHub repository ryanduguid/aus-accounting-mcp (0 stars, last pushed 9d ago), licensed MIT. It adds 434 tokens to every session, about $0.0022 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens