tuskledger-mcp: Instructions file for Codex

AGENTS.md

tuskledger-mcp AGENTS.md is an instructions file for Codex, OpenCode from BradMorphsters/tuskledger-mcp. It costs 1,179 tokens per session, scanned A, original, MIT.

A project instruction file for tuskledger-mcp, a local connector between an AI assistant and the Tusk Ledger personal-finance application.

In plain words
What is it for?
It guides safe development of read-only finance-data tools, input rules, tests, and project documentation.
Why use it?
It tells coding agents how the project works and keeps them within its local-only permission boundaries.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md.

This is BradMorphsters/tuskledger-mcp's own configuration. It tells Codex and OpenCode how to work on tuskledger-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 tuskledger-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to BradMorphsters/tuskledger-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/BradMorphsters/tuskledger-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/BradMorphsters/tuskledger-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 tuskledger-mcp AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/bradmorphsters/tuskledger-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/bradmorphsters/tuskledger-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,179 This file is loaded in full into every session.
When invoked 1,179 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 $0.01179 $0.01179
Opus 5.5 $0.00472 $0.00472
Sonnet 5.5 $0.00236 $0.00236
Haiku 4.5 $0.00118 $0.00118

Measured 2mo ago against content hash 752334427c7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tuskledger-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 2mo 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 · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Working memory for AI assistants (Claude Code, Cursor, Cowork, etc.) operating on this repository. Read this first.

What this project is

tuskledger-mcp is a Model Context Protocol server that runs locally on a user's machine and gives their AI assistant typed access to data in their Tusk Ledger install. It's a thin adapter — the actual finance data and logic live in the main tuskledger app; this package just translates MCP tool calls into HTTP requests against that app's local FastAPI backend (http://127.0.0.1:8000 by default).

Local-first, no exceptions. Nothing here calls out to the network. The only HTTP destination is 127.0.0.1. If you find yourself writing a request to a non-localhost URL, stop and ask the user.

Permission boundaries

Safe to do without asking

  • Add a new tool that wraps an existing read-only backend endpoint
  • Improve a tool description (LLM tool-selection accuracy depends on these)
  • Tighten input schemas (additionalProperties: false, required fields, etc.)
  • Add tests
  • Update the README, CHANGELOG, or AGENTS.md

Ask the user first

  • Add a tool that performs a write/mutation
  • Bump the mcp SDK version
  • Change the JSON shape of any tool's output (it's a contract for the LLM caller)
  • Change the env-var names (users have these wired in their MCP client config)

Never do without explicit user instruction

  • Add a tool that performs a destructive operation (delete a transaction, remove a connected account, rotate keys, etc.)
  • Add a non-localhost HTTP destination
  • Capture, log, or transmit Plaid tokens, balances, or transaction details outside the user's machine
  • Change the package name (it's published as tuskledger-mcp)

Repo structure

tuskledger-mcp/
├── README.md            ← user-facing install + usage docs
├── AGENTS.md            ← you are here
├── CHANGELOG.md
├── LICENSE              ← MIT
├── pyproject.toml       ← package metadata, deps, console script
├── tuskledger_mcp/
│   ├── __init__.py      ← __version__
│   ├── __main__.py      ← `python -m tuskledger_mcp` entry
│   ├── client.py        ← TuskLedgerClient: sync httpx wrapper
│   └── server.py        ← TOOLS list + _dispatch + build_server + serve_stdio
└── tests/
    └── test_server.py   ← dispatch + schema invariants

Read the full file on GitHub · 123 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. 2mo ago First seen · 123 lines · 1,179 tokens per session scan A 752334427c7c

Subscribe to this mod's changes

tuskledger-mcp AGENTS.md is an instructions file published in the GitHub repository BradMorphsters/tuskledger-mcp (0 stars, last pushed 16d ago), licensed MIT. It adds 1,179 tokens to every session, about $0.0047 per session on Opus 5.5. 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

tuskledger-mcp AGENTS.md compared with instructions from other repositories

tuskledger-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
tuskledger-mcp AGENTS.mdBradMorphsters/tuskledger-mcpInstructions file016d agoMITA1,179Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode