What is finance-tools CLAUDE.md?

A set of Claude Code instructions for a template used to build Python MCP servers. The template runs its development tasks in Docker, a tool that packages software in isolated containers.

Use it when developing, formatting, checking, testing, or documenting a Python MCP server based on this template.

It explains the template’s structure, conventions, and every path that must be updated when replacing its placeholder server code.

finance-tools CLAUDE.md — Instructions file for coding agents by sinan-ozel: A set of Claude Code instructions for a template…

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/sinan-ozel/finance-tools/claude-md

Clone the repo

git clone --depth 1 https://github.com/sinan-ozel/finance-tools

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sinan-ozel/finance-tools/claude-md.svg)](https://agentmods.dev/instructions/sinan-ozel/finance-tools/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/sinan-ozel/finance-tools/claude-md"><img src="https://agentmods.dev/badge/instructions/sinan-ozel/finance-tools/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,490 This file is loaded in full into every session.

When invoked 1,490 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01490	$0.01490
Opus 5	$0.00745	$0.00745
Sonnet 5	$0.00298	$0.00298
Haiku 4.5	$0.00149	$0.00149

Measured 4d ago against content hash 3fb178e9e9d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

finance-tools 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 4d 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.

CLAUDE.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — MCP Server Template

This repo is a template for building Python MCP servers. It is not a runnable application itself — the server/ directory contains placeholder code that the user replaces with their actual tools.

Architecture

Every dev operation runs through Docker Compose. There is no expectation that Python or any tool is installed locally — Docker is the only requirement.

Dockerfile               ← root; builds the MCP server image
server/main.py           ← the MCP server (FastMCP, streamable-http, port 8000)
server/__init__.py       ← version string: __version__ = "x.y.z"
pyproject.toml           ← dependencies + tool config (black/ruff/isort/docformatter)

Key Conventions

Source directory

Server code lives in server/. All tooling (reformat, lint, test Dockerfiles) references server/. When the user renames this to their actual module name, they must update every path in: Dockerfile, reformat/Dockerfile, lint/Dockerfile, docs-validate/Dockerfile, tests/Dockerfile, tests/docker-compose.yaml, reformat/reformat.sh, lint/lint.sh, pyproject.toml.

Placeholders to replace

<SERVER-NAME> — hyphenated (Docker image name, GitHub repo name, badge URLs)
<ORGANIZATION> — GitHub org or username

Version

server/__init__.py holds __version__. CI reads it with a regex (no import needed). Bumping this above the last git tag triggers a stable Docker Hub release on the next main push.

MCP transport

FastMCP with transport="streamable-http". Endpoint at /mcp (POST). Port 8000. This is the current MCP standard — prefer it over the older SSE transport.

Always use Pydantic BaseModels with detailed Field descriptions when writing tools.

Directory Structure

reformat/               docker-compose + Dockerfile + reformat.sh
                        runs black, docformatter, isort on server/ and tests/
                        volume-mounts project root so changes write back to host

lint/                   docker-compose + Dockerfile + lint.sh
                        runs ruff check on server/ and tests/ (read-only)

docs-validate/          docker-compose + Dockerfile
                        runs mkdocs build --strict
                        volume-mounts project root for docs/ and mkdocs.yml

tests/                  docker-compose with TWO services:
                        1. mcp-server  — root Dockerfile, health-checked on port 8000
                        2. test        — tests/Dockerfile, waits for server healthy
                        test command: pytest --mcp-tools=http://mcp-server:8000 tests/

inspector/              docker-compose with TWO services:
                        1. mcp-server  — same as above
                        2. mcp-inspector — ghcr.io/modelcontextprotocol/inspector
                        inspector pre-pointed at http://mcp-server:8000/mcp
                        UI accessible at http://localhost:6274 (check logs for token)

.github/workflows/ci.yaml   full pipeline (see below)
.vscode/tasks.json           tasks: test, lint, reformat, validate-docs, inspector
scripts/semver_compare.py    used by CI to compare version strings

Read the full file on GitHub · 155 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.

4d ago First seen · 155 lines · 1,490 tokens per session scan A 3fb178e9e9d5

Subscribe to this mod's changes

finance-tools CLAUDE.md is an instructions file published in the GitHub repository sinan-ozel/finance-tools (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,490 tokens to every session, about $0.0075 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.

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 · 5,182 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

finance-tools CLAUDE.md