What is felt-mcp AGENTS.md?

A set of repository instructions for felt-mcp, an MCP server that connects AI assistants to Felt. It covers architecture decisions, changelog rules, Felt API documentation, commands, and Python coding standards.

Use it when modifying felt-mcp, reading its architecture records, updating its changelog, running linting or tests, or checking its Python formatting and type requirements.

It tells contributors which project decisions and quality checks apply before code is changed. This helps keep the server aligned with its documented architecture and Python style.

How kthy/felt-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to kthy/felt-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/kthy/felt-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/kthy/felt-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/kthy/felt-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/kthy/felt-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/kthy/felt-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/kthy/felt-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/kthy/felt-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/kthy/felt-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 996 This file is loaded in full into every session.

When invoked 996 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.

Model	Per session	Once invoked
Fable 5.1	$0.00996	$0.00996
Opus 5.5	$0.00398	$0.00398
Sonnet 5.5	$0.00199	$0.00199
Haiku 4.5	$0.00100	$0.00100

Measured 2mo ago against content hash f825abac7751, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

felt-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

This file provides guidance to AI agents working with code in this repository, which holds an MCP server for agentic interaction with [Felt]. More details in README.md.

Architecture Decision Records

Architecture decisions are documented in ADRs.md in the repository root. All code must adhere to the decisions recorded there.

Changelog

The project keeps a changelog in CHANGELOG.md. Usage is as described at https://keepachangelog.com/en/1.1.0/. You can also refer to https://raw.githubusercontent.com/Utiligize/configator-op/refs/heads/main/CHANGELOG.md to see how I want it to look.

SDK Docs

The MCP is built around the Felt API which has docs at https://developers.felt.com/rest-api/api-reference.

Commands

Lint, format and type check: just lint
Test: just test or for single test: uv run python -m pytest tests/path/to/test.py::test_function
re-run previously failed tests: just test-failed

Code Style Guidelines

Python version: 3.14 (strict)
Line length: 99 characters
Indentation: 4 spaces for Python files
Imports: Grouped by stdlib, third-party, local with alphabetical ordering
Type hints: Required for all functions (disallow_untyped_defs = true)
Naming: Follow Python conventions (snake_case for functions/variables, CamelCase for classes)
Docstrings: Follow PEP 257 for concise, single-line docstrings for simple functions, more detailed for complex functionality
Testing: Use pytest fixtures and appropriate mocking
Formatting: Enforced by Ruff with rules listed in pyproject.toml
Git commit messages: Use the Conventional Commits style
When importing Python packages, use the explicit style from <package> import <method>

MCP Tools & Configuration

Context7: Use for up-to-date documentation for third-party code libraries
SonarQube: See sonar-project.properties for project setup

Implementation Workflow

This repository follows GitHub Flow for version control and collaboration.

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.

2mo ago First seen · 123 lines · 996 tokens per session scan A f825abac7751

Subscribe to this mod's changes

felt-mcp AGENTS.md is an instructions file published in the GitHub repository kthy/felt-mcp (0 stars, last pushed 7mo ago), licensed MIT. It adds 996 tokens to every session, about $0.0040 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.

Building agents Languages Python

felt-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
felt-mcp AGENTS.mdkthy/felt-mcp	Instructions file	0	7mo ago	MIT	A	996	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

felt-mcp: Instructions file for Codex