What is tweekit-mcp AGENTS.md?

Repository instructions for tweekit-mcp, an MCP server project. They explain where code belongs and how to install dependencies, run the server, deploy it, and test it.

Use them when changing the server, running local or production builds, checking endpoints, or adding and testing features.

They give a coding agent the project’s expected structure and commands, reducing mistakes during development or deployment.

How equilibrium-team/tweekit-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to equilibrium-team/tweekit-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/equilibrium-team/tweekit-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/equilibrium-team/tweekit-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/equilibrium-team/tweekit-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/equilibrium-team/tweekit-mcp/agents-md)

Your own site

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

Per session 1,033 This file is loaded in full into every session.

When invoked 1,033 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	$0.01033	$0.01033
Opus 5.5	$0.00413	$0.00413
Sonnet 5.5	$0.00207	$0.00207
Haiku 4.5	$0.00103	$0.00103

Measured 11d ago against content hash febb0c5e0474, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tweekit-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 11d 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 · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

server.py runs the FastMCP streamable HTTP server for local development; keep API helpers here.
functions/main.py exposes the Firebase HTTP entry point and ASGI bridge used in production.
functions/requirements.txt and functions/packages/ store vendored deps for Firebase; never edit generated wheels by hand.
scripts/deploy_firebase.sh handles vendoring plus firebase deploy; review flags before running.
scripts/deploy_cloud_run.sh builds via Cloud Build and deploys to Cloud Run (stage/prod targets).
Config roots (pyproject.toml, firebase.json, uv.lock) define Python deps and hosting rewrites.
test_server.py provides async smoke tests with fastmcp.Client; set the base URL per environment.
tests/ contains pytest suites for proxy, bundles, config files, and client SDK helpers.

Build, Test, and Development Commands

Install / sync deps: uv sync or pip install -e .[dev].
Run the MCP server locally: uv run python server.py (override with PORT=9090 …).
Smoke test endpoints: uv run python test_server.py --base-url <URL>.
Vendor Firebase deps: uv pip install -r functions/requirements.txt --target functions/packages (use pip if uv unavailable).
Deploy to Firebase: bash scripts/deploy_firebase.sh -p <PROJECT_ID> [--skip-vendor].
Deploy to Cloud Run: bash scripts/deploy_cloud_run.sh <stage|prod> --version <x.y.z>.
Full pytest suite (requires API secrets): TWEEKIT_API_KEY=… TWEEKIT_API_SECRET=… uv run python -m pytest.

Coding Style & Naming Conventions

Python ≥3.10 with PEP 8 defaults: four-space indents, snake_case functions, SCREAMING_SNAKE_CASE env constants.
Prefer async HTTP flows with httpx.AsyncClient; always call response.raise_for_status() and log via logging.getLogger(__name__).
Use docstrings on FastMCP tools/resources and include type hints so FastMCP preserves schema metadata.
Keep responses FastMCP-friendly (Image, File, or JSON-serializable payloads) and avoid leaking API credentials in logs.

Read the full file on GitHub · 55 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.

11d ago Changed · +1 lines · +95 tokens per session febb0c5e0474
2mo ago First seen · 54 lines · 938 tokens per session scan A cb13354a32bd

Subscribe to this mod's changes

tweekit-mcp AGENTS.md is an instructions file published in the GitHub repository equilibrium-team/tweekit-mcp (1 stars, last pushed today), licensed MIT. It adds 1,033 tokens to every session, about $0.0041 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.

tweekit-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tweekit-mcp AGENTS.mdequilibrium-team/tweekit-mcp	Instructions file	1	today	MIT	A	1,033	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

tweekit-mcp: Instructions file for Codex