What is centian CLAUDE.md?

Project instructions for Centian, a command-line tool that places one management layer in front of multiple MCP servers. MCP servers provide tools that an AI assistant can call.

Guiding work on Centian's proxy, centralized MCP configuration, server enablement, and hooks that run before or after tool requests.

They give the assistant the project's purpose, architecture, configuration location, server-management behavior, and debugging guidance in one reference.

How T4cceptor/centian configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to T4cceptor/centian. 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/T4cceptor/centian/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/T4cceptor/centian

Made for: Claude Code.

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/t4cceptor/centian/claude-md/github.svg)](https://agentmods.dev/instructions/t4cceptor/centian/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/t4cceptor/centian/claude-md"><img src="https://agentmods.dev/badge/instructions/t4cceptor/centian/claude-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/t4cceptor/centian/claude-md"><img src="https://agentmods.dev/badge/instructions/t4cceptor/centian/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 845 This file is loaded in full into every session.

When invoked 845 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	$0.00845	$0.00845
Opus 5.5	$0.00338	$0.00338
Sonnet 5.5	$0.00169	$0.00169
Haiku 4.5	$0.00085	$0.00085

Measured 2mo ago against content hash 65ccd5179d9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

centian 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 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.

CLAUDE.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Centian

Project Name: Centian

Repository: https://github.com/T4cceptor/centian Repo Owner: T4cceptor (User) Repo Name: centian

Description: A CLI tool to proxy MCP servers, collect and configure their configurations at a single place, and enable lifecycle hooks for tool requests and their responses.

Purpose

Centian serves as a centralized proxy for Model Context Protocol (MCP) servers, providing:

MCP Server Proxy: Acts as a proxy layer for multiple MCP servers
Centralized Configuration: Collect and manage configurations for all MCP servers in one place
Lifecycle Hooks: Enable custom hooks for tool requests and their responses
Request/Response Management: Handle and transform MCP tool requests and responses

Architecture

The CLI tool is built in Go and provides a unified interface to interact with multiple MCP servers while offering configuration management and extensibility through lifecycle hooks.

Global Configuration System

Key Features:

Config Location: ~/.centian/config.json
Auto-initialization: Creates default config if none exists
Server Management: Add, remove, enable/disable MCP servers
Lifecycle Hooks: Pre/post request hooks and connection events
Validation: Built-in config validation
Project-based isolation: Optional multi-project layout for tenant separation

Main Components:

GlobalConfig - Root configuration structure with proxy settings and either flat gateways (legacy) or named projects
ProjectConfig - Per-project configuration holding gateways, processors, capabilities, auth, and metadata. Each project gets its own SQLite database, route prefix, and feature flags
MCPServer - Individual server configurations with command, args, environment variables
ProxySettings - Bind address, port, logging, timeouts (truly global settings)
HookSettings - Lifecycle hooks for request/response interception

Config Layouts:

Legacy flat: gateways, processors, auth at the top level of GlobalConfig (auto-migrated to a "default" project at runtime via ResolveProjects())
Project-based: named ProjectConfig entries under "projects", each with its own gateways, processors, capabilities, and auth

Read the full file on GitHub · 86 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 · 86 lines · 845 tokens per session scan A 65ccd5179d9e

Subscribe to this mod's changes

centian CLAUDE.md is an instructions file published in the GitHub repository T4cceptor/centian (16 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 845 tokens to every session, about $0.0034 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 2026-08-30.

Building agents ai ai-agent ai-agents ai-governance mcp mcp-server

centian CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
centian CLAUDE.mdT4cceptor/centian	Instructions file	16	4mo ago	Apache-2.0	A	845	Claude Code
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

centian: Instructions file for Claude Code