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.
npx agentmods add instructions/t4cceptor/centian/claude-mdgit clone --depth 1 https://github.com/T4cceptor/centianWrote 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.
[](https://agentmods.dev/instructions/t4cceptor/centian/claude-md)<a href="https://agentmods.dev/instructions/t4cceptor/centian/claude-md"><img src="https://agentmods.dev/badge/instructions/t4cceptor/centian/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00845 | $0.00845 |
| Opus 5 | $0.00423 | $0.00423 |
| Sonnet 5 | $0.00169 | $0.00169 |
| Haiku 4.5 | $0.00085 | $0.00085 |
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 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.
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
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 · 86 lines · 845 tokens per session scan A 65ccd5179d9e
centian CLAUDE.md is an instructions file published in the GitHub repository T4cceptor/centian (15 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 845 tokens to every session, about $0.0042 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 2026-08-30.
Other instructions, from other repositories
mcp-air AGENTS.md
AGENTS.md instructions for VericyIO/mcp-air, covering agents.md, verification commands, node version, publishing and constants sync.
promptspeak-mcp-server CLAUDE.md
Claude Code instructions for chrbailey/promptspeak-mcp-server, covering promptspeak - claude instructions, general principles, pipeline execution rules, architecture and security enforcement (check 6).
councilof-ai AGENTS.md
AGENTS.md instructions for CSOAI-ORG/councilof-ai: ONE source of truth. All public surfaces (PyPI, npm, HF, Kaggle, GitHub org) are GENERATED MIRRORS from this monorepo.
councilof-ai CLAUDE.md
Claude Code instructions for CSOAI-ORG/councilof-ai, covering claude.md — csoai / councilof-ai agent coordination, deployed truth (build — still true), standing doctrine (binding — the gates enforce it), how we work (see council-os/playbook.md for the evidence) and guardrails.
csoai-static-deploy2 AGENTS.md
AGENTS.md instructions for CSOAI-ORG/csoai-static-deploy2, covering verify a signed card (most common task), or one command end-to-end, measure a system (the gspc server) and hard rules for agents.
openchronicle-mcp CLAUDE.md
Claude Code instructions for CSOAI-ORG/openchronicle-mcp, covering claude.md, project status file, project-specific notes, current sprint and build and development.