What is CaddyUI-MCP AGENTS.md?

A project instruction file for CaddyUI-MCP, a Python server that lets an MCP client manage a Caddy reverse proxy through its web API. A reverse proxy directs web requests to services, and MCP is a way for an AI tool to call external services.

Use it when changing the CaddyUI-MCP project so agents follow its development process, code layout, dependency rules, and repository instructions.

It gives coding agents shared rules for the project, including where code belongs, how to test and deploy it, and which repository is authoritative.

How loryanstrant/CaddyUI-MCP configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to loryanstrant/CaddyUI-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/loryanstrant/CaddyUI-MCP/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/loryanstrant/CaddyUI-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/loryanstrant/caddyui-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/loryanstrant/caddyui-mcp/agents-md)

Your own site

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

Per session 774 This file is loaded in full into every session.

When invoked 774 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	$0.00774	$0.00774
Opus 5.5	$0.00310	$0.00310
Sonnet 5.5	$0.00155	$0.00155
Haiku 4.5	$0.00077	$0.00077

Measured 15d ago against content hash 5309af3e41fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

CaddyUI-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 15d 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 · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — CaddyUI-MCP

Start here (generated)

Read NAVIGATION.md - the repository map: docs, headings, entry points, public symbols, operations.
Use .agent/navigation.json when structured paths are easier to consume than prose.
Use the Gitea MCP server for live state: issues, pull requests, CI results.

Do not hand-edit NAVIGATION.md or .agent/navigation.json; they are generated by navgen (tools/navgen/navgen repo in dev-standards) and refreshed nightly.

Cross-tool agent instructions (Claude Code, Copilot agent mode). Gotcha: Copilot inline suggestions do NOT read this file — any rule that must hold for inline completions is mirrored into .github/copilot-instructions.md. Keep them in sync.

Project

An MCP server that wraps CaddyUI's /api/v1 REST API so an MCP client can manage a Caddy reverse proxy (proxy/redirection hosts, raw routes, certificates). Python 3.13 + FastMCP v3. Canonical repo on Gitea (gitea.strant.casa/loryanstrant/CaddyUI-MCP); GitHub is a one-way push mirror — never review/merge PRs there. Modelled on the ESPHome-MCP homelab template.

How to work here

Use the plan-before-coding and write-a-test-plan skills (global, in ~/.copilot/skills/ — also available to Claude Code). Apply dev-standards/standards/{core,generic}.md.
Smallest shippable slice; one thing at a time. No new tools/deps unless they replace something. Pin dependencies; prefer boring, proven libraries.
At end of a task, capture any reusable lesson in DECISIONS.md.

Layout

src/caddyui_mcp/client.py — async httpx client for /api/v1 (Bearer auth, typed errors).
src/caddyui_mcp/server.py — FastMCP tools (one per operation) + INSTRUCTIONS.
src/caddyui_mcp/__main__.py — main() (stdio) / main_web() (HTTP :8080) with a connectivity pre-flight.
healthcheck.py — drives the full MCP handshake for the container healthcheck.

Read the full file on GitHub · 58 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.

15d ago Changed · +14 lines · +140 tokens per session 5309af3e41fd
2mo ago First seen · 44 lines · 634 tokens per session scan A b844f65792d4

Subscribe to this mod's changes

CaddyUI-MCP AGENTS.md is an instructions file published in the GitHub repository loryanstrant/CaddyUI-MCP (3 stars, last pushed 15d ago), licensed MIT. It adds 774 tokens to every session, about $0.0031 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.

DevOps and cloud LLM caddy container docker mcp model-context-protocol

CaddyUI-MCP AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
CaddyUI-MCP AGENTS.mdloryanstrant/CaddyUI-MCP	Instructions file	3	15d ago	MIT	A	774	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	today	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

CaddyUI-MCP: Instructions file for Codex