What is garchi-cms-skills AGENTS.md?

Repository instructions for the Garchi CMS skills package, which connects AI agents to Garchi CMS, a headless content management system. They describe the package layout, its integrations, and the responsibilities of its three skills.

Use them when editing or validating the Garchi CMS integration, its manifests, MCP configuration, marketplace files, or the skills for building sites and managing or rendering content.

They help contributors change the correct files and preserve the repository's role as a distribution package rather than an application. They also clarify which skill handles site building, content rendering, or content management.

How lumenharbor/garchi-cms-skills configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to lumenharbor/garchi-cms-skills. 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/lumenharbor/garchi-cms-skills/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/lumenharbor/garchi-cms-skills

Made for: Claude Code, 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/lumenharbor/garchi-cms-skills/agents-md/github.svg)](https://agentmods.dev/instructions/lumenharbor/garchi-cms-skills/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/lumenharbor/garchi-cms-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/lumenharbor/garchi-cms-skills/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/lumenharbor/garchi-cms-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/lumenharbor/garchi-cms-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 801 This file is loaded in full into every session.

When invoked 801 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	$0.00801	$0.00801
Opus 5	$0.00400	$0.00400
Sonnet 5	$0.00160	$0.00160
Haiku 4.5	$0.00080	$0.00080

Measured 9d ago against content hash 5ba84d00ca69, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

garchi-cms-skills 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 9d 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 · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository guide

This repository is the canonical AI-agent integration for Garchi CMS, a headless CMS by LumenHarbor Digital Solutions Limited. It is a distribution package, not an application: no build step, no runtime code.

Layout

plugin.json              Agent Plugins v1 manifest (canonical)
mcp.json                 Agent Plugins v1 MCP config — hosted Garchi MCP, OAuth
.mcp.json                Same server, Claude Code / Codex manifest format
.app.json                Codex mapping to the registered Garchi ChatGPT connector
.claude-plugin/          Claude Code plugin + marketplace manifests
.codex-plugin/           Codex / ChatGPT plugin manifest
.agents/plugins/         Codex repo marketplace entry
skills/                  The three skills — the only place skill content lives
assets/logo.png          Marketplace logo

The skills

Skill	Responsibility
`garchi-build-site`	Orchestration: pick starter kit vs. integration, connect MCP, model content, verify content stays editable without code changes.
`garchi-render-content`	Application code that fetches and renders Garchi content.
`garchi-manage-content`	Content operations over the Garchi MCP server.

Their trigger conditions are deliberately disjoint. Keep them that way: an agent should be able to tell from the descriptions alone which one applies.

Working in this repository

skills/ is canonical. Never fork a skill per platform — the manifests all point at the same directory.
Manifests carry metadata only. If you change the plugin name, version, description or logo path, change it in every manifest in the same commit.
No secrets. Ever. The MCP entries carry a URL and nothing else; authentication is the client's OAuth flow against Garchi.
Skill references live beside their skill in references/. Cross-skill links use relative paths and are only valid when the whole plugin is installed — always pair them with a public URL fallback.
Do not vendor the starter kits. Reference the official repositories.

Read the full file on GitHub · 71 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.

9d ago First seen · 71 lines · 801 tokens per session scan A 5ba84d00ca69

Subscribe to this mod's changes

garchi-cms-skills AGENTS.md is an instructions file published in the GitHub repository lumenharbor/garchi-cms-skills (0 stars, last pushed 2d ago), licensed MIT. It adds 801 tokens to every session, about $0.0040 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 2026-08-31.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

garchi-cms-skills: Instructions file for Claude Code