A setup command for using Anthropic Claude Code, a terminal-based AI coding tool, with Marko projects. It configures project guidance, Marko plugins, connected tools, and language-server completions.

Use it to install Marko's Claude Code settings, register its plugins and connected tools, and distribute Marko skills to a project.

It gives Claude Code the project-specific information and integrations needed to work with Marko code. The setup also preserves your own additions outside the generated guidance markers.

claude-code — Agent by marko-php

Install

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.

agentmods

npx agentmods add agents/marko-php/marko/claude-code

Clone the repo

git clone --depth 1 https://github.com/marko-php/marko

Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,732 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 findings. Scan, not verified.

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	$0.00032	$0.01732
Opus 5	$0.00016	$0.00866
Sonnet 5	$0.00006	$0.00346
Haiku 4.5	$0.00003	$0.00173

Measured 2d ago against content hash 0436c8d89f5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

claude-code scanned grade C with 2 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 2d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://claude.ai/install.sh | bash

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://claude.ai/install.sh | bash

packages/docs-markdown/docs/ai-assisted-development/agents/claude-code.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code is Anthropic's official CLI for Claude. devai:install gives it full Marko awareness by writing .claude/settings.json with the Marko plugin marketplace registration and enabling three Claude Code plugins: marko-skills, marko-lsp, and marko-mcp.

Prerequisites

Claude Code installed. The recommended method is the native installer (no Node.js required, auto-updates in the background):
```
curl -fsSL https://claude.ai/install.sh | bash
```
This covers macOS, Linux, and WSL; see the Claude Code setup docs for Windows and other options. The legacy npm install -g @anthropic-ai/claude-code still works, but the native installer is now the preferred path.
Authenticated. Run claude in your terminal and complete the browser sign-in on first launch (there is no separate auth login command — use /login inside a session to switch or manage credentials). Run claude doctor to confirm the installation type.
marko/devai installed (see Installation)

What devai:install writes

Running marko devai:install with Claude Code detected produces the following files:

AGENTS.md                          # Merged Marko guidelines (shared across agents)
CLAUDE.md                          # Includes @AGENTS.md and Claude-specific notes
.claude/settings.json              # Marketplace registration + enabled plugins

AGENTS.md and CLAUDE.md

The installer writes merged Marko guidelines to AGENTS.md. The CLAUDE.md file references it via @AGENTS.md and adds a short Marko tooling section that describes the three plugins and the skill authority directive (skills are canonical spec — do not infer from sibling code).

Both files are written inside a  marker block: each is created if absent, and on later runs only the marked region is refreshed — so anything you add outside the markers (your own project instructions in CLAUDE.md, extra guidelines in AGENTS.md) is preserved. Remove the markers to take full ownership and devai leaves the file alone. See Editing generated files. This is separate from the .marko/devai.json install marker described below, which only tracks whether devai has run.

Read the full file on GitHub · 101 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.

2d ago First seen · 101 lines · 32 tokens per session scan C 0436c8d89f5f

Subscribe to this mod's changes

claude-code is an agent published in the GitHub repository marko-php/marko (393 stars, last pushed 3d ago), licensed MIT. It adds 32 tokens to every session and 1,732 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Languages Writing and docs php php-framework php8

claude-code

Getting it into your agent

What it costs to keep this loaded

Grade C, and why

Downloads and executes remote codehighSupply chain

Makes network callslowCapability

How it starts

Prerequisites

What devai:install writes

AGENTS.md and CLAUDE.md

What this file has done since we first saw it

Other agents, from other repositories

fixture-reviewer

module-docs-sync

tdd-coach

quick-syntax

index

changelog-keeper