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 skills/marko-php/marko/create-modulenpx skills add marko-php/marko --skill create-modulegit clone --depth 1 https://github.com/marko-php/markoWhat 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 | $0.00120 | $0.02137 |
| Opus 5 | $0.00060 | $0.01069 |
| Sonnet 5 | $0.00024 | $0.00427 |
| Haiku 4.5 | $0.00012 | $0.00214 |
Grade A, and why
create-module 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 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.
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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a Marko module
A Marko module is a Composer package that the framework auto-discovers via the extra.marko.module flag. Modules can live anywhere — app/{name}/ for application code, modules/{vendor}/{name}/ for a distributable package dropped into a host project, packages/{name}/ in the framework monorepo, or vendor/{vendor}/{name}/ once installed from Packagist. The layout is identical in every case. Directory and Composer-name segments are always lowercase; only the PHP namespace is StudlyCase.
This skill is the canonical specification for a Marko module. Do not inspect existing modules in this project to infer layout — siblings may have drifted from spec. Copy the templates from assets/ verbatim, substitute placeholders, and stop.
Step 1 — Confirm the name, then pick a location
If the user did not give the module a name, ask for one before scaffolding anything. Do not invent a name, reuse a vendor as the name, or proceed with a placeholder.
Casing rule — read this before creating any directory
A module's identity has two forms that must stay in sync:
- Directory and Composer name → always lowercase. They are identical segment-for-segment, so a module can move between tiers (e.g.
modules/→vendor/) or be symlinked with zero path rewrites. - PHP namespace → always StudlyCase.
blog→Blog,my-payment→MyPayment.
So the name blog yields directory blog/, Composer name …/blog, and namespace …\Blog. Lowercase module directories are correct — do not capitalize them. The casing only flips to StudlyCase in the PHP namespace and the psr-4 autoload key. (If you have seen "lowercase module names" before and assumed it was a bug, it was not: the directory is supposed to be lowercase; only the namespace is StudlyCase.)
Pick the tier by where the module lives
| Tier | Directory | Composer name | Namespace | When |
|---|---|---|---|---|
| App-local | app/{name}/ |
app/{name} |
App\{Name} |
Application code, not distributed. The vendor segment is always the literal app — there is no project-derived vendor. |
| Distributable | modules/{vendor}/{name}/ |
{vendor}/{name} |
{Vendor}\{Name} |
A package you intend to publish or share, dropped into a host project. Two-segment, vendor-scoped. |
| Framework monorepo | packages/{name}/ |
marko/{name} |
Marko\{Name} |
Only when working inside the Marko monorepo itself (root contains packages/core/). |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 125 lines · 120 tokens per session scan A f4eced9985f8
create-module is a skill published in the GitHub repository marko-php/marko (393 stars, last pushed 3d ago), licensed MIT. It adds 120 tokens to every session and 2,137 once invoked, about $0.0006 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 skills, from other repositories
system-web-components
ALWAYS use when creating, modifying, or reviewing ANY front-end web components, widgets, or custom elements in this repository. Mandatory for all web component work — creating new components, modifying existing ones, registering in zolinga.json, writing component docs, or debugging component…
system-create-mcp-resource
Use when creating or updating MCP resources — static files exposed to MCP clients via resources/list and resources/read. Covers .meta.json descriptors, tenant filtering, URI rewriting, dynamic resources via mcp:resources/list event hook, and the mcp-system scheme.
system-create-mcp-tool
Use when exposing a Zolinga event handler as an MCP (Model Context Protocol) tool — i.e. a method clients can invoke via JSON-RPC tools/call. Covers handler class, manifest binding, JSON Schemas, the Tools\CallEvent contract, and the schema.response requirement enforced by McpToolsListHandler::collectTools().
system-inspect
How to query the Zolinga system's runtime state — merged manifest cache, API service stubs, configuration layers, and log files — using jq, grep, tail, and PHP.
system-create-handler
Use when creating a new event handler/listener in a Zolinga module, including event naming, class placement, origin filtering, rights checks, and event object selection.
system-create-mcp-prompt
Use when creating or updating MCP prompts — reusable prompt templates exposed to MCP clients via prompts/list and prompts/get. Covers .meta.json definitions, tenant filtering, content.uri file references, {{arg}} substitution, and the mcp-system scheme.