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/ohnotnow/devnotes/mcp-developmentnpx skills add ohnotnow/devnotes --skill mcp-developmentgit clone --depth 1 https://github.com/ohnotnow/devnotesWhat 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 | $0.00180 | $0.00867 |
| Opus 5 | $0.00090 | $0.00434 |
| Sonnet 5 | $0.00036 | $0.00173 |
| Haiku 4.5 | $0.00018 | $0.00087 |
Grade A, and why
mcp-development 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 today.
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.
This is a copy
100% identical to mcp-development — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Development
Documentation
Use search-docs for detailed Laravel MCP patterns and documentation.
For MCP UI apps (interactive HTML resources), read references/app.md — it covers the full architecture, host theming CSS variables, tool-to-UI linking patterns, library scripts (Tailwind, Alpine via Library), and real-world examples.
Basic Usage
Register MCP servers in routes/ai.php:
use Laravel\Mcp\Facades\Mcp;
Mcp::web();
Creating MCP Primitives
php artisan make:mcp-tool ToolName # Create a tool
php artisan make:mcp-resource ResourceName # Create a resource
php artisan make:mcp-prompt PromptName # Create a prompt
php artisan make:mcp-server ServerName # Create a server
php artisan make:mcp-app-resource DashboardApp # Create a UI app (2 files)
After creating primitives, register them in your server's $tools, $resources, or $prompts properties.
Tools
use Illuminate\Json\Schema\JsonSchema;
use Laravel\Mcp\Request;
use Laravel\Mcp\Response;
use Laravel\Mcp\Server\Tool;
class MyTool extends Tool
{
protected string $description = 'Describe what this tool does';
public function schema(JsonSchema $schema): array
{
return [
'name' => $schema->string()->description('The name parameter')->required(),
];
}
public function handle(Request $request): Response
{
$request->validate(['name' => 'required|string']);
return Response::text('Hello, '.$request->get('name'));
}
}
Registering Primitives in a Server
use Laravel\Mcp\Server;
class AppServer extends Server
{
protected array $tools = [
\App\Mcp\Tools\MyTool::class,
];
protected array $resources = [
\App\Mcp\Resources\MyResource::class,
];
protected array $prompts = [
\App\Mcp\Prompts\MyPrompt::class,
];
}
What ships with it
1 file 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.
- today First seen · 113 lines · 180 tokens per session scan A 548b3529309b
mcp-development is a skill published in the GitHub repository ohnotnow/devnotes (0 stars, last pushed yesterday), licensed MIT. It adds 180 tokens to every session and 867 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to mcp-development, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…