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 skills add noerd-dev/noerd --skill noerd-module-developmentgit clone --depth 1 https://github.com/noerd-dev/noerdWrote 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.
[](https://agentmods.dev/skills/noerd-dev/noerd/noerd-module-development)<a href="https://agentmods.dev/skills/noerd-dev/noerd/noerd-module-development"><img src="https://agentmods.dev/badge/skills/noerd-dev/noerd/noerd-module-development/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.
<a href="https://agentmods.dev/skills/noerd-dev/noerd/noerd-module-development"><img src="https://agentmods.dev/badge/skills/noerd-dev/noerd/noerd-module-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00148 | $0.02019 |
| Opus 5.5 | $0.00059 | $0.00808 |
| Sonnet 5.5 | $0.00030 | $0.00404 |
| Haiku 4.5 | $0.00015 | $0.00202 |
Grade A, and why
noerd-module-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 1mo 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Noerd Module Development
A module is a Composer package under app-modules/{module}/ (namespace Noerd\{Module} by
convention) that ships a tenant app: YAML configs, Livewire components, model, migrations, routes,
translations, tests and an install/update command. Hard rules: noerd/noerd Boost guideline. Docs:
vendor/noerd/noerd/docs/creating-modules.md, make-app.md, navigation.md,
artisan-commands.md, traits.md, ai-agents.md.
1. Scaffold
php artisan noerd:make-app # choose "Module": asks title, name, heroicon, then registers with Composer and installs (tenant assignment is the only question)
php artisan noerd:make-module # the scaffolder itself: module name, app title, heroicon
# scripted: noerd:make-module inventory --title=Inventory --icon=cube
composer update noerd/{module}
php artisan noerd:install-{module} # copies YAML, registers the tenant app, migrates (--scaffold = the silent make-app run)
php artisan noerd:make-resource Item --app={module} # per record type, after model + migration exist in the module
The scaffold is dashboard + plumbing, no model. noerd:make-resource / make-list / make-detail
/ make-page / make-dashboard detect a module app (app-modules/{app}/composer.json) and write
into it: components under {app}::, routes into routes/{app}-routes.php, YAML + navigation into
both copies.
Never write the tenant_apps row of a module by hand or via the root noerd:make-app flow —
the generated install command registers it (name = UPPERCASE module key, icon = the heroicon from
getAppIcon(), route = the module dashboard). A module ships no icon file; a Blade icon is only
the manual exception when no heroicon fits.
Generated layout (keep it — do not invent new base folders):
app-modules/{module}/
├── app-configs/{module}/ # YAML templates: lists/, details/, pages/, navigation.yml
├── app-configs/stubs/add_{module}_tenant_app.php.stub # tenant-app migration published by the install command
├── database/{migrations,factories,seeders}/
├── resources/boost/guidelines/core.blade.php # module-specific agent rules (Boost)
├── resources/lang/de.json # English key → German
├── resources/views/components/ # {module}-dashboard.blade.php, *-list.blade.php, *-detail.blade.php, *-page.blade.php, *-modal.blade.php (flat)
├── routes/{module}-routes.php
├── src/{Commands,Models,Providers}/
├── tests/ # Pest, incl. tests/Traits
├── AGENTS.md + CLAUDE.md # contributor notes for the module
└── composer.json
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.
- 1mo ago Changed · +7 lines a56fc93bc9a5
- 1mo ago Changed · +1 lines 86e8647b915c
- 1mo ago Changed · +17 lines · +1 tokens per session df495c9d9f83
- 1mo ago First seen · 114 lines · 147 tokens per session scan A 4850c4401313
noerd-module-development is a skill published in the GitHub repository noerd-dev/noerd (17 stars, last pushed 5d ago), licensed MIT. It adds 148 tokens to every session and 2,019 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…