new-app

new-app is a skill for Claude Code, Codex from maludb-ed/htmx-php-builder. It costs 102 tokens per session (2,770 once invoked), scanned A, original, MIT.

A fixed workflow for starting a new web application using HTMX, PHP, and Bootstrap 5.3. It guides the project from data and authentication design to individual features.

In plain words
What is it for?
Use it to plan the database, memory, login system, shared app shell, email flows, command bar, and feature slices.
Why use it?
It gives a new application a defined build order and review points before more code is written.

Skill for Claude CodeCodex

Part of the htmx-php-builder plugin — 9 skills shipped together

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 skills/maludb-ed/htmx-php-builder/new-app
Any agent
npx skills add maludb-ed/htmx-php-builder --skill new-app
Clone the repo
git clone --depth 1 https://github.com/maludb-ed/htmx-php-builder

Made for: Claude Code, Codex.

Or install htmx-php-builder, the plugin that ships this one along with the rest of its 9 skills.

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.

agentmods badge for new-app

README.md
[![agentmods](https://agentmods.dev/badge/skills/maludb-ed/htmx-php-builder/new-app.svg)](https://agentmods.dev/skills/maludb-ed/htmx-php-builder/new-app)
Your own site
<a href="https://agentmods.dev/skills/maludb-ed/htmx-php-builder/new-app"><img src="https://agentmods.dev/badge/skills/maludb-ed/htmx-php-builder/new-app.svg" alt="Measured on agentmods" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,770 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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.

ModelPer sessionOnce invoked
Fable 5 $0.00102 $0.02770
Opus 5 $0.00051 $0.01385
Sonnet 5 $0.00020 $0.00554
Haiku 4.5 $0.00010 $0.00277

Measured 3d ago against content hash c3c461539611, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

new-app 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 3d 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.

skills/new-app/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

New Application Workflow

Build every application in the same fixed order. Do not skip phases, reorder them, or start writing feature screens before Phase 2 is approved by the user. Each phase ends with a user checkpoint.

Before starting, load context from the sibling skills in this plugin:

  • memory-first-planning — memory-first design, ask-me-anything, SaaS Plus+, the two-memory architecture served through MCP. Consult during Phase 0 and 1.
  • mcp-servers — the two MCP servers every app ships (record + activity memory). Consult during Phase 1 (tool-surface design) and Phase 4.
  • design-system — the mandatory UI template and rules. Consult during Phase 2 and every screen thereafter.
  • php-patterns — the mandatory PHP code structure. Consult before writing any PHP.
  • php-session-auth — security rules for the auth build in Phase 2.
  • malumail-send — the default email channel (MaluMail API) for reset/verification emails and notifications. Consult in Phase 2 and wherever a feature sends mail.
  • chat-actions — the voice-first command bar on every screen: LLM router → actions MCP server → the app's own endpoints. Consult in Phase 1 (action manifest), Phase 2 (command bar in the shell), and Phase 4 (assistant service).

The stack (fixed — do not reopen unless the user does)

Layer Choice
OS Ubuntu 24.04
System of record PostgreSQL 17
Activity memory MaluDB (PostgreSQL extensions), fed by application logs
Memory interface Two client-facing read MCP servers per app (Python + FastMCP), per the mcp-servers skill
Action interface One localhost-only actions MCP server per app (navigation + app actions), per the chat-actions skill
Assistant One unified Claude Agent SDK service (Python) — AMA answers, chat actions, navigation
Web server Apache (also reverse-proxies the MCP servers and AMA service)
Application PHP (vanilla, per php-patterns skill)
UI Bootstrap 5.3 per the design-system skill
Interactivity HTMX partial updates

Read the full file on GitHub · 128 lines

Files

What ships with it

2 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.

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.

  1. 3d ago First seen · 128 lines · 102 tokens per session scan A c3c461539611

Subscribe to this mod's changes

new-app is a skill published in the GitHub repository maludb-ed/htmx-php-builder (8 stars, last pushed 28d ago), licensed MIT. It adds 102 tokens to every session and 2,770 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens