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 escapeboy/ai-prompts --skill module-assistantgit clone --depth 1 https://github.com/escapeboy/ai-promptsWrote 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/escapeboy/ai-prompts/module-assistant)<a href="https://agentmods.dev/skills/escapeboy/ai-prompts/module-assistant"><img src="https://agentmods.dev/badge/skills/escapeboy/ai-prompts/module-assistant/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/escapeboy/ai-prompts/module-assistant"><img src="https://agentmods.dev/badge/skills/escapeboy/ai-prompts/module-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 596 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 5 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00024 | $0.05949 |
| Opus 5.5 | $0.00010 | $0.02380 |
| Sonnet 5.5 | $0.00005 | $0.01190 |
| Haiku 4.5 | $0.00002 | $0.00595 |
Grade A, and why
module:assistant 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 — 762 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Module: AI Assistant
Implement an AI-powered assistant chat panel embedded in your Laravel application. The assistant understands your domain, can execute tools to read/write data, and supports multiple LLM providers including local agents.
Reference implementation: Agent Fleet — Livewire panel with streaming, PrismPHP tool calling, local agent support (Claude Code text-based <tool_call> loop, Codex via MCP), conversation history, context awareness.
Usage
/module:assistant [action]
Quick Examples
/module:assistant # Full implementation
/module:assistant analyze # Only analyze and produce a component plan
/module:assistant tools # Only generate the tool registry (add to existing assistant)
Actions
1. Full Implementation (Default)
Implements the complete assistant: database, backend, tools, frontend.
Process:
Phase 1: Analyze the Project
-
Read CLAUDE.md to understand the domain, models, and architecture.
-
Check prerequisites:
- Livewire 3+ installed? (
composer show livewire/livewire) - PrismPHP installed? (
composer show prism-php/prism) - Alpine.js available? (comes with Livewire)
- Tailwind CSS configured?
- Livewire 3+ installed? (
-
If MCP is already set up (from
/module:mcp): the assistant can reference MCP tools for local agents that support MCP natively (e.g. Codex). -
Identify domain tools — the assistant needs tools to interact with your data. Scan models and actions to plan what tools to create (same analysis as
/module:mcp analyze). -
Decide the tool strategy:
- Cloud LLMs (Anthropic, OpenAI): Use PrismPHP Tool objects — native function calling.
- Claude Code (local): Use text-based
<tool_call>format — system prompt describes tool schemas, responses parsed for<tool_call>tags. - Codex (local): Use MCP natively — connect to your MCP server (requires
/module:mcpfirst).
Phase 2: Database
Create the migration for assistant conversations and messages.
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 First seen · 762 lines · 24 tokens per session scan A d8e564878337
module:assistant is a skill published in the GitHub repository escapeboy/ai-prompts (91 stars, last pushed 15d ago), licensed MIT. It adds 24 tokens to every session and 5,949 once invoked, about $0.0001 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
create-powergrid-plugin
Create a complete PowerGrid plugin from scratch, including PHP class, Column macro, Blade view, Alpine.js component, and registration.
laravel-upgrade
Upgrade a Laravel application across major versions safely (Laravel 8 -> 9 -> 10 -> 11 -> 12 -> 13), one hop at a time. Use when upgrading Laravel, when a composer update fails after a major bump, when deciding whether to hop versions by hand or pay for Laravel Shift, or when something compiled fine but broke at…
filament-plugin-development
Build and publish custom Filament plugins (Filament is the Laravel admin-panel framework). Use when creating a Filament plugin/package, implementing the Plugin contract, scaffolding from the plugin skeleton, registering assets/resources/pages/render-hooks, making a configurable plugin, testing it, or publishing to…
laravel-architecture-review
Review a Laravel codebase's architecture and design, not just its types. Use when asked to audit a Laravel app, find architectural smells, decide where business logic belongs (controller vs Action vs Service), whether a Repository/DDD/TDD layer is justified, or how to apply SOLID/DRY to a Laravel project. Runs the…
powergrid-theme
Create or update a PowerGrid v7 theme using the Theme abstract class, per-section token methods (layout/header/table/footer/cols/tabs plus filter/editable/toggleable), config themeoverrides, or ArrayTheme.
upgrade-theme-v6-to-v7
Migrates a v6 Theme class to the v7 architecture: a tiny struct() plus per-section token methods (layout/header/table/footer/cols/tabs + filter/editable/toggleable) with parentTheme inheritance.