horse-framework

horse-framework is a skill for Claude Code, Codex from SecondLifes/delphi-expert. It costs 13 tokens per session (1,927 once invoked), scanned A, a copy of Horse Framework, MIT.

A guide to Horse, a Delphi framework for building REST APIs—web services that expose data and actions through HTTP endpoints.

In plain words
What is it for?
Use it to create Horse API projects, add endpoints, build middleware, connect FireDAC databases, and structure Delphi server code.
Why use it?
It provides project patterns for organizing routes, middleware, controllers, database access, authentication, cross-origin requests, and logging.

Skill for Claude CodeCodex

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/secondlifes/delphi-expert/horse-framework
Any agent
npx skills add SecondLifes/delphi-expert --skill horse-framework
Clone the repo
git clone --depth 1 https://github.com/SecondLifes/delphi-expert

Made for: Claude Code, Codex.

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 horse-framework

README.md
[![agentmods](https://agentmods.dev/badge/skills/secondlifes/delphi-expert/horse-framework.svg)](https://agentmods.dev/skills/secondlifes/delphi-expert/horse-framework)
Your own site
<a href="https://agentmods.dev/skills/secondlifes/delphi-expert/horse-framework"><img src="https://agentmods.dev/badge/skills/secondlifes/delphi-expert/horse-framework.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,927 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00013 $0.01927
Opus 5 $0.00006 $0.00963
Sonnet 5 $0.00003 $0.00385
Haiku 4.5 $0.00001 $0.00193

Measured 3d ago against content hash 2e38360bd0da, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

horse-framework 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.

Origin

This is a copy

100% identical to Horse Framework — 2 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.

.agents/skills/horse-framework/SKILL.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Horse Framework — Skill

Use this skill when creating REST APIs with the Horse framework in Delphi.

When to Use

  • When creating a new REST API project
  • When adding routes and endpoints
  • When implementing middleware (JWT, CORS, logging)
  • When integrating Horse with FireDAC

About Horse

Horse is a minimalist and performant REST framework for Delphi, inspired by Express.js (Node.js). It uses the middleware chain concept and is extremely simple to configure.

Project Structure

src/
├── MeuApp.dpr                          ← Projeto principal
├── Controllers/
│   ├── MeuApp.Controller.Customer.pas
│   ├── MeuApp.Controller.Product.pas
│   └── MeuApp.Controller.Health.pas
├── Middleware/
│   ├── MeuApp.Middleware.Auth.pas
│   ├── MeuApp.Middleware.Logger.pas
│   └── MeuApp.Middleware.CORS.pas
├── Domain/
│   ├── MeuApp.Domain.Customer.Entity.pas
│   └── MeuApp.Domain.Customer.Repository.Intf.pas
├── Application/
│   └── MeuApp.Application.Customer.Service.pas
├── Infrastructure/
│   └── MeuApp.Infra.Customer.Repository.pas
└── Config/
    └── MeuApp.Config.Server.pas

Basic Server Configuration

program MeuApp;

{$APPTYPE CONSOLE}

uses
  Horse,
  Horse.Jhonson,       //JSON middleware
  Horse.CORS,          //CORS middleware
  Horse.HandleException,
  MeuApp.Controller.Customer,
  MeuApp.Controller.Health;

begin
  THorse.Use(Jhonson);
  THorse.Use(CORS);
  THorse.Use(HandleException);

  //Register broken
  TCustomerController.RegisterRoutes;
  THealthController.RegisterRoutes;

  THorse.Listen(9000,
    procedure
    begin
      Writeln('Server running on port 9000');
    end
  );
end.

Controller Pattern

unit MeuApp.Controller.Customer;

interface

uses
  Horse,
  System.JSON;

type
  TCustomerController = class
  public
    class procedure RegisterRoutes;
  private
    class procedure GetAll(AReq: THorseRequest; ARes: THorseResponse; ANext: TProc);
    class procedure GetById(AReq: THorseRequest; ARes: THorseResponse; ANext: TProc);
    class procedure Create(AReq: THorseRequest; ARes: THorseResponse; ANext: TProc);
    class procedure Update(AReq: THorseRequest; ARes: THorseResponse; ANext: TProc);
    class procedure Delete(AReq: THorseRequest; ARes: THorseResponse; ANext: TProc);
  end;

implementation

uses
  System.SysUtils,
  MeuApp.Application.Customer.Service.Intf;

class procedure TCustomerController.RegisterRoutes;
begin
  THorse.Get('/api/customers', GetAll);
  THorse.Get('/api/customers/:id', GetById);
  THorse.Post('/api/customers', Create);
  THorse.Put('/api/customers/:id', Update);
  THorse.Delete('/api/customers/:id', Delete);
end;

class procedure TCustomerController.GetAll(
  AReq: THorseRequest; ARes: THorseResponse; ANext: TProc);
var
  LService: ICustomerService;
  LResult: TJSONArray;
begin
  LService := TServiceFactory.CreateCustomerService;
  LResult := LService.GetAllAsJSON;
  ARes.Send<TJSONArray>(LResult).Status(THTTPStatus.OK);
end;

class procedure TCustomerController.GetById(
  AReq: THorseRequest; ARes: THorseResponse; ANext: TProc);
var
  LService: ICustomerService;
  LId: Integer;
  LResult: TJSONObject;
begin
  LId := AReq.Params['id'].ToInteger;
  LService := TServiceFactory.CreateCustomerService;

  LResult := LService.GetByIdAsJSON(LId);
  if not Assigned(LResult) then
  begin
    ARes.Send('Customer not found').Status(THTTPStatus.NotFound);
    Exit;
  end;

  ARes.Send<TJSONObject>(LResult).Status(THTTPStatus.OK);
end;

class procedure TCustomerController.Create(
  AReq: THorseRequest; ARes: THorseResponse; ANext: TProc);
var
  LService: ICustomerService;
  LBody: TJSONObject;
begin
  LBody := AReq.Body<TJSONObject>;
  LService := TServiceFactory.CreateCustomerService;

  try
    LService.CreateFromJSON(LBody);
    ARes.Send('Created').Status(THTTPStatus.Created);
  except
    on E: EValidationException do
      ARes.Send(E.Message).Status(THTTPStatus.BadRequest);
    on E: EBusinessRuleException do
      ARes.Send(E.Message).Status(THTTPStatus.Conflict);
  end;
end;

Read the full file on GitHub · 285 lines

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 · 285 lines · 13 tokens per session scan A 2e38360bd0da

Subscribe to this mod's changes

horse-framework is a skill published in the GitHub repository SecondLifes/delphi-expert (3 stars, last pushed 2d ago), licensed MIT. It adds 13 tokens to every session and 1,927 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to Horse Framework, differing in 2 lines, and is treated as a copy.

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