Horse is a lightweight web framework for Delphi and Lazarus programs, providing tools for building HTTP servers and APIs. It is for developers who need routing, request handling, middleware, streaming, WebSockets, and related server features in those languages. Its catalogue skills support working with the framework.
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/hashload/horse/horse-security-authnpx skills add HashLoad/horse --skill horse-security-authgit clone --depth 1 https://github.com/HashLoad/horseWrote 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/hashload/horse/horse-security-auth)<a href="https://agentmods.dev/skills/hashload/horse/horse-security-auth"><img src="https://agentmods.dev/badge/skills/hashload/horse/horse-security-auth.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00024 | $0.00672 |
| Opus 5 | $0.00012 | $0.00336 |
| Sonnet 5 | $0.00005 | $0.00134 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
horse-security-auth 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 5d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Horse Security & Authentication
1. Organizing Public and Protected Routes
Always separate public endpoints (e.g., authentication, login, system health) from protected ones. Use THorse.Group to configure middleware layers specifically for protected routes without affecting public endpoints:
begin
// Global Middlewares (CORS, Johnson, etc.)
THorse.Use(CORS).Use(Jhonson);
// 1. Public Routes
THorse.Post('/login', DoLoginHandler);
THorse.Get('/health', GetHealthHandler);
// 2. Protected Routes (Using a Group with JWT Middleware)
THorse.Group.Prefix('/api/v1')
.Use(HorseJWT('my_secret_key')) // Authenticates all routes within this group
.Get('/customers', GetCustomersHandler)
.Get('/orders', GetOrdersHandler);
THorse.Listen(9000);
end;
2. Setting Up JWT (JSON Web Token) Authentication
The official JWT middleware is horse-jwt.
Acquiring Token Payload in Handlers
Once HorseJWT authenticates the request, it decodes the payload and stores it in the Session property of THorseRequest. You can retrieve claims using the Session dictionary:
procedure GetProfileHandler(Req: THorseRequest; Res: THorseResponse; Next: TProc);
var
LClaims: TJWTClaims; // Or TJSONObject depending on the horse-jwt version used
LUserId: string;
begin
// Example of pulling JWT claims
LUserId := Req.Session<TJSONObject>.GetValue<string>('sub');
Res.Send(Format('Hello, User %s!', [LUserId]));
end;
3. Setting Up Basic Authentication
For quick, credential-based authentication, use the official horse-basic-auth middleware:
uses Horse.BasicAuth;
begin
// Protect all API routes with Basic-Auth
THorse.Group.Prefix('/api')
.Use(HorseBasicAuth(
function(AUsername, APassword: string): Boolean
begin
// Replace with secure database/credential lookup
Result := (AUsername = 'admin') and (APassword = 'secret123');
end
))
.Get('/secrets', GetSecretsHandler);
end;
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.
- 5d ago First seen · 79 lines · 24 tokens per session scan A bcb2b8fd4dec
horse-security-auth is a skill published in the GitHub repository HashLoad/horse (1,371 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 672 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
api-design-patterns
Comprehensive API design patterns covering REST, GraphQL, gRPC, versioning, authentication, and modern API best practices.
api-design-patterns
Comprehensive API design patterns covering REST, GraphQL, gRPC, versioning, authentication, and modern API best practices.
api-design-patterns
Comprehensive API design patterns covering REST, GraphQL, gRPC, versioning, authentication, and modern API best practices.
recon-playbook
Use when starting or restructuring an authorized external web and API assessment.
hunt-wordpress
Use when an authorized target exposes WordPress core, plugin, theme, REST, or XML-RPC behavior.
create-tutorial
Scaffold a new Membrane API Gateway tutorial in the api-gateway repo — the numbered self-teaching YAML under distribution/tutorials/ /, its support files and README links, and the matching auto-discovered integration test. Use whenever the user asks to create, add, write, or scaffold a tutorial (or a tutorial step)…