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-multi-instancenpx skills add HashLoad/horse --skill horse-multi-instancegit clone --depth 1 https://github.com/HashLoad/horseWhat 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 | $0.00028 | $0.00583 |
| Opus 5 | $0.00014 | $0.00292 |
| Sonnet 5 | $0.00006 | $0.00117 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
horse-multi-instance 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 2d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Horse Multi-Instance
Decoupled Server Contexts
Use THorseInstance when your application needs to expose multiple separate HTTP interfaces (e.g., a public REST API on port 8080 and an admin/telemetry dashboard on port 9090) within the same process.
Each THorseInstance allocates its own isolated:
- Routing tables
- Middleware pipelines
- Active requests telemetry counters
- Lifecycle hooks (
onRequest,preParsing,preValidation,onSend,onResponse)
Declaring and Configuring Instances
Always create and configure THorseInstance explicitly, registering endpoints and middlewares directly on the instance:
var
FPublicApi: THorseInstance;
FAdminPanel: THorseInstance;
begin
// 1. Public API configuration
FPublicApi := THorseInstance.Create;
FPublicApi.Use(Jhonson); // Middleware registered only for FPublicApi
FPublicApi.Get('/api/v1/ping', DoPingHandler);
// 2. Admin Panel configuration
FAdminPanel := THorseInstance.Create;
FAdminPanel.Get('/admin/metrics', DoMetricsHandler);
end;
Starting Listeners Concurrently
Since listeners enter blocking execution loops (depending on the provider and application shape), you must start the physical socket listening in separate threads:
// Start Instance 1 in a background thread
TThread.CreateAnonymousThread(
procedure
begin
FPublicApi.Listen(9001);
end).Start;
// Start Instance 2 in a background thread
TThread.CreateAnonymousThread(
procedure
begin
FAdminPanel.Listen(9002);
end).Start;
Stopping Servers and Freeing Resources
When shutting down, stop listening on each instance before freeing the objects:
FPublicApi.StopListen;
FAdminPanel.StopListen;
FPublicApi.Free;
FAdminPanel.Free;
Design Safeguards & AI Best Practices
- Never write static vars inside local middlewares: Ensure any middleware used inside a
THorseInstancerelies on instance-specific configuration or request-scoped services (Req.Services). - Backward Compatibility: If the project does not require multiple instances, continue using the static
THorsefacade class. It is automatically routed to a default instance under the hood. - FPC/Lazarus Compatibility: When writing samples or libraries for Lazarus, avoid Delphi anonymous procedures inline (
procedure begin end) for route handlers. Use standard global procedures instead.
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.
- 2d ago First seen · 78 lines · 28 tokens per session scan A 4a9942cf28d5
horse-multi-instance is a skill published in the GitHub repository HashLoad/horse (1,371 stars, last pushed 4d ago), licensed MIT. It adds 28 tokens to every session and 583 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.
recon-playbook
Use when starting or restructuring an authorized external web and API assessment.
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)…
optimize-interceptor-docs
Rewrite the reference documentation of a Membrane config element so the page generated at membrane-api.io comes out clean, exact, and reference-style. Use whenever the user wants to write, improve, optimize, polish, or review the docs / Javadoc / @description / @yaml example of an interceptor, plugin, or any…
review-branch
Review the current git branch against master — code quality, refactoring opportunities, regressions, correctness, and test coverage — and print a severity-grouped markdown report. Use whenever the user asks to review the branch, review their changes against master, do a pre-PR / pre-merge review, or asks "is this…
membrane-config
Generate a Membrane API Gateway configuration example or snippet — an apis.yaml (default) or, when explicitly asked, a legacy proxies.xml. Use this whenever the user wants a config, example, or snippet for Membrane: routing a port to a backend, a flow with plugins (setHeader, rateLimiter, basicAuthentication, openapi…