Manage Settings
asgeirtj/system_prompts_leaks
Any explicit Muse Code setting question or change (model, reasoning effort, /settings) requires a silent readskill call for bundled:manage-settings as FIRST ACTION—no assistant text or other tool…
Guide for setting up Horse applications, bootstrap program (.dpr), basic console initialization, and registering modules.
$ npx skills add HashLoad/horse --skill horse-app-structure -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install HashLoad/horse horse-app-structure --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/HashLoad/horse.git skills-src && mkdir -p .claude/skills && cp -r skills-src/doc/skills/horse-app-structure .claude/skills/horse-app-structure && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "horse-app-structure" agent skill from https://github.com/HashLoad/horse/tree/master/doc/skills/horse-app-structure into .claude/skills/horse-app-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "horse-app-structure", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/HashLoad/horse/tree/master/doc/skills/horse-app-structureType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add HashLoad/horse --skill horse-app-structure -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install HashLoad/horse horse-app-structure --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HashLoad/horse.git skills-src && mkdir -p .agents/skills && cp -r skills-src/doc/skills/horse-app-structure .agents/skills/horse-app-structure && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "horse-app-structure" agent skill from https://github.com/HashLoad/horse/tree/master/doc/skills/horse-app-structure into .agents/skills/horse-app-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "horse-app-structure", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add HashLoad/horse --skill horse-app-structure -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install HashLoad/horse horse-app-structure --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HashLoad/horse.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/doc/skills/horse-app-structure .cursor/skills/horse-app-structure && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "horse-app-structure" agent skill from https://github.com/HashLoad/horse/tree/master/doc/skills/horse-app-structure into .cursor/skills/horse-app-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "horse-app-structure", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/HashLoad/horse.git --path doc/skills/horse-app-structure--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add HashLoad/horse --skill horse-app-structure -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install HashLoad/horse horse-app-structure --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HashLoad/horse.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/doc/skills/horse-app-structure .gemini/skills/horse-app-structure && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "horse-app-structure" agent skill from https://github.com/HashLoad/horse/tree/master/doc/skills/horse-app-structure into .gemini/skills/horse-app-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "horse-app-structure", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install HashLoad/horse horse-app-structureInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add HashLoad/horse --skill horse-app-structure -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/HashLoad/horse.git skills-src && mkdir -p .github/skills && cp -r skills-src/doc/skills/horse-app-structure .github/skills/horse-app-structure && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "horse-app-structure" agent skill from https://github.com/HashLoad/horse/tree/master/doc/skills/horse-app-structure into .github/skills/horse-app-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "horse-app-structure", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add HashLoad/horse --skill horse-app-structure -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install HashLoad/horse horse-app-structure --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HashLoad/horse.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/doc/skills/horse-app-structure .opencode/skills/horse-app-structure && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "horse-app-structure" agent skill from https://github.com/HashLoad/horse/tree/master/doc/skills/horse-app-structure into .opencode/skills/horse-app-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "horse-app-structure", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
horse-app-structureGuide for setting up Horse applications, bootstrap program (.dpr), basic console initialization, and registering modules.
Horse App Structure is an agent skill from HashLoad/horse. Guide for setting up Horse applications, bootstrap program (.dpr), basic console initialization, and registering modules.
Its SKILL.md is about 720 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Fast, opinionated, minimalist web framework for Delphi. The licence is MIT.
2 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit d4351a5. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are pascal).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Horse App Structure loads about 716 tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 167 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from HashLoad/horse at commit d4351a5, republished under its MIT licence (© HashLoad). 167 words, ~716 tokens.
.claude/skills/horse-app-structure/SKILL.md (or your agent's skills folder).A standard Horse application is typically configured as a Delphi Console Application ({$APPTYPE CONSOLE}).
program MyHorseApp;
{$APPTYPE CONSOLE}
uses
System.SysUtils,
Horse,
Horse.Jhonson,
Horse.CORS;
begin
// 1. Opt-in for the High-Performance Radix Tree Router (highly recommended)
THorse.UseRadixRouter;
// 2. Register Global Middlewares
THorse
.Use(CORS)
.Use(Jhonson);
// 3. Register Routes / Controllers
THorse.Get('/ping',
procedure(Req: THorseRequest; Res: THorseResponse; Next: TProc)
begin
Res.Send('pong');
end);
// 4. Start Server with Listen Callback (prevents sequential execution blocking)
THorse.Listen(9000,
procedure
begin
Writeln('Server is running on port ' + THorse.Port.ToString);
end);
end.For production grade projects, keep the .dpr file clean by delegating route definitions to specialized Controller classes:
Horse units).Horse is inherently multithreaded (each request runs on a separate worker thread). Accessing a database inside a route handler requires strict thread safety to avoid memory corruption, race conditions, or application crashes (Access Violations):
TFDConnection or query component in your Controller or DataModule and share it across handlers.try...finally block (Delphi XE7+ compatible):procedure GetCustomerHandler(Req: THorseRequest; Res: THorseResponse; Next: TProc);
var
LConnection: TFDConnection;
LQuery: TFDQuery;
begin
LConnection := TFDConnection.Create(nil);
LQuery := TFDQuery.Create(nil);
try
// Configure connection locally (preferably utilizing FireDAC Connection Pooling)
LConnection.ConnectionDefName := 'MyPooledConnectionDef';
LConnection.Connected := True;
LQuery.Connection := LConnection;
LQuery.SQL.Text := 'SELECT * FROM CUSTOMERS WHERE ID = :ID';
LQuery.ParamByName('ID').AsInteger := Req.Params.Field('id').AsInteger;
LQuery.Open;
Res.Send(LQuery.ToJSONArray);
finally
LQuery.Free;
LConnection.Free;
end;
end;© HashLoad, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in doc/skills/horse-app-structure of HashLoad/horse.
Open the folder on GitHubat commit d4351a5
Horse App Structure next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Horse App Structure this skillHashLoad/horse | 1.4k | — | ~716 | Automated safety check: Pass | MIT | |
| Manage Settingsasgeirtj/system_prompts_leaks | 69k | — | ~3.1k | Automated safety check: Pass | CC0-1.0 | |
| Tabler Bootstrap Component Rulestabler/tabler | 42k | — | ~2.2k | Automated safety check: Pass | MIT | |
| Bootstrap Soulbytedance/deer-flow | 83k | 2 repos | ~1.2k | Automated safety check: Pass | MIT | |
| Warp Settings Editorwarpdotdev/warp | 65k | 1 repos | ~675 | Automated safety check: Pass | AGPL-3.0 | |
| Warp Settings Page Builderwarpdotdev/warp | 65k | 1 repos | ~4.5k | Automated safety check: Pass | AGPL-3.0 |
asgeirtj/system_prompts_leaks
Any explicit Muse Code setting question or change (model, reasoning effort, /settings) requires a silent readskill call for bundled:manage-settings as FIRST ACTION—no assistant text or other tool…
tabler/tabler
Sets the file structure, typing and Data API pattern for writing a new Bootstrap-style JavaScript component class in Tabler's vendored port of Bootstrap's JS.
bytedance/deer-flow
Runs a short adaptive conversation with you and writes a personalized SOUL.md that defines your AI partner's name, personality, communication style and boundaries.
warpdotdev/warp
Finds and changes Warp application settings by searching a bundled JSON schema and editing the matching TOML settings file at the right nesting depth.
warpdotdev/warp
How to build a settings page in the Warp desktop client so widgets, page titles and settings search behave correctly, and which common mistakes to avoid.
lobehub/lobehub
Adds a server-side environment variable that sets the default for a user setting in LobeHub, wired from the env schema through server config to the user store and docs.
HashLoad/horse
Guide for setting up thread-safe database connection pooling (FireDAC / UniDAC) in multithreaded Horse applications.
HashLoad/horse
Guide for managing request-scoped contextual services and IoC (dependency injection) in Delphi and Lazarus.
HashLoad/horse
Guide to handling file uploads (multipart), downloads, and stream lifetime management in the Horse framework.
HashLoad/horse
Guidelines and workflows for developing and maintaining gRPC services, HTTP/2 h2c transport, and Protobuf serialization within the Horse framework.
HashLoad/horse
Guide for writing automated integration tests for Horse endpoints using DUnit/DUnitX and THTTPClient.
HashLoad/horse
Guide for ensuring Lazarus and Free Pascal (FPC) compatibility, addressing anonymous methods differences, JSON units, and compiler directives.
Guide for setting up Horse applications, bootstrap program (.dpr), basic console initialization, and registering modules. Horse App Structure is an agent skill from HashLoad/horse.dpr), basic console initialization, and registering modules.
Run `npx skills add HashLoad/horse --skill horse-app-structure -a claude-code`. Or copy the skill folder (doc/skills/horse-app-structure in HashLoad/horse) into .claude/skills/horse-app-structure in your project. Claude Code loads it when a task matches its description.
Run `npx skills add HashLoad/horse --skill horse-app-structure -a codex`. Or copy the skill folder (doc/skills/horse-app-structure in HashLoad/horse) into .agents/skills/horse-app-structure in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HashLoad/horse --skill horse-app-structure -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/horse-app-structure, .gemini/skills/horse-app-structure, .github/skills/horse-app-structure and .opencode/skills/horse-app-structure in your project.
SKILL.md names no scripts, command-line tools or credentials: Horse App Structure is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Horse App Structure is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 716 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Horse App Structure: Manage Settings (asgeirtj/system_prompts_leaks, 69k stars), Tabler Bootstrap Component Rules (tabler/tabler, 42k stars), Bootstrap Soul (bytedance/deer-flow, 83k stars) and Warp Settings Editor (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
HashLoad (a GitHub organization) maintains it in HashLoad/horse, which has 1,377 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on October 7, 2026.
Source: HashLoad/horse on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.