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.
git clone --depth 1 https://github.com/gabrielmoreira/agent-skills-mirrorWrote 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/commands/gabrielmoreira/agent-skills-mirror/client-command-hook-template.cs)<a href="https://agentmods.dev/commands/gabrielmoreira/agent-skills-mirror/client-command-hook-template.cs"><img src="https://agentmods.dev/badge/commands/gabrielmoreira/agent-skills-mirror/client-command-hook-template.cs.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 5.1 | $0.00000 | $0.00891 |
| Opus 5 | $0.00000 | $0.00445 |
| Sonnet 5 | $0.00000 | $0.00178 |
| Haiku 4.5 | $0.00000 | $0.00089 |
Grade A, and why
client-command-hook-template.cs 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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- client-command-hook-template.cs — 100% identical, 99 lines differ
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SwiftlyS2 ClientCommandHookHandler Template
Official docs sections:
CommandsNative Functions and Hooks
Suitable for: intercepting raw commands sent by clients (such as jointeam or radio commands) and deciding whether to allow or block them before they enter the normal processing pipeline.
Suitable scenarios
- Intercept and restrict
jointeam(for example, prevent non-admins from switching to spectator) - Intercept and replace radio commands (for example, custom
cheer,roger, and similar behavior) - Intercept purchase commands
- Any scenario that requires global interception at the command layer
Basic pattern
using SwiftlyS2.Shared.Hooks;
namespace MyNamespace;
public partial class MyPlugin
{
// 1. Optional: declaratively register the command (to ensure low-level recognition)
[Command("jointeam", registerRaw: true)]
public void OnJoinTeamCommand(ICommandContext context) { }
// 2. Install the global command-interception hook
[ClientCommandHookHandler]
public HookResult OnClientCommandHook(int playerId, string commandLine)
{
// Fast routing: only handle the commands you care about
if (!commandLine.StartsWith("jointeam"))
return HookResult.Continue;
var player = Core.PlayerManager.GetPlayer(playerId);
if (player is null || !player.IsValid)
return HookResult.Continue;
// Example: prevent non-admins from switching to spectator
if (commandLine.StartsWith("jointeam 1")
&& !Core.Permission.PlayerHasPermission(player.SteamID, "admin.spectate"))
{
player.SendMessage(MessageType.Chat, "[Plugin] Non-admins cannot switch to spectator.");
return HookResult.Stop; // Block the command
}
return HookResult.Continue; // Allow it through
}
}
Multi-command interception pattern
private static readonly HashSet<string> InterceptedCommands =
["roger", "negative", "cheer", "thanks", "holdpos", "followme"];
[Command("roger", registerRaw: true)]
[CommandAlias("negative", registerRaw: true)]
[CommandAlias("cheer", registerRaw: true)]
[CommandAlias("thanks", registerRaw: true)]
[CommandAlias("holdpos", registerRaw: true)]
[CommandAlias("followme", registerRaw: true)]
public void OnRadioCommand(ICommandContext context) { }
[ClientCommandHookHandler]
public HookResult OnClientCommandHook(int playerId, string commandLine)
{
// Extract the command name
var spaceIndex = commandLine.IndexOf(' ');
var commandName = spaceIndex < 0 ? commandLine : commandLine[..spaceIndex];
if (!InterceptedCommands.Contains(commandName))
return HookResult.Continue;
var player = Core.PlayerManager.GetPlayer(playerId);
if (player is null || !player.IsValid)
return HookResult.Continue;
// Dispatch by command name
return commandName switch
{
"cheer" => HandleCheerCommand(player),
_ => HookResult.Continue
};
}
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.
- 4d ago First seen · 107 lines · 0 tokens per session scan A 716a849c4c8d
client-command-hook-template.cs is a command published in the GitHub repository gabrielmoreira/agent-skills-mirror (17 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 891 tokens. 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 2026-09-03.
Other commands, from other repositories
gamedev-unity
You are an expert Unity game developer with deep knowledge of C#, the Unity Engine, and game design patterns. You write production-grade, performant, and maintainable Unity code.
new-script
You are a Unity C# scripting expert. Generate a new Unity script using best practices and appropriate templates.
scripts
Commands for creating C# script files, attaching MonoBehaviours to GameObjects, and reading/writing serialized fields. Writing a .cs file does not make its type available — Unity must import and compile it (a domain reload) first. The flow is: createscript → recompile → poll recompilestatus (until completed/uptodate)…
engineer
Engineer — Unity C# code: gameplay systems, 2D mechanics, infrastructure.
client-command-hook-template.cs
A C# template for a SwiftlyS2 client-command hook, which intercepts commands sent by game clients before normal processing.
compile
Compile Unity C# assembly with intelligent name matching and auto-fix errors.