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 skills add CrestApps/CrestApps.AgentSkills --skill orchardcore-ai-response-handlersgit clone --depth 1 https://github.com/CrestApps/CrestApps.AgentSkillsWrote 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/crestapps/crestapps.agentskills/orchardcore-ai-response-handlers)<a href="https://agentmods.dev/skills/crestapps/crestapps.agentskills/orchardcore-ai-response-handlers"><img src="https://agentmods.dev/badge/skills/crestapps/crestapps.agentskills/orchardcore-ai-response-handlers/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/crestapps/crestapps.agentskills/orchardcore-ai-response-handlers"><img src="https://agentmods.dev/badge/skills/crestapps/crestapps.agentskills/orchardcore-ai-response-handlers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 58 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00085 | $0.01565 |
| Opus 5 | $0.00043 | $0.00783 |
| Sonnet 5 | $0.00017 | $0.00313 |
| Haiku 4.5 | $0.00009 | $0.00156 |
Grade A, and why
orchardcore-ai-response-handlers 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 8d 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchard Core Chat Response Handlers
Route a chat prompt to a handler
IChatResponseHandler is a shared CrestApps.Core contract used by Orchard chat
sessions and chat interactions. A handler either returns response updates now or
defers the assistant response until an external system supplies it.
using CrestApps.Core.AI.ResponseHandling;
namespace MyCompany.OrchardCore.Chat;
public sealed class LiveAgentResponseHandler : IChatResponseHandler
{
public string Name => "LiveAgent";
public async Task<ChatResponseHandlerResult> HandleAsync(
ChatResponseHandlerContext context,
CancellationToken cancellationToken = default)
{
await SendToAgentSystemAsync(context.Prompt, cancellationToken);
return ChatResponseHandlerResult.Deferred();
}
private static Task SendToAgentSystemAsync(
string prompt,
CancellationToken cancellationToken)
{
return Task.CompletedTask;
}
}
Register a custom handler as an enumerable scoped service:
using CrestApps.Core.AI.ResponseHandling;
using Microsoft.Extensions.DependencyInjection;
services.TryAddEnumerable(
ServiceDescriptor.Scoped<IChatResponseHandler, LiveAgentResponseHandler>());
The active handler is selected from AIChatSession.ResponseHandlerName or
ChatInteraction.ResponseHandlerName. The built-in AI path handles the normal
case. Do not claim a custom handler is selected for a Conversation-mode session
without checking the active chat feature's resolver behavior.
Return streaming or deferred output
Use Deferred() only when the handler has handed work to an external process
that will deliver the reply later. The hub persists the user prompt and does
not wait for an assistant response.
For immediate output, return an async sequence of ChatResponseUpdate values:
using CrestApps.Core.AI.ResponseHandling;
using Microsoft.Extensions.AI;
return ChatResponseHandlerResult.Streaming(StreamUpdatesAsync(cancellationToken));
static async IAsyncEnumerable<ChatResponseUpdate> StreamUpdatesAsync(
[System.Runtime.CompilerServices.EnumeratorCancellation] CancellationToken cancellationToken)
{
yield return new ChatResponseUpdate(ChatRole.Assistant, "Connecting you to an agent.");
await Task.CompletedTask;
}
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.
- 8d ago First seen · 220 lines · 85 tokens per session scan A 19f732aba157
orchardcore-ai-response-handlers is a skill published in the GitHub repository CrestApps/CrestApps.AgentSkills (13 stars, last pushed 13d ago), licensed MIT. It adds 85 tokens to every session and 1,565 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
powerpoint-cli
PowerPoint CLI automation skill for Windows presentations. Use when a coding agent needs token-efficient, scriptable, or unattended PowerPoint automation via pptcli commands. Best for CI/CD, scheduled jobs, batch processing, PowerShell workflows, and bulk deck edits. Supports slides, shapes, text frames, tables…
powerpoint-mcp
PowerPoint MCP Server skill for Windows presentation automation via a live PowerPoint desktop instance (COM/PIA). Use when an assistant needs rich MCP tools to create, open, build, format, and export PowerPoint (.pptx/.pptm) presentations — slides, shapes, text boxes, tables, native charts, images, audio, video…
publish-release
Releases a new McpOrchestrator version end to end — version bump PR, tag, and the automated deploy to GitHub Releases, NuGet, and the MCP Registry. Use when asked to release, publish, deploy, ship, or bump the version of McpOrchestrator.
dotnet-debugging
Debug .NET applications using debug-mcp MCP tools — launch processes, set breakpoints, step through code, inspect variables, evaluate expressions, and analyze exceptions. Use this skill when debugging .NET/C# applications, investigating runtime behavior, diagnosing exceptions, inspecting object state, or performing…
release-notes
Writes user-facing release notes from a git commit range. Use when asked to draft release notes, a changelog entry, or "what's new" text for a release.
sast-fileupload
Detect insecure file upload vulnerabilities in a codebase using a three-phase approach: discovery (find all upload sites), batched verify (check extension bypass and related issues in parallel subagents, 3 sites each), and merge (consolidate batch results). Requires sast/architecture.md (run sast-analysis first).…