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/crestapps/crestapps.agentskills/crestapps-core-ai-runtimenpx skills add CrestApps/CrestApps.AgentSkills --skill crestapps-core-ai-runtimegit 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/crestapps-core-ai-runtime)<a href="https://agentmods.dev/skills/crestapps/crestapps.agentskills/crestapps-core-ai-runtime"><img src="https://agentmods.dev/badge/skills/crestapps/crestapps.agentskills/crestapps-core-ai-runtime.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 | $0.00031 | $0.00600 |
| Opus 5 | $0.00015 | $0.00300 |
| Sonnet 5 | $0.00006 | $0.00120 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
crestapps-core-ai-runtime 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 6d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CrestApps.Core AI Runtime - Prompt Templates
Configure the AI Runtime
You are a CrestApps.Core expert. Generate code and configuration for the provider-agnostic AI runtime in CrestApps.Core.
Guidelines
- Use
AddCoreAIServices()only when the host needs the raw service registrations. - Prefer
AddCrestAppsCore(...).AddAISuite(...)for application composition. - Program against
IAIClientFactory,IAICompletionService, andIAICompletionContextBuilder. - Treat connections as provider credentials and endpoints.
- Treat deployments as named model selections.
- Resolve deployments through the runtime instead of hardcoding model calls in business logic.
Raw Service Registration
builder.Services
.AddCoreAIServices()
.AddCoreAIOrchestration()
.AddCoreAIOpenAI();
Builder-Based Registration
builder.Services.AddCrestAppsCore(crestApps => crestApps
.AddAISuite(ai => ai
.AddOpenAI()
)
);
Key Runtime Services
| Service | Use |
|---|---|
IAIClientFactory |
Create typed chat, embedding, image, speech, and other provider clients |
IAICompletionService |
Send deployment-aware completions without the full orchestration loop |
IAICompletionContextBuilder |
Build enriched AI completion contexts through handlers |
IAIDeploymentStore |
Read named deployments from config and store sources |
IAIProviderConnectionStore |
Read provider connections from config and store sources |
Example Completion Service
using CrestApps.Core.AI.Completions;
using CrestApps.Core.AI.Deployments;
using CrestApps.Core.AI.Models;
using Microsoft.Extensions.AI;
public sealed class QuestionService(
IAICompletionService completionService,
IAICompletionContextBuilder completionContextBuilder,
IAIDeploymentManager deploymentManager)
{
public async Task<string> AskAsync(
string question,
CancellationToken cancellationToken = default)
{
var deployment = await deploymentManager.ResolveOrDefaultAsync(
AIDeploymentPurpose.Chat,
cancellationToken: cancellationToken)
?? throw new InvalidOperationException("No chat deployment is configured.");
var completionContext = await completionContextBuilder.BuildAsync(
deployment,
cancellationToken: cancellationToken);
var messages = new List<ChatMessage>
{
new(ChatRole.System, "You are a helpful assistant."),
new(ChatRole.User, question),
};
var response = await completionService.CompleteAsync(
deployment,
messages,
completionContext,
cancellationToken);
return response.Text;
}
}
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.
- 6d ago First seen · 92 lines · 31 tokens per session scan A bdafe10656eb
crestapps-core-ai-runtime is a skill published in the GitHub repository CrestApps/CrestApps.AgentSkills (13 stars, last pushed 8d ago), licensed MIT. It adds 31 tokens to every session and 600 once invoked, about $0.0002 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
debug-evals
Debug haiku.rag evaluation runs in Logfire. Use when asked to look at Logfire for an eval run, find failing or low-scoring eval cases, compare runs, check citation quality (citedmap) or judge pass rate (answerequivalent), or explain why an eval case failed. Drives the Logfire MCP against the evals service, or the…
microsoft-extensions-ai
Build provider-agnostic .NET AI integrations with Microsoft.Extensions.AI, IChatClient, embeddings, middleware, structured output, vector search, and evaluation. USE FOR: building or reviewing .NET code that uses Microsoft.Extensions.AI, Microsoft.Extensions.AI.Abstractions, IChatClient, IEmbeddingGenerator…
blockrun
Pay-per-call access to AI models, real-time data, media generation and multi-chain RPC over x402 micropayments (USDC on Base or Solana). No API keys, no accounts, no subscriptions. Start here when you have the BlockRun MCP installed and need to know WHICH tool answers a question, how the wallet works, or how to make a…
solr-semantic-search
To build Solr phrase-tagging semantic search: concept tagging, taxonomy, graph paths.
td-api-reference
MUST READ before writing TD Python via executepython, setdatcontent, or editdatcontent, and before any heavy build. Parameters, storage, operators, referencing, threading, cook model, heavy-build safety caps.
maui-essentials-ai
Adopt Microsoft.Maui.Essentials.AI for local/on-device MAUI AI. USE FOR: Apple Intelligence chat, IChatClient, iOS/macOS/Mac Catalyst 26+ checks, fallback UI, NLEmbeddingGenerator, local tool invocation, privacy/offline UX. DO NOT USE FOR: source-generated tools, cloud-only AI, UI debugging.