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 crestapps-core-orchestrationgit 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-orchestration)<a href="https://agentmods.dev/skills/crestapps/crestapps.agentskills/crestapps-core-orchestration"><img src="https://agentmods.dev/badge/skills/crestapps/crestapps.agentskills/crestapps-core-orchestration.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.00494 |
| Opus 5 | $0.00016 | $0.00247 |
| Sonnet 5 | $0.00006 | $0.00099 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
crestapps-core-orchestration 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 7d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CrestApps.Core Orchestration - Prompt Templates
Configure the Default Orchestrator
You are a CrestApps.Core expert. Generate code and guidance for the default orchestration pipeline in CrestApps.Core.
Guidelines
- Use the default orchestrator when the host needs tool calling, retrieval, streaming, and response routing in one pipeline.
- Register orchestration through
AddAISuite(...)orAddCoreAIOrchestration(). - Inject
IOrchestratorResolverand callResolve(name)to obtain the configured orchestrator. Resolution falls back to the configured default when the name is empty or unknown. - Let the orchestrator handle threshold-based tool scoping instead of manually injecting very large tool sets.
Raw Registration
builder.Services
.AddCoreAIServices()
.AddCoreAIOrchestration()
.AddCoreAIOpenAI();
Streaming Example
public sealed class ChatService(IOrchestrator orchestrator)
{
public async IAsyncEnumerable<string> StreamAsync(OrchestrationContext context)
{
await foreach (var update in orchestrator.ExecuteStreamingAsync(context))
{
if (!string.IsNullOrEmpty(update.Text))
{
yield return update.Text;
}
}
}
}
Important Services
| Service | Purpose |
|---|---|
IOrchestrator |
Main agentic execution loop |
IOrchestratorResolver |
Resolve a named orchestrator with fallback to the configured default |
IToolRegistry |
Merge tools from all providers |
IAIToolsService |
Resolve a registered keyed AITool by name |
IOrchestrationContextBuilder |
Build orchestration context through handlers |
Default Scoping Guidance
- At or below
ScopingThreshold, all configured tools are passed through. - Above that threshold, non-MCP catalogs at or below
PlanningThresholduse relevance scoring without an LLM planning call. - MCP tools or a count above
PlanningThresholdtrigger an LLM planning phase followed by relevance scoring. - If planning fails, the orchestrator still scopes by the user message and recent conversation context.
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.
- 7d ago First seen · 62 lines · 32 tokens per session scan A c9400ddb0594
crestapps-core-orchestration is a skill published in the GitHub repository CrestApps/CrestApps.AgentSkills (13 stars, last pushed 9d ago), licensed MIT. It adds 32 tokens to every session and 494 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
mongodb-mcp-v3-migration
Migrates external consumer code from the mongodb-mcp-server v1/v2 single-package API to the v3 scoped-package structure. In v3, mongodb-mcp-server is a binary-only package (npx / MCPB); library embedding uses @mongodb-js/mcp-cli, @mongodb-js/mcp-core, @mongodb-js/mcp-http-runners, @mongodb-js/mcp-tools-, and the other…
gdal-api
Use when programming against GDAL/OGR in C, C++, Python, or .NET for raster/vector I/O, coordinate transformation, or custom geospatial algorithms. GDAL API: low-level programming interface for reading/writing 70+ geospatial formats.
data-engineering
Transforms, validates, loads data in ETL pipelines. Use when building scrapers, validating NDJSON feeds, or importing data into CMS/DB targets.
aws-generative-ai-developer
Build Amazon Bedrock and serverless generative AI applications using Lambda, API Gateway, Step Functions, EventBridge, S3, DynamoDB, SQS, Guardrails, and IAM. Prefer this for serverless GenAI app design and implementation; prefer aws-agentcore for AgentCore runtime, aws-bedrock-agent-security-governor for deep Bedrock…
flowllm-dev
FlowLLM repository development guidance. Use when working in the flowllm codebase to implement, debug, test, review, or document FlowLLM runtime behavior, including CLI/client calls, services, application wiring, jobs, steps, components, configuration, streaming, registry registration, and tests.
scalix-ai
Run AI inference on Scalix Cloud through the OpenAI-compatible API — chat completions, streaming, and the Scalix Lumio model family. Use when the user wants LLM inference on Scalix, asks about Scalix AI or Lumio models, or wants to point existing OpenAI-compatible code at Scalix.