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-ai-model-capabilitiesgit 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-model-capabilities)<a href="https://agentmods.dev/skills/crestapps/crestapps.agentskills/crestapps-core-ai-model-capabilities"><img src="https://agentmods.dev/badge/skills/crestapps/crestapps.agentskills/crestapps-core-ai-model-capabilities/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/crestapps-core-ai-model-capabilities"><img src="https://agentmods.dev/badge/skills/crestapps/crestapps.agentskills/crestapps-core-ai-model-capabilities.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00210 | $0.03360 |
| Opus 5.5 | $0.00084 | $0.01344 |
| Sonnet 5.5 | $0.00042 | $0.00672 |
| Haiku 4.5 | $0.00021 | $0.00336 |
Grade A, and why
crestapps-core-ai-model-capabilities 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 yesterday.
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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CrestApps.Core AI Model Capabilities
A deployment declares what its model can do. Two kinds of definitions are registered once at startup and referenced by name:
| Concept | Shape | Example |
|---|---|---|
| Feature | A trained capability the model has or lacks | toolCalling, reasoning, realtime |
| Parameter | A configurable option with a kind, allowed values, range and default | reasoningEffort |
| Slot | What this installation uses a deployment for; pairs a required feature with a site default | chat, embedding, realtime |
Capabilities live on the deployment. Slots are derived from them: declaring textEmbedding is what puts a model in the embedding picker. There is no purpose flag to set.
Guidelines
AddCoreAIServices()already callsAddCoreAIDeploymentCapabilities(), which callsAddCoreAIDeploymentSlots(). Call them directly only in hosts that compose raw registrations.- Declare only trained traits as features. Provider-hosted tools (web search, computer use) are ordinary tools, not features.
textGenerationis opt-out: a deployment with no metadata counts as text-capable and is unconstrained. Every other feature is opt-in. Once a deployment declares any metadata, everything it omits is enforced as unsupported.speechToTextandtextToSpeechmean a dedicated transcription or synthesis endpoint.audioInputandaudioOutputmean a chat model that accepts or emits audio inline. Never mix them.- Use
IAIDeploymentCapabilityServiceto ask what a deployment supports. Do not readAIDeploymentMetadatadirectly in business code. - See
crestapps-core-ai-runtimefor slot resolution in everyday code and the provider skills for provider-specific features.
Built-in Definitions
| Feature | Constant | Default on new deployments |
|---|---|---|
textGeneration |
AIDeploymentFeatureNames.TextGeneration |
yes |
toolCalling |
AIDeploymentFeatureNames.ToolCalling |
yes |
streaming |
AIDeploymentFeatureNames.Streaming |
yes |
structuredOutputs, reasoning, imageInput, imageOutput, audioInput, audioOutput, videoInput, videoOutput, realtime, textEmbedding, speechToText, textToSpeech |
matching AIDeploymentFeatureNames constants |
no |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 212 lines · 210 tokens per session scan A bfca54c96e0a
crestapps-core-ai-model-capabilities is a skill published in the GitHub repository CrestApps/CrestApps.AgentSkills (13 stars, last pushed yesterday), licensed MIT. It adds 210 tokens to every session and 3,360 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-10-22.
Other skills, from other repositories
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…
gdal-api
Use when programming against GDAL/OGR in C, C++, Python, Java, or .NET — raster/vector I/O, gdal.UseExceptions, OGRSpatialReference transforms, gdal.Translate / gdal.Warp, VRT/COG, or fixing "no driver registered" and UnsatisfiedLinkError; C++ gdal-config, Maven org.gdal:gdal 3.13.0, NuGet MaxRev.Gdal.Core.
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.
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.
opik-verify
Decide ship or hold for a candidate from the compare skill's numbers, against an explicit release policy — regressions, pass rate, safety-tagged cases, subgroup consistency, latency and cost budgets, flakiness, evidence size, and whether the judge is validated. Reads two experiments on an Opik test suite via the SDK…
add-prompt
Scaffold a new MCP prompt template. Use when the user asks to add a prompt, create a reusable message template, or define a prompt for LLM interactions.