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-chat-interactionsgit 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-chat-interactions)<a href="https://agentmods.dev/skills/crestapps/crestapps.agentskills/crestapps-core-chat-interactions"><img src="https://agentmods.dev/badge/skills/crestapps/crestapps.agentskills/crestapps-core-chat-interactions/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-chat-interactions"><img src="https://agentmods.dev/badge/skills/crestapps/crestapps.agentskills/crestapps-core-chat-interactions.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00202 | $0.03158 |
| Opus 5.5 | $0.00081 | $0.01263 |
| Sonnet 5.5 | $0.00040 | $0.00632 |
| Haiku 4.5 | $0.00020 | $0.00316 |
Grade A, and why
crestapps-core-chat-interactions 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CrestApps.Core Chat Interactions
A Chat Interaction is an operator-controlled conversation that needs no AI Profile: the interaction itself stores its deployments, system message, sampling, tools, agents, MCP connections, data source and documents. It is the fastest way to validate a provider and deployment. AI Chat sessions (AIChatSession) are the profile-based equivalent used by end-user chat pages and widgets. Both ship in CrestApps.Core.AI.Chat and share the same chat UI scripts.
Guidelines
- Start with Chat Interactions to validate a connection and deployment, then move reusable behavior into an AI Profile (
crestapps-core-ai-profiles). - Register stores for
ChatInteractionandIChatInteractionPromptStoreon the chat interactions builder. - The framework does not ship a mapped hub. Subclass
ChatInteractionHubBase(andAIChatHubCore<TClient>for sessions), map it, and callConfigureChatHubOptions<THub>()for each concrete hub. - The hubs' authorization hooks return
trueby default. Override them or put[Authorize]on the hub. - Chat Interactions do not get the AI Profile prompt-security preamble or injection blocking (the operator controls the prompt), but they do get input-boundary delimiters and a per-user tool access check at send time.
- Use
crestapps-core-chatfor server-side completion code,crestapps-core-signalrfor hub routes and authentication, andcrestapps-core-realtime-voicefor voice sessions.
Registration
using CrestApps.Core.AI.Chat;
using CrestApps.Core.AI.OpenAI;
using CrestApps.Core.AI.Security;
using CrestApps.Core.Data.EntityCore;
using CrestApps.Core.SignalR;
using MyApp.Hubs;
builder.Services.AddCrestAppsCore(crestApps => crestApps
.AddAISuite(ai => ai
.AddEntityCoreStores()
.AddOpenAI()
.AddSignalR(addStoreCommitterFilter: true)
.AddChatInteractions(chatInteractions => chatInteractions
.AddEntityCoreStores()
.ConfigureChatHubOptions<ChatInteractionHub>()
.ConfigureVisitorIdentity(options =>
{
options.RemoteAddressMode = AIVisitorRemoteAddressMode.Hashed;
})
.ConfigureChatRateLimiting(options =>
{
options.AnonymousSessionStartPartitions =
ChatRateLimitPartition.Visitor |
ChatRateLimitPartition.NetworkAddress;
})
)
)
.AddEntityCoreSqliteDataStore("Data Source=app.db")
);
// HubOptions<THub> is per concrete hub type; configure every chat hub you map.
builder.Services.ConfigureCrestAppsChatHubOptions<AIChatHub>();
var app = builder.Build();
app.MapHub<ChatInteractionHub>("/hubs/chat-interaction");
app.MapHub<AIChatHub>("/hubs/ai-chat");
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 Changed · +129 lines · +176 tokens per session 0cd0a4f7f902
- 1mo ago First seen · 46 lines · 26 tokens per session scan A cb779956df75
crestapps-core-chat-interactions is a skill published in the GitHub repository CrestApps/CrestApps.AgentSkills (13 stars, last pushed yesterday), licensed MIT. It adds 202 tokens to every session and 3,158 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 2026-08-30.
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…
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.
manage-annotations
MUST READ before creating, modifying, or querying annotations. Contains parameter names, coordinate model, and API quirks.
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.
data-engineering
Method for scraping, transforming, validating and loading data through NDJSON. Use when building a scraper or ETL step, validating an NDJSON feed, or importing data into a CMS or database.
vector-backend-operations
Select and connect the right vector-store backend for the vector-mcp MCP server — chromadb, postgres/pgvector, qdrant, couchbase, or mongodb — and supply the correct dbtype/connection parameters that every collection and search call needs. Use when the agent must decide which engine to target, wire up…