crestapps-core-ai-personas

crestapps-core-ai-personas is a skill for Claude Code from CrestApps/CrestApps.AgentSkills. It costs 196 tokens per session (2,060 once invoked), scanned A, original, MIT.

A reusable definition for an AI assistant's identity, including its instructions, name, language, voice, and avatar. Profiles and conversations can link to a persona by name so one change applies wherever that persona is used.

In plain words
What is it for?
Use it to define and reuse assistant identities across AI profiles, chat interactions, realtime conversations, and voice experiences.
Why use it?
It prevents teams from copying the same identity settings into many assistant profiles. Updating the shared persona changes later conversations that link to it.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the crestapps-core plugin — 47 skills shipped together

Good fit Use it to define and reuse assistant identities across AI profiles, chat interactions, realtime conversations, and voice experiences.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/crestapps/crestapps.agentskills/crestapps-core-ai-personas
Install

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.

Any agent
npx skills add CrestApps/CrestApps.AgentSkills --skill crestapps-core-ai-personas
Clone the repo
git clone --depth 1 https://github.com/CrestApps/CrestApps.AgentSkills

Made for: Claude Code.

Or install crestapps-core, the plugin that ships this one along with the rest of its 47 skills.

Wrote 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.

agentmods badge for crestapps-core-ai-personas

README.md
[![agentmods](https://agentmods.dev/badge/skills/crestapps/crestapps.agentskills/crestapps-core-ai-personas/github.svg)](https://agentmods.dev/skills/crestapps/crestapps.agentskills/crestapps-core-ai-personas)
Your own site
<a href="https://agentmods.dev/skills/crestapps/crestapps.agentskills/crestapps-core-ai-personas"><img src="https://agentmods.dev/badge/skills/crestapps/crestapps.agentskills/crestapps-core-ai-personas/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.

agentmods 80×15 button for crestapps-core-ai-personas

Your own site · 80×15
<a href="https://agentmods.dev/skills/crestapps/crestapps.agentskills/crestapps-core-ai-personas"><img src="https://agentmods.dev/badge/skills/crestapps/crestapps.agentskills/crestapps-core-ai-personas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 196 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,060 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00196 $0.02060
Opus 5.5 $0.00078 $0.00824
Sonnet 5.5 $0.00039 $0.00412
Haiku 4.5 $0.00020 $0.00206

Measured yesterday against content hash 91920b42fab7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

crestapps-core-ai-personas 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.

plugins/crestapps-core/skills/crestapps-core-ai-personas/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CrestApps.Core AI Personas

A persona says who the assistant is: its instructions, the name it uses, its language, voice and avatar. The profile's system message and prompt templates still say what it does. A resource links to one optional persona by its technical name, so editing the persona changes every profile, interaction and template that links to it from the next message. Personas are not AI templates: a template is copied when used, a persona stays linked.

Guidelines

  • Personas are opt-in. Without AddPersonas(...), persona links are kept but ignored and chats run with the profile's own instructions and voice.
  • Link by Name, never by item id. Names survive export and import across tenants; ids do not. A persona's name cannot change once saved.
  • Keep business rules in the profile. The persona block comes first in the system message, so the profile's rules win a conflict.
  • Greetings stay with the profile's welcome message so one persona can serve profiles that open differently.
  • Resolve personas only through IAIPersonaResolver (or the service-provider helpers) so chat, chat interactions, realtime and voice behave the same.

Registration

builder.Services.AddCrestAppsCore(crestApps => crestApps
    .AddAISuite(ai => ai
        .AddOpenAI()
        .AddPersonas(personas => personas
            .AddYesSqlStores()          // or .AddEntityCoreStores()
            .AddEmbeddedPersonas(typeof(Program).Assembly))
    )
);

AddPersonas (or services.AddCoreAIPersonas()) registers IAIPersonaManager, IAIPersonaResolver, the persona catalog handler, AIPersonaCompletionContextBuilderHandler and AIPersonaFileSystemProvider, which reads Templates/Personas in the content root. A YesSql host also creates the index table once with schemaBuilder.CreateAIPersonaIndexSchemaAsync(yesSqlStoreOptions) next to its other index tables.

What a Persona Holds

AIPersona property Purpose
Name Technical name links point to; fixed after save
DisplayText, Description Editor display
Instructions Required persona prompt, rendered as Liquid
AssistantName Name the assistant uses; shown on assistant messages
Language BCP-47 tag used as the speech language when the caller names none
VoiceName, VoiceDeploymentName Provider-specific voice and the deployment it was chosen from
AvatarUrl Optional avatar image

Read the full file on GitHub · 197 lines

Changes

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.

  1. yesterday First seen · 197 lines · 196 tokens per session scan A 91920b42fab7

Subscribe to this mod's changes

crestapps-core-ai-personas is a skill published in the GitHub repository CrestApps/CrestApps.AgentSkills (13 stars, last pushed yesterday), licensed MIT. It adds 196 tokens to every session and 2,060 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.

Related

Other skills, from other repositories

powerpoint-cli

Discover and use the PowerPoint CLI plugin to automate a live PowerPoint desktop session. Use for terminal, PowerShell, batch, and coding-agent tasks; not general presentation design. Triggers: pptcli, PowerPoint command line, presentation automation script.

sbroenne/mcp-server-powerpoint · 55 tokens

powerpoint-deck-design

Plan or improve the visual design of a PowerPoint presentation: layout, typography, color, hierarchy, accessibility, and consistency. Use when the user asks to create, redesign, or review how a deck looks; not for general PowerPoint automation or content-only edits.

sbroenne/mcp-server-powerpoint · 59 tokens

home-memory-documentation

Do not load unless the request or established context explicitly identifies Home Memory (HM) and requires a documentation decision about record boundaries, relationships or information placement. If the product is ambiguous, ask whether the user means Home Memory or Smartconstruct and load neither product skill first.…

impactjo/home-memory · 112 tokens

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…

jkolo/debug-mcp · 70 tokens

sast-missingauth

Detect missing authentication and broken function-level authorization vulnerabilities in a codebase using a three-phase approach: recon (map endpoints and the role/permission system), batched verify (check auth/authz in parallel subagents, 3 endpoints each), and merge (consolidate batch results). Covers…

capture0x/YeepForge · 121 tokens

sast-analysis

Perform codebase analysis and architecture mapping as the first phase of a security assessment. Explores the tech stack, frameworks, entry points, data flows, and trust boundaries. Outputs sast/architecture.md. Run this before any vulnerability detection skill. Use when asked to analyze a codebase for security or when…

capture0x/YeepForge · 73 tokens