create-ai-assistant

create-ai-assistant is a skill for Claude Code from runwhen-contrib/runwhen-platform-mcp. It costs 117 tokens per session (1,677 once invoked), scanned A, original, Apache-2.0.

A guide for creating and tailoring named AI assistants in a RunWhen workspace.

In plain words
What is it for?
Use it to create, update, or delete assistants and attach stack-specific rules and reusable commands to them.
Why use it?
It helps teams give different assistants focused knowledge and behavior for particular technologies, teams, or workflows.

Skill for Claude Code

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

Part of the runwhen-platform plugin — 15 skills, 3 agents, 1 MCP server shipped together

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.

agentmods
npx agentmods add skills/runwhen-contrib/runwhen-platform-mcp/create-ai-assistant
Any agent
npx skills add runwhen-contrib/runwhen-platform-mcp --skill create-ai-assistant
Clone the repo
git clone --depth 1 https://github.com/runwhen-contrib/runwhen-platform-mcp

Made for: Claude Code.

Or install runwhen-platform, the plugin that ships this one along with the rest of its 15 skills, 3 agents, 1 MCP server.

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 create-ai-assistant

README.md
[![agentmods](https://agentmods.dev/badge/skills/runwhen-contrib/runwhen-platform-mcp/create-ai-assistant.svg)](https://agentmods.dev/skills/runwhen-contrib/runwhen-platform-mcp/create-ai-assistant)
Your own site
<a href="https://agentmods.dev/skills/runwhen-contrib/runwhen-platform-mcp/create-ai-assistant"><img src="https://agentmods.dev/badge/skills/runwhen-contrib/runwhen-platform-mcp/create-ai-assistant.svg" alt="Measured on agentmods" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,677 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00117 $0.01677
Opus 5 $0.00059 $0.00839
Sonnet 5 $0.00023 $0.00335
Haiku 4.5 $0.00012 $0.00168

Measured 6d ago against content hash 919142765ce2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

create-ai-assistant 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.

skills/create-ai-assistant/SKILL.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create an AI Assistant

An AI Assistant (also called an Agent or, internally, a persona) is a named configuration of the RunWhen workspace AI. Each assistant can be focused on a particular tech stack, team, or workflow — e.g. an "Azure DevOps Helper" that prioritizes pipeline and repo tasks, or a "Postgres On-Call" that knows which replicas to inspect.

The assistant's short_name is exactly the value you pass as persona_name to workspace_chat. So once you create azure-devops, you talk to it with:

workspace_chat(workspace_name="my-workspace", message="...", persona_name="azure-devops")

You tailor an assistant in two layers:

  1. The assistant itself — display name, description, and search/filter/run tuning (create_assistant / update_assistant).
  2. Persona-scoped rules and commands — behavior instructions and reusable procedures attached to just this assistant (create_chat_rule / create_chat_command with scope_type="persona").

When to use

  • A team wants a focused assistant for a specific tech stack (Azure DevOps, GKE, Kafka…)
  • Different audiences need different investigation behavior in the same workspace
  • You want to bundle stack-specific noise suppression, priorities, and runbooks under one identity

If you only need to tune behavior for everyone in a workspace, prefer workspace-scoped rules/commands (see manage-rules, manage-commands) and skip creating a new assistant.

Key concepts

Concept Tool Notes
Assistant identity create_assistant short_name becomes the persona_name for chat
Assistant tuning create_assistant / update_assistant Filters, search filters, run config
Per-assistant behavior create_chat_rule (scope_type="persona") 1–3 sentence interpretation rules
Per-assistant procedures create_chat_command (scope_type="persona") Reusable slash-command workflows
Verify workspace_chat (persona_name=...) Talk to the assistant to confirm behavior

Read the full file on GitHub · 181 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. 6d ago First seen · 181 lines · 117 tokens per session scan A 919142765ce2

Subscribe to this mod's changes

create-ai-assistant is a skill published in the GitHub repository runwhen-contrib/runwhen-platform-mcp (1 stars, last pushed 22d ago), licensed Apache-2.0. It adds 117 tokens to every session and 1,677 once invoked, about $0.0006 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 2026-08-31.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

specflow-use

To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.

griddynamics/rosetta · 27 tokens

qa-knowledge

To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.

griddynamics/rosetta · 32 tokens

ue-mcp-epic-routing

Use when deciding between ue-mcp's native category actions and Epic's wrapped ToolsetRegistry tools (the epic actions, incl. the Blueprint graph DSL) for a task in Unreal. Pulls in when authoring Blueprint graph bodies, or any time both a native action and an epic action could do the job and you need to pick.

db-lyon/ue-mcp · 81 tokens

mcp-google-map-project

Project knowledge for developing and maintaining @cablate/mcp-google-map. Architecture, Google Maps API guide, GIS domain knowledge, and design decisions. Read this skill to onboard onto the project or make informed development decisions.

cablate/mcp-google-map · 49 tokens

frontmcp-setup

Use when starting, scaffolding, or organizing a FrontMCP project. Covers creating a new project (CLI scaffold or manual) for Node, Vercel, and other targets; standalone versus Nx-monorepo layout, naming conventions, generators, and dependency rules; composing multiple @App classes, ESM packages, and remote MCP servers…

agentfront/frontmcp · 176 tokens