agent

agent is a command for Claude Code from Sahib-Sawhney-WH/sahibs-claude-plugin-marketplace. It costs 14 tokens per session (1,229 once invoked), scanned A, original, MIT.

A code generator for Dapr Agents, a framework for building AI agents that can use language models, tools, memory, and Dapr services. It can scaffold assistant, durable, service, or multi-agent projects.

In plain words
What is it for?
Use it to create basic or workflow-backed agents, REST services, or systems where multiple agents work together, with selected tools, memory types, and language-model providers.
Why use it?
It removes the need to assemble the agent structure, dependencies, configuration, and container files by hand.

Command for Claude Code

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

Part of the dapr plugin — 9 skills, 14 commands, 8 agents shipped together

Good fit Use it to create basic or workflow-backed agents, REST services, or systems where multiple agents work together, with selected tools, memory types, and language-model providers.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/sahib-sawhney-wh/sahibs-claude-plugin-marketplace/agent
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.

Clone the repo
git clone --depth 1 https://github.com/Sahib-Sawhney-WH/sahibs-claude-plugin-marketplace

Made for: Claude Code.

Or install dapr, the plugin that ships this one along with the rest of its 9 skills, 14 commands, 8 agents.

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 agent

README.md
[![agentmods](https://agentmods.dev/badge/commands/sahib-sawhney-wh/sahibs-claude-plugin-marketplace/agent/github.svg)](https://agentmods.dev/commands/sahib-sawhney-wh/sahibs-claude-plugin-marketplace/agent)
Your own site
<a href="https://agentmods.dev/commands/sahib-sawhney-wh/sahibs-claude-plugin-marketplace/agent"><img src="https://agentmods.dev/badge/commands/sahib-sawhney-wh/sahibs-claude-plugin-marketplace/agent/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 agent

Your own site · 80×15
<a href="https://agentmods.dev/commands/sahib-sawhney-wh/sahibs-claude-plugin-marketplace/agent"><img src="https://agentmods.dev/badge/commands/sahib-sawhney-wh/sahibs-claude-plugin-marketplace/agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,229 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 $0.00014 $0.01229
Opus 5 $0.00007 $0.00615
Sonnet 5 $0.00003 $0.00246
Haiku 4.5 $0.00001 $0.00123

Measured 12d ago against content hash f965284f283a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

agent 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 12d 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.

plugins/dapr/commands/agent.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DAPR Agent Generator

Create intelligent, durable AI agents powered by LLMs using the DAPR Agents framework.

Behavior

When the user runs /dapr:agent:

  1. Determine Agent Type

    • Assistant: Basic LLM-powered agent with tools
    • Durable: Workflow-backed agent with fault tolerance
    • Service: Headless agent exposed via REST API
    • Multi: Multi-agent orchestration system
  2. Generate Agent Code

    • Create agent class with LLM integration
    • Add tool definitions with @tool decorator
    • Configure memory management
    • Set up Dapr components
  3. Create Supporting Files

    • requirements.txt with dapr-agents dependencies
    • Component YAML for state/conversation
    • Dockerfile for containerization

Arguments

Argument Description
assistant <name> Create a basic AssistantAgent
durable <name> Create a workflow-backed DurableAgent
service <name> Create a headless AgentService
multi <name> Create a multi-agent system
--tools Comma-separated list of tools to include
--memory Memory type: short-term, long-term, vector
--llm LLM provider: openai, azure, anthropic, ollama

Examples

Basic Assistant Agent

/dapr:agent assistant weather-bot

Creates an agent that can:

  • Process user queries
  • Call tools dynamically
  • Maintain conversation context

Durable Agent with Tools

/dapr:agent durable order-processor --tools "inventory,payment,shipping"

Creates a fault-tolerant agent with:

  • Workflow-backed execution
  • Automatic retry on failures
  • Persistent state across restarts

Headless Agent Service

/dapr:agent service research-agent --memory vector

Creates a REST API agent with:

  • HTTP endpoints for queries
  • Vector memory for RAG
  • Long-running task support

Multi-Agent System

/dapr:agent multi customer-support --agents "triage,technical,billing"

Creates coordinated agents with:

  • Pub/sub communication
  • Workflow orchestration
  • Specialized agent roles

Read the full file on GitHub · 219 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. 12d ago First seen · 219 lines · 14 tokens per session scan A f965284f283a

Subscribe to this mod's changes

agent is a command published in the GitHub repository Sahib-Sawhney-WH/sahibs-claude-plugin-marketplace (4 stars, last pushed 8mo ago), licensed MIT. It adds 14 tokens to every session and 1,229 once invoked, about $0.0001 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.