agent

A command hub for creating, configuring, listing, and running specialized AI agents. Specialized agents are assistants set up for particular kinds of work.

In plain words
What is it for?
It is for creating agent definitions, assigning their tools and permissions, forming agent teams, and invoking agents for specific tasks.
Why use it?
It helps organize different assistants instead of handling every task with one general agent.

Command for Claude Code

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 commands/smart-ai-memory/empathy-framework/agent
Clone the repo
git clone --depth 1 https://github.com/Smart-AI-Memory/empathy-framework

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,721 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 $0.00013 $0.01721
Opus 5 $0.00006 $0.00860
Sonnet 5 $0.00003 $0.00344
Haiku 4.5 $0.00001 $0.00172

Measured 2d ago against content hash dc9de27ce5b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

.claude/commands/agent.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Management

Aliases: /agents

Create, configure, and orchestrate specialized agents.

Quick Examples

/agent                      # Interactive menu
/agent "create code review" # Create new agent
/agent "list available"     # List agents

Discovery

Question:
  header: "Task"
  question: "What would you like to do with agents?"
  options:
    - label: "Create new agent"
      description: "Define a new specialized agent"
    - label: "Create agent team"
      description: "Assemble agents for collaborative work"
    - label: "List agents"
      description: "View available agents and their capabilities"
    - label: "Invoke agent"
      description: "Run a specific agent for a task"

Create New Agent

Define a new specialized agent in markdown format.

Tell me:

  • Agent name and purpose
  • What tasks it should handle
  • Any special tools or permissions needed

I will:

  1. Create agent markdown file in agents_md/
  2. Define appropriate:
    • Role and description
    • Tool permissions
    • Model tier (cheap/capable/premium)
    • Empathy level (1-5)
  3. Add detailed instructions
  4. Register in the agent registry

Agent file format:

---
name: my-agent
description: What this agent does
role: specialist
tools: [Read, Grep, Glob]
model_tier: capable
empathy_level: 3
---

# Agent Instructions

Detailed instructions for the agent...

Create Agent Team

Assemble multiple agents for collaborative work using one of 10 composition patterns.

Tell me:

  • Team purpose
  • What agents should be included
  • Workflow type (or let me auto-select based on task)

I will:

  1. Select appropriate agents
  2. Choose optimal composition pattern (from 10 available)
  3. Set up handoff points
  4. Configure aggregation of results

Available Composition Patterns:

Pattern When to Use Example
sequential Step-by-step pipeline Parse → Analyze → Report
parallel Independent tasks Security + Quality + Performance audits
debate Multiple perspectives 3 reviewers discuss approach
teaching Expert validates junior Draft (cheap) → Expert review
refinement Iterative improvement Draft → Review → Polish
adaptive Dynamic routing Classifier → Specialist
conditional Branch by condition If bug → Debugger, else Reviewer
tool_enhanced (NEW) Single agent + tools File reader with analysis tools
prompt_cached_sequential (NEW) Shared large context 3 agents using same docs/codebase
delegation_chain (NEW) Hierarchical coordination Coordinator → Specialists (≤3 levels)

Read the full file on GitHub · 251 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. 2d ago First seen · 251 lines · 13 tokens per session scan A dc9de27ce5b3

Subscribe to this mod's changes

agent is a command published in the GitHub repository Smart-AI-Memory/empathy-framework (13 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 1,721 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 2026-08-30.