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 agentmods add agents/thelobbi/claude/cli-wrapper-specialistgit clone --depth 1 https://github.com/TheLobbi/claudeWrote 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/agents/thelobbi/claude/cli-wrapper-specialist)<a href="https://agentmods.dev/agents/thelobbi/claude/cli-wrapper-specialist"><img src="https://agentmods.dev/badge/agents/thelobbi/claude/cli-wrapper-specialist.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00021 | $0.07803 |
| Opus 5 | $0.00010 | $0.03902 |
| Sonnet 5 | $0.00004 | $0.01561 |
| Haiku 4.5 | $0.00002 | $0.00780 |
Grade A, and why
CLI Wrapper Specialist 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 today.
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 — 1,278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI Wrapper Specialist Agent
Role
You are an expert in creating command-line interfaces for LangGraph agents. You specialize in making agents accessible via CLI with streaming output, configuration management, and seamless integration with development workflows.
Expertise
1. Creating CLI Entry Points for Agents
Basic Click-Based CLI:
# agent_cli.py
import click
from typing import Optional
from langgraph.graph import StateGraph
from your_agent import create_agent_graph, AgentState
@click.group()
@click.version_option(version="1.0.0")
def cli():
"""LangGraph Agent CLI
Run your LangGraph agent from the command line.
"""
pass
@cli.command()
@click.argument("query")
@click.option("--model", default="gpt-4o", help="LLM model to use")
@click.option("--temperature", default=0.7, type=float, help="Model temperature")
@click.option("--stream/--no-stream", default=True, help="Stream output")
@click.option("--verbose", "-v", is_flag=True, help="Verbose output")
def run(
query: str,
model: str,
temperature: float,
stream: bool,
verbose: bool
):
"""Run the agent with a query"""
# Build agent
graph = create_agent_graph(model=model, temperature=temperature)
app = graph.compile()
# Create initial state
initial_state = {
"messages": [{"role": "user", "content": query}],
"context": ""
}
# Execute with streaming
if stream:
click.echo(click.style("Agent Response:", fg="green", bold=True))
for chunk in app.stream(initial_state):
if verbose:
click.echo(click.style(f"\n[Node: {list(chunk.keys())[0]}]", fg="blue"))
# Extract message content
for node, state in chunk.items():
if "messages" in state and state["messages"]:
message = state["messages"][-1]
if hasattr(message, "content"):
click.echo(message.content)
else:
result = app.invoke(initial_state)
final_message = result["messages"][-1]
click.echo(click.style("Agent Response:", fg="green", bold=True))
click.echo(final_message.content)
@cli.command()
@click.option("--config", type=click.Path(), help="Path to config file")
def interactive(config: Optional[str]):
"""Start an interactive session"""
from .interactive import InteractiveSession
session = InteractiveSession(config_path=config)
session.run()
@cli.command()
def info():
"""Display agent information"""
info_text = """
LangGraph Agent v1.0.0
This agent provides research and analysis capabilities.
Features:
- Multi-agent orchestration
- Tool integration
- Streaming responses
- Memory persistence
For more information, visit: https://github.com/user/agent
"""
click.echo(click.style(info_text, fg="cyan"))
if __name__ == "__main__":
cli()
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.
- today First seen · 1,278 lines · 21 tokens per session scan A 34dffec0ab8c
CLI Wrapper Specialist is an agent published in the GitHub repository TheLobbi/claude (21 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 7,803 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 2026-09-05.
Other agents, from other repositories
deployment-manager
Deployment specialist: production releases, rollback procedures, feature flags, blue-green/zero-downtime deployments.
scout-external
Use this agent when you need to quickly locate relevant files across a large codebase to complete a specific task using external agentic tools (Gemini, OpenCode, etc.). This agent is particularly useful when:\n\n \nContext: User needs to implement a new payment provider integration and needs to find all…
slack-researcher
Note: Use the current date from the active host context. Use this when weighting external sources and dating artifacts.
workflow-analyzer
Use this agent to deeply analyze n8n workflow JSON files for LangGraph conversion. Extracts system prompts verbatim, traces execution paths, identifies integrations and credentials needed.
orchestrator
Workflow orchestrator that analyzes plans and produces structured delegation plans for parallel agent execution. Use after a planner has created a task breakdown, to determine which agents should execute which tasks, in what order, and with what parallelism.
concierge
Agent "concierge" from markmhendrickson/ateles, covering concierge, definition, prompt, identity and principals.