Run config global settings
Skill kjuhwa/skills-hub/skills/agents/run-config-global-settings
Use RunConfig to set run-wide defaults for model, max turns, tracing, and guardrails.From its SKILL.md
npx -y skills add kjuhwa/skills-hub --skill run-config-global-settingsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.4 KB, 443 tokens by cl100k_base, as published. Nobody here has run it
run-config-global-settings
Pass RunConfig to Runner.run(run_config=...) to set run-wide defaults that apply unless overridden by per-agent settings.
When to apply
When you want consistent model defaults, turn limits, tracing, or input filters across all agents in a run without configuring each agent individually.
Core snippet
import asyncio
from agents import Agent, Runner, ModelSettings
from agents.run import RunConfig
run_config = RunConfig(
model="gpt-4o-mini", # Default model for all agents
model_settings=ModelSettings( # Default model settings
temperature=0.5,
max_tokens=2048,
),
max_turns=20, # Default is 10
tracing_disabled=False,
workflow_name="My Workflow", # Name shown in Traces dashboard
trace_include_sensitive_data=True, # Include tool args/outputs in traces
)
agent = Agent(
name="Assistant",
instructions="You are a helpful assistant.",
# Agent-level model overrides RunConfig.model for this agent
model="gpt-4o",
)
async def main():
result = await Runner.run(agent, "Hello!", run_config=run_config)
print(result.final_output)
asyncio.run(main())
Key properties
| Property | Default | Description |
|---|---|---|
model | None (agent's model) | Run-wide model override |
max_turns | 10 | Max agent loop iterations |
tracing_disabled | False | Disable traces for this run |
workflow_name | "Agent workflow" | Name in Traces dashboard |
trace_include_sensitive_data | True | Include args/outputs in traces |
Key notes
- Per-agent
modelandmodel_settingsoverrideRunConfigvalues for that agent RunConfigis passed toRunner.run(), not stored on the Agentcall_model_input_filtercan intercept and modify the input before each model call
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.