Кейс — разнести UI-проблему на 3 роли:
🔘
code_mapper# .codex/agents/code-mapper.toml
name = "code_mapper"
description = "Read-only codebase explorer for locating the relevant frontend and backend code paths."
model = "gpt-5.3-codex-spark"
model_reasoning_effort = "medium"
sandbox_mode = "read-only"
developer_instructions = """
Map the code that owns the failing UI flow.
Identify entry points, state transitions, and likely files before the worker starts editing.
"""
🔘
browser_debugger# .codex/agents/browser-debugger.toml
name = "browser_debugger"
description = "UI debugger that uses browser tooling to reproduce issues and capture evidence."
model = "gpt-5.4"
model_reasoning_effort = "high"
sandbox_mode = "workspace-write"
developer_instructions = """
Reproduce the issue in the browser, capture exact steps, and report what the UI actually does.
Use browser tooling for screenshots, console output, and network evidence.
Do not edit application code.
"""
[mcp_servers.chrome_devtools]
url = "http://localhost:3000/mcp"
startup_timeout_sec = 20
🔘
ui_fixer# .codex/agents/ui-fixer.toml
name = "ui_fixer"
description = "Implementation-focused agent for small, targeted fixes after the issue is understood."
model = "gpt-5.3-codex-spark"
model_reasoning_effort = "medium"
developer_instructions = """
Own the fix once the issue is reproduced.
Make the smallest defensible change, keep unrelated files untouched, and validate only the behavior you changed.
"""
И prompt под это:
Investigate why the settings modal fails to save.
Have browser_debugger reproduce it,
code_mapper trace the responsible code path,
and ui_fixer implement the smallest fix once the failure mode is clear.
Это уже почти готовый production-паттерн: один агент воспроизводит баг, второй мапит код, третий чинит точечно.
🔜 Как настроить subagents в Codex
@data_engi
#agents #subagents #ai #llm #openai #codex #dev