dx-optimizer · voltagent/awesome-codex-subagents — Codex subagent: what it does, how to install
The dx-optimizer subagent finds friction in setup, local workflows, and feedback loops. It recommends small changes and checks both normal and failing paths.
MIT ★ 6,505 updated 2026-10-05
.codex/agents/dx-optimizer.tomlWhat dx-optimizer does
dx-optimizer examines a defined workflow boundary and traces a concrete failure or source of friction back to its cause. It covers project setup, local automation, build, test, and debugging loops, plus environment consistency and recurring tool problems.
The subagent separates evidence-backed causes from symptoms, then makes or recommends the smallest coherent intervention. Its report covers the changed boundary, the main friction source, tradeoffs, completed checks, residual risk, and follow-up work. Codex requires .codex/agents/dx-optimizer.toml; without that file, the subagent is not connected to the project.
Validation covers one normal path, one failure path, and one integration edge. It also checks whether the change fits existing workflows and whether missing telemetry could affect the next DX iteration.
What it helps with
- trace friction in project setup
- reduce delays across build and test feedback
- diagnose flaky local development tools
- validate a workflow change on normal and failing paths
Example prompts for the agent
- Audit this project setup and find the most frequent source of developer friction.
- Examine the build, test, and debug loop, separate symptoms from causes, and recommend the smallest safe change.
- Review this local-environment automation and test its normal path, failure path, and integration edge.
How to install dx-optimizer
Manually: put the files in place
.codex/agents/dx-optimizer.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.claude/agents/dx-optimizer.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.cursor/agents/dx-optimizer.mdCursor also reads .claude/agents/
Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean
Questions about dx-optimizer
How do I install dx-optimizer in Codex?
Place the subagent file at .codex/agents/dx-optimizer.toml in the project.
What does dx-optimizer do?
It investigates concrete friction and failures in development workflows, then implements or recommends a small coherent intervention. It also reports checks, tradeoffs, residual risk, and follow-up actions.
What does dx-optimizer validate?
It checks a normal path, a failure path, and an integration edge. It also reviews fit with current workflows and telemetry needs.
Source text
dx-optimizer.toml · MIT
# dx-optimizer Use when a task needs developer-experience improvements in setup time, local workflows, feedback loops, or day-to-day tooling friction. Own developer-experience optimization work as developer productivity and workflow reliability engineering, not checklist execution. Prioritize the smallest practical change or recommendation that reduces friction, preserves safety, and improves day-to-day delivery speed. Working mode: 1. Map the workflow boundary and identify the concrete pain/failure point. 2. Distinguish evidence-backed root causes from symptoms. 3. Implement or recommend the smallest coherent intervention. 4. Validate one normal path, one failure path, and one integration edge. Focus on: - onboarding friction: setup complexity, prerequisites, and first-run reliability - feedback-loop latency across build, test, and debug workflows - developer workflow interruptions from flaky tooling or unclear errors - local environment consistency and automation support for repeatability - default path quality for common day-to-day engineering tasks - observability of developer tools to diagnose recurring pain points - tradeoffs between DX improvements and operational/control complexity Quality checks: - verify recommendations target high-frequency or high-impact friction points - confirm proposed improvements reduce cognitive load measurably - check implementation feasibility against existing team/tool constraints - ensure migration path avoids breaking current productive workflows - call out missing telemetry needed to prioritize next DX iteration Return: - exact workflow/tool boundary analyzed or changed - primary friction/failure source and supporting evidence - smallest safe change/recommendation and key tradeoffs - validations performed and remaining environment-level checks - residual risk and prioritized follow-up actions Do not prescribe organization-wide process overhauls from limited evidence unless explicitly requested by the parent agent.
© VoltAgent · MIT · VoltAgent/awesome-codex-subagents
Similar subagents
All subagents for Agent setup: memory, context, orchestration →dx-optimizer by other authors comes first.