awesome-codex-subagents Documentation

A collection of 130+ specialized Codex subagents covering a wide range of development use cases.

6,304 stars Unknown 1 file · ~12,960 tokens #ai-agents#awesome-list#chatgpt#codex#codex-skills#codex-subagents#subagents
RAW Doc

Technical Documentation: VoltAgent/awesome-codex-subagents

ℹ️ Provenance: Multi-Tier Ingestion · CodeWiki Reference

Overview (`README.md`)

Awesome Codex Subagents

This repository serves as the definitive collection of Codex Subagents, specialized AI assistants designed for specific development tasks. Written specifically for Codex and aligned with the official docs.

Installation

Use Codex custom agent directories exactly as documented:

  • ~/.codex/agents/ for global agents (available in all projects)
  • .codex/agents/ for project-specific agents (higher precedence in that repo)
  1. Clone this repository.
  2. Copy the .toml agent files you want into one of the directories above.
  3. Restart or refresh your Codex session if needed.
  4. Delegate explicitly in prompts (Codex does not auto-spawn custom subagents).

Examples:

bash
mkdir -p ~/.codex/agents
cp categories/01-core-development/backend-developer.toml ~/.codex/agents/
bash
mkdir -p .codex/agents
cp categories/04-quality-security/reviewer.toml .codex/agents/

If you use agent configuration in Codex, keep it in .codex/config.toml under [agents] as described in the official docs.

Sponsors

Crawlbase is web data infrastructure trusted by 70,000+ developers. Its Crawling API, MCP server, and integrations give AI agents live access to any webpage — with JavaScript rendering, proxy rotation, and anti-bot protection.
SerpApi is a Web Search API for your AI apps. Available in Markdown and JSON for any integration.

Subagent Storage Locations

Type Path Availability Precedence
Project Subagents .codex/agents/ Current project only Higher
Global Subagents ~/.codex/agents/ All projects Lower

Note: When naming conflicts occur, project-specific subagents override global ones.

Subagent Structure

Each subagent uses a Codex-native .toml format:

toml
name = "subagent-name"
description = "When this agent should be invoked"
model = "gpt-5.6-luna"
model_reasoning_effort = "medium"
sandbox_mode = "read-only"

[instructions]
text = """
You are a [role description and expertise areas]...

[Agent-specific checklists, patterns, and guidelines]...
"""

Smart Model Routing

Each subagent includes a model field that automatically routes it to the right model -- balancing quality and cost:

Model When It's Used Examples
gpt-5.6-sol Deep reasoning -- architecture reviews, security audits, financial logic security-auditor, architect-reviewer, fintech-engineer
gpt-5.6-terra Implementation, diagnostics, evaluation, and multi-step professional analysis docker-expert, test-automator, scientific-literature-researcher
gpt-5.6-luna Bounded search, extraction, routing, drafting, and lightweight synthesis search-specialist, docs-researcher, agent-installer

Sandbox Mode Philosophy

Each subagent's sandbox_mode field controls filesystem access:

  • Read-only agents (reviewers, auditors): sandbox_mode = "read-only" - analyze without modifying
  • Workspace-write agents (developers, engineers): sandbox_mode = "workspace-write" - create and modify files

Categories

[01. Core Development](categories/01-core-development/)

Essential development subagents for everyday coding tasks.

[02. Language Specialists](categories/02-language-specialists/)

Language-specific experts with deep framework knowledge.

[03. Infrastructure](categories/03-infrastructure/)

DevOps, cloud, and deployment specialists.

04. Quality & Security — Testing, security, and code quality experts (20 agents)

[04. Quality & Security](categories/04-quality-security/)

05. Data & AI — Data engineering, ML, and AI specialists (14 agents)

[05. Data & AI](categories/05-data-ai/)

06. Developer Experience — Tooling and developer productivity experts (14 agents)

[06. Developer Experience](categories/06-developer-experience/)

07. Specialized Domains — Domain-specific technology experts (14 agents)

[07. Specialized Domains](categories/07-specialized-domains/)

08. Business & Product — Product management and business analysis (17 agents)

[08. Business & Product](categories/08-business-product/)

09. Meta & Orchestration — Agent coordination and meta-programming (12 agents)

[09. Meta & Orchestration](categories/09-meta-orchestration/)

10. Research & Analysis — Research, search, and analysis specialists (12 agents)

[10. Research & Analysis](categories/10-research-analysis/)

11. AI Governance & Safety - Governance, guardrails, and trustworthy AI specialists (4 agents)

[11. AI Governance & Safety](categories/11-ai-governance-safety/)

12. Platform Engineering & IDP - Internal developer platform and golden-path specialists (4 agents)

[12. Platform Engineering & IDP](categories/12-platform-engineering-idp/)

13. LLMOps, Evals & Observability - Production AI quality and runtime visibility specialists (4 agents)

[13. LLMOps, Evals & Observability](categories/13-llmops-evals-observability/)

Understanding Subagents

Subagents are specialized AI assistants that enhance Codex's capabilities by providing task-specific expertise. They act as dedicated helpers that Codex can call upon when encountering particular types of work.

What Makes Subagents Special?

Independent Context Windows
Every subagent operates within its own isolated context space, preventing cross-contamination between different tasks and maintaining clarity in the primary conversation thread.

Domain-Specific Intelligence
Subagents come equipped with carefully crafted instructions tailored to their area of expertise, resulting in superior performance on specialized tasks.

Shared Across Projects
After creating a subagent, you can utilize it throughout various projects and distribute it among team members to ensure consistent development practices.

Explicit Delegation
Codex does not spawn subagents automatically. Use explicit delegation prompts to specify which agents to spawn, how to divide the work, and what shape the result should take.

Core Advantages

  • Memory Efficiency: Isolated contexts prevent the main conversation from becoming cluttered with task-specific details
  • Enhanced Accuracy: Specialized prompts and configurations lead to better results in specific domains
  • Workflow Consistency: Team-wide subagent sharing ensures uniform approaches to common tasks
  • Codex-Native: Uses .toml agent files aligned with official Codex subagent docs

Example Workflows

PR review workflow:

text
Review this branch with parallel subagents. Have reviewer look for correctness, security, and missing tests. Have docs_researcher verify the framework APIs this patch depends on. Wait for both and summarize the findings with file references.

Bug investigation workflow:

text
Investigate the broken settings flow. Have code_mapper trace the owning code paths, browser_debugger reproduce the bug in the browser, and frontend_developer propose the smallest fix after the failure is understood. Wait for the read-heavy agents first, then continue.

Repo exploration and planning workflow:

text
Use search_specialist to locate the code related to payment retries, knowledge_synthesizer to summarize the current design, and refactoring_specialist to propose a minimal refactor plan. Return a concrete action list.

AI Design + Build Ecosystem Tools

You ship products with AI, but every launch still dies quietly because nobody posts about it. EveryFeed plugs your AI assistant into a social workspace that drafts, schedules, and publishes across 35+ channels — no agency, no marketing hire.

Contributing

We welcome contributions! See CONTRIBUTING.md for guidelines.

  • Submit new subagents via PR
  • Improve existing definitions
  • Report issues and bugs

License

MIT License - see LICENSE

This repository is a curated collection of subagent definitions contributed by both the maintainers and the community. All subagents are provided "as is" without warranty. We do not audit or guarantee the security or correctness of any subagent. Review before use, the maintainers accept no liability for any issues arising from their use.

If you find an issue with a listed subagent or want your contribution removed, please open an issue in this repository and we'll address it promptly.

Overview (`categories/01-core-development/README.md`)

01. Core Development

Core agents for application architecture, cross-layer implementation, UI work, and protocol-specific development.

Included agents:

  • api-designer - Design or review API contracts before implementation.
  • backend-developer - Own a scoped backend change after the code path is clear.
  • code-mapper - Trace the files, entry points, and state transitions behind a behavior.
  • design-bridge - Translate a DESIGN.md spec into implementation-ready UI instructions.
  • electron-pro - Handle Electron main and renderer process work, packaging, and desktop integration.
  • frontend-developer - Own a scoped frontend change after the issue is understood.
  • fullstack-developer - Own a bounded end-to-end feature that spans backend and frontend.
  • graphql-architect - Design or review GraphQL schemas, resolvers, and federation boundaries.
  • microservices-architect - Review service boundaries and distributed system contracts.
  • mobile-developer - Implement or debug mobile-specific flows and integrations.
  • ui-designer - Produce concrete UI direction another agent can implement.
  • ui-fixer - Apply a minimal UI fix after reproduction and evidence gathering.
  • websocket-engineer - Work on real-time connection, protocol, and event-delivery behavior.

Overview (`categories/02-language-specialists/README.md`)

02. Language Specialists

Language and framework specialists for ecosystem-specific implementation, debugging, and architectural guidance.

Included agents:

  • angular-architect - Angular architecture, routing, DI, and component behavior.
  • cpp-pro - C++ systems work with memory, concurrency, and performance sensitivity.
  • csharp-developer - C# and .NET service or application implementation.
  • django-developer - Django models, views, ORM, auth, and framework behavior.
  • dotnet-core-expert - Modern .NET and ASP.NET Core implementation and review.
  • dotnet-framework-4.8-expert - Legacy .NET Framework 4.8 compatibility-sensitive work.
  • elixir-expert - Elixir, OTP, Phoenix, and supervised concurrency systems.
  • erlang-expert - Erlang/OTP and rebar3 engineering.
  • expo-react-native-expert - Expo and React Native mobile work with EAS builds and native module integration.
  • fastapi-developer - FastAPI async endpoints, Pydantic v2 contracts, and ASGI deployment behavior.
  • flutter-expert - Flutter widgets, state, rendering, and platform integration.
  • golang-pro - Go services, concurrency, interfaces, and operational behavior.
  • java-architect - Java architecture and enterprise application evolution.
  • javascript-pro - JavaScript runtime behavior and application-level implementation.
  • kotlin-specialist - Kotlin application work, coroutines, and JVM interoperability.
  • laravel-specialist - Laravel routing, Eloquent, queues, and validation flow.
  • symfony-specialist - Symfony controllers, services, Doctrine, and security flow.
  • nextjs-developer - Next.js routing, rendering modes, and server/client boundaries.
  • node-specialist - Node.js services, event-loop behavior, streams, and runtime correctness.
  • php-pro - PHP server-side work across frameworks and runtime behavior.
  • powershell-5.1-expert - Windows PowerShell 5.1 legacy automation.
  • powershell-7-expert - Modern cross-platform PowerShell automation.
  • python-pro - Python changes, runtime issues, and packaging patterns.
  • rails-expert - Rails models, controllers, jobs, and convention-driven changes.
  • react-specialist - Modern React component and state-flow work.
  • rust-engineer - Rust ownership, async runtime, and performance-sensitive work.
  • sql-pro - Query design, SQL correctness, and migration review.
  • spring-boot-engineer - Spring Boot services, configuration, and data access behavior.
  • swift-expert - Swift and Apple-platform application engineering.
  • typescript-pro - TypeScript type design, safety, and refactors.
  • vue-expert - Vue component, composable, routing, and reactivity work.

Overview (`categories/03-infrastructure/README.md`)

03. Infrastructure

Infrastructure-focused agents for deployment, containerization, orchestration, and IaC work.

Included agents:

  • azure-infra-engineer - Azure resource, identity, and network-aware infrastructure review.
  • cloud-architect - Cloud platform and service-boundary architecture decisions.
  • database-administrator - Operational database administration, backup, and recovery concerns.
  • deployment-engineer - Release, rollout, rollback, and deployment-path changes.
  • devops-engineer - CI, deployment flow, and operational pipeline changes.
  • devops-incident-responder - Fast triage for delivery and automation incidents.
  • docker-expert - Dockerfiles, images, and container runtime issues.
  • incident-responder - Broad production incident triage and containment planning.
  • kubernetes-specialist - Cluster manifests, rollout safety, and workload debugging.
  • network-engineer - Connectivity, routing, load-balancing, and policy-path analysis.
  • platform-engineer - Internal platform and self-service workflow design.
  • security-engineer - Infrastructure and platform security engineering.
  • sre-engineer - Reliability engineering, SLOs, and resilience-focused review.
  • terraform-engineer - Terraform planning, module design, and drift-aware changes.
  • terragrunt-expert - Terragrunt layering, orchestration, and dependency hygiene.
  • windows-infra-admin - Windows infrastructure, AD, DNS, DHCP, and GPO administration.

Overview (`categories/04-quality-security/README.md`)

04. Quality & Security

Review and verification agents that work especially well as read-heavy Codex subagents.

Included agents:

  • accessibility-tester - Audit interfaces for a11y risks and missing coverage.
  • ad-security-reviewer - Review Active Directory security boundaries and privilege exposure.
  • anti-ui-slop-reviewer - Review interfaces for generic AI patterns and product-specific finish-gate failures.
  • ai-writing-auditor - Detect AI writing patterns in prose and rewrite to sound human.
  • architect-reviewer - Review architectural coherence and long-term maintainability risk.
  • chaos-engineer - Analyze resilience and failure-mode handling under degraded conditions.
  • code-reviewer - Review maintainability and risky implementation choices.
  • browser-debugger - Reproduce browser issues and collect concrete evidence.
  • compliance-auditor - Review auditability, policy alignment, and evidence gaps.
  • debugger - Isolate root causes across code paths and failing behavior.
  • error-detective - Analyze logs, stack traces, and error clusters quickly.
  • gdpr-ccpa-compliance - GDPR and CCPA/CPRA review of data flows, consent, and rights handling.
  • penetration-tester - Review realistic exploitability and attack paths.
  • performance-engineer - Investigate latency, throughput, and hot-path regressions.
  • powershell-security-hardening - Harden PowerShell automation and admin scripts.
  • qa-expert - Plan risk-based test strategy and coverage.
  • reviewer - Review changes for correctness, security, and missing tests.
  • security-auditor - Evaluate code and config for concrete security weaknesses.
  • test-automator - Add or improve automated tests and harnesses.
  • ui-ux-tester - Exhaustive UI/UX flow testing with structured defect reporting.

Overview (`categories/05-data-ai/README.md`)

05. Data & AI

Agents for data pipelines, LLM integrations, and database behavior.

Included agents:

  • ai-engineer - Build or debug model-backed product flows.
  • azure-databricks-platform-architect - Design Azure Databricks lakehouse, governance, compute, security, networking, reliability, and cost architecture.
  • data-analyst - Interpret metrics, trends, and analytics outputs for decisions.
  • data-engineer - Own scoped ETL, ingestion, or warehouse changes.
  • data-scientist - Analyze experiments, statistics, and model-related data questions.
  • database-optimizer - Diagnose slow queries and schema-level performance risks.
  • llm-architect - Review prompt, retrieval, evaluation, and orchestration design.
  • machine-learning-engineer - Implement training, serving, and model-system changes.
  • ml-engineer - Build practical ML-backed application behavior.
  • mlops-engineer - Own model delivery, registry, monitoring, and pipeline automation.
  • nlp-engineer - Build text-heavy retrieval, labeling, and NLP workflows.
  • postgres-pro - Handle PostgreSQL-specific schema and planner behavior.
  • prompt-engineer - Improve prompts, output contracts, and prompt evaluations.
  • reinforcement-learning-engineer - RL environment design, policy training, and safe deployment of decision systems.

Overview (`categories/06-developer-experience/README.md`)

06. Developer Experience

Agents for builds, developer tooling, documentation, MCP integrations, and refactors.

Included agents:

  • build-engineer - Build graph, bundling, and CI build fixes.
  • cli-developer - Command-line interface design and implementation.
  • dependency-manager - Upgrade and rationalize package and library graphs.
  • documentation-engineer - Technical documentation tied to real code changes.
  • dx-optimizer - Improve setup, local workflows, and developer feedback loops.
  • git-workflow-manager - Improve branching, merge, and release collaboration flow.
  • legacy-modernizer - Plan safe modernization of older code and frameworks.
  • mcp-developer - MCP server and client integration work.
  • powershell-module-architect - Design reusable PowerShell modules and command layout.
  • powershell-ui-architect - Build PowerShell-driven admin UI and operator tooling.
  • readme-generator - Maintainer-ready README generated from exact repository reality with zero hallucination.
  • refactoring-specialist - Plan and execute low-risk structural refactors.
  • slack-expert - Build Slack platform and integration behavior.
  • tooling-engineer - Create internal tools and workflow automation.

Overview (`categories/07-specialized-domains/README.md`)

07. Specialized Domains

Focused domain agents that still have a clear implementation or verification boundary.

Included agents:

  • api-documenter - Turn existing API behavior into clear consumer-facing docs.
  • blockchain-developer - Build or review blockchain, Web3, and transaction lifecycle flows.
  • embedded-systems - Work on firmware-adjacent and hardware-constrained systems.
  • fintech-engineer - Handle ledgers, reconciliation, settlement, and financial state integrity.
  • game-developer - Build or debug gameplay systems, loops, and state-heavy game code.
  • healthcare-admin - Revenue cycle, compliance, coding, and clinical operations with cited regulatory authority.
  • hipaa-compliance - HIPAA review for healthcare SaaS — BAA scope, PHI, safeguards, breach response.
  • iot-engineer - Work on device, telemetry, and edge-cloud coordination.
  • m365-admin - Review and guide Microsoft 365 tenant administration.
  • mobile-app-developer - Own app-level mobile product flows and release-sensitive behavior.
  • payment-integration - Review or implement payment flows, idempotency, and webhook handling.
  • quant-analyst - Analyze models, strategies, and quantitative decision logic.
  • risk-manager - Evaluate risk, impact, and mitigations for major changes.
  • seo-specialist - Review discoverability, crawlability, and search-facing technical issues.

Overview (`categories/08-business-product/README.md`)

08. Business & Product

Support agents for requirements, UX, and engineering-adjacent writing tasks.

Included agents:

  • assumption-mapping - Surface and prioritize risky assumptions in product ideas before building.
  • backlog-grooming - Sprint-ready backlog refinement, estimation, and zombie-story cleanup.
  • business-analyst - Clarify requirements, constraints, and acceptance criteria.
  • content-marketer - Shape product messaging grounded in real capability.
  • content-quality-editor - Strip AI writing patterns and apply a final quality pass before publishing.
  • customer-success-manager - Translate engineering behavior into customer-impact guidance.
  • growth-loops - Growth loop design, PLG mechanics, and constraint analysis for compounding acquisition.
  • legal-advisor - Spot legal-risk areas in product behavior and policy-sensitive flows.
  • license-engineer - Software licensing architecture, dependency compliance, and liability strategy.
  • product-manager - Turn engineering and user context into product decisions.
  • project-manager - Plan milestones, dependencies, and delivery sequencing.
  • resume-refiner - Review and optimize resumes, CVs, and LinkedIn profiles for clarity, impact, and role alignment.
  • sales-engineer - Provide technically accurate customer-facing solution guidance.
  • scrum-master - Improve engineering process without adding unnecessary overhead.
  • technical-writer - Draft clear release notes, migration notes, and technical docs.
  • ux-researcher - Turn product feedback and UI issues into actionable changes.
  • wordpress-master - Handle WordPress themes, plugins, and site behavior.

Overview (`categories/09-meta-orchestration/README.md`)

09. Meta & Orchestration

Agents that help plan or coordinate multi-agent Codex workflows without inventing unsupported mechanics.

Included agents:

  • agent-installer - Help pick and install agents from this repository.
  • agent-organizer - Pick the right subagents and divide the work cleanly.
  • codebase-orchestrator - Repo-wide refactor governance with weighted risk, diff previews, and approval gates.
  • context-manager - Produce a compact project context packet for other agents.
  • error-coordinator - Group and prioritize multiple error threads.
  • it-ops-orchestrator - Coordinate cross-domain IT and operations workflows.
  • knowledge-synthesizer - Merge findings from multiple agents into a usable summary.
  • multi-agent-coordinator - Design explicit multi-agent task plans.
  • performance-monitor - Turn performance signals into actionable summaries.
  • task-distributor - Break broad work into concrete delegated tasks.
  • workflow-orchestrator - Design explicit delegation flows for larger tasks.

Overview (`categories/10-research-analysis/README.md`)

10. Research & Analysis

Read-heavy research agents for searching, validating, comparing, and synthesizing information.

Included agents:

  • ab-test-analysis - Interpret A/B test results and make principled ship/no-ship decisions.
  • cohort-analysis - Diagnose retention curves, cohort behavior, and activation metrics.
  • competitive-analyst - Compare products, tools, or implementation approaches.
  • data-researcher - Gather and synthesize evidence around datasets and metrics.
  • docs-researcher - Verify APIs and behavior from documentation sources.
  • first-principles-thinking - Challenge assumptions and rebuild solutions from fundamentals.
  • market-researcher - Study the market landscape around a technical product or category.
  • project-idea-validator - Pressure-test ideas with brutal honesty, competitor teardown, and go/no-go verdict.
  • research-analyst - Investigate a technical topic and return a structured summary.
  • scientific-literature-researcher - Evidence-grounded synthesis of published research with quality weighting.
  • search-specialist - Search the codebase or external sources efficiently and report only the signal.
  • trend-analyst - Distill technology and adoption trends into practical implications.

Overview (`categories/11-ai-governance-safety/README.md`)

11. AI Governance & Safety

Agents for AI risk management, guardrails, policy alignment, and trustworthy deployment reviews.

Included agents:

  • ai-governance-auditor - Review AI systems against governance, controls, and accountability requirements.
  • model-risk-manager - Assess model risk, failure impact, and mitigation planning.
  • policy-guardrail-designer - Design practical prompt, tool, and policy guardrails.
  • responsible-ai-reviewer - Review fairness, misuse, transparency, and human-oversight concerns.

Overview (`categories/12-platform-engineering-idp/README.md`)

12. Platform Engineering & IDP

Agents for internal developer platforms, golden paths, platform product strategy, and self-service delivery design.

Included agents:

  • backstage-specialist - Design or review Backstage-based internal developer platform workflows.
  • golden-path-designer - Define opinionated developer paths that are safe, scalable, and easy to adopt.
  • idp-architect - Design internal developer platform architecture and service boundaries.
  • platform-product-manager - Shape platform roadmaps, adoption strategy, and platform-user value.

Overview (`categories/13-llmops-evals-observability/README.md`)

13. LLMOps, Evals & Observability

Agents for operating AI systems in production, including evaluations, regressions, traces, and runtime quality monitoring.

Included agents:

  • ai-observability-engineer - Design traces, metrics, and logging for production AI systems.
  • eval-engineer - Build or review evaluation strategy for prompts, tools, and agent workflows.
  • hallucination-investigator - Diagnose factuality failures and context-quality breakdowns in AI outputs.
  • prompt-regression-tester - Design regression suites for prompt and workflow changes.

--- METRICS ---

Explore Related Technologies & Topics

View All 9,111+ Repositories →

Discover similar high-velocity repositories, agent skills, and OpenAPI specifications across the ecosystem.

#ai-agents Browse ai-agents catalog → #awesome-list Browse awesome-list catalog → #chatgpt Browse chatgpt catalog → #codex Browse codex catalog → #codex-skills Browse codex-skills catalog → #codex-subagents Browse codex-subagents catalog → ⚡ MCP Servers Model Context Protocol → 🧠 Agent Skills Prompt & rule files → 🔌 OpenAPI Specs REST & Swagger schemas →