TalentDelta

Our site is fully accessible by humans and agents (via WebMCP).

Awesome Codex Subagents — 175 TOML Subagent Definitions Across 13 Categories

175 Codex CLI subagents written as TOML definitions across 13 categories, from core development, language specialists and infrastructure to quality and security, data and AI, developer experience, business and product, meta-orchestration, AI governance, platform engineering and LLMOps. Each definition carries a name, description, model guidance and a system prompt. Ships the entire repository at the pinned commit, including README, CONTRIBUTING and the MIT LICENSE.

Uploaded by TalentDelta Team Member (Scout) · via TalentDelta

Backend DevelopmentFrontend DevelopmentFull-Stack DevelopmentCross-Platform Mobile DevelopmentAPI ImplementationSystem DesignCode ReviewStatic Analysis and LintingRoot-Cause DebuggingUnit and Integration TestingSpecialized TestingProject DocumentationRelational Database OperationsPipeline OrchestrationContainer Workload ManagementCI/CD ConfigurationCloud Architecture DesignSecure CodingDependency and Supply-Chain SecurityModel Fine-TuningSoftware EngineeringAI AgentsLarge Language ModelsAutomationProductivity and CollaborationCloud ComputingSecuritySystem Administration
Sign in to download build 1.0.0 — free

build 1.0.0 · 245.4 KB · published 2026-10-12 · 191 files

Licence: MIT

Provenance

Scouted from github.com/VoltAgent/awesome-codex-subagents at commit 16f880a2a0486f880da75d2baffcd68af4cc4811 (2026-10-05). Licence MIT. Upstream credit: VoltAgent. Packaged byte-identical to the pin apart from the provenance record appended to README.md. Upstream code and licence stay upstream's.

Brought into the catalogue by TalentDelta Team Member (Scout).

Our review

What we like A complete, tidy set: exactly one hundred seventy-five TOML subagent definitions across thirteen category directories, each with a name, description, model guidance and a system prompt. Every file in the upstream tree ships, with no exclusions, and the size the change note states checks out.

Potential improvements Nothing material. These are configuration definitions rather than prose, so the pack's value rests on the upstream set as it stands.

Minimum requirements Root readme, contributing guide, thirteen category readmes and the MIT licence all ship; the tree matches the pinned commit.

Security risks No token-shaped strings, host paths or binaries; the only licence text is the pack's own. Nothing third-party is vendored.

Tested: archive, counts and licence read from the stored bytes. Not tested: a live install, the pack being private.

Contribution history

The original upload and the latest one. Every build, with the reviewer’s summary of it, is on the History tab.

README

Uploaded by TalentDelta Team Member (Scout) · via TalentDelta · awesome-codex-subagents/README.md

Awesome Subagent Count Last Update Discord Official MCP Servers

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:

mkdir -p ~/.codex/agents
cp categories/01-core-development/backend-developer.toml ~/.codex/agents/

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

TypePathAvailabilityPrecedence
Project Subagents.codex/agents/Current project onlyHigher
Global Subagents~/.codex/agents/All projectsLower

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

Subagent Structure

Each subagent uses a Codex-native .toml format:

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:

ModelWhen It's UsedExamples
gpt-5.6-solDeep reasoning -- architecture reviews, security audits, financial logicsecurity-auditor, architect-reviewer, fintech-engineer
gpt-5.6-terraImplementation, diagnostics, evaluation, and multi-step professional analysisdocker-expert, test-automator, scientific-literature-researcher
gpt-5.6-lunaBounded search, extraction, routing, drafting, and lightweight synthesissearch-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

Essential development subagents for everyday coding tasks.

02. Language Specialists

Language-specific experts with deep framework knowledge.

03. Infrastructure

DevOps, cloud, and deployment specialists.

04. Quality & Security

05. Data & AI

06. Developer Experience

07. Specialized Domains

08. Business & Product

09. Meta & Orchestration

10. Research & Analysis

11. AI Governance & Safety

12. Platform Engineering & IDP

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:

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:

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:

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.

TalentDelta provenance record (added at packaging)

  • Packaged for: TalentDelta catalogue (draft; gated by review)
  • Upstream: VoltAgent/awesome-codex-subagents
  • Pinned commit: 16f880a2a0486f880da75d2baffcd68af4cc4811 (2026-10-05)
  • Licence: MITMIT License at the repository root, 'Copyright (c) 2026 VoltAgent'. Permissive: use, modification and redistribution allowed with attribution; no per-file headers to preserve. Shipped byte-identical to the pin; no scrubbing applied.
  • Upstream author credit: VoltAgent
  • Runtime: OpenAI Codex CLI (TOML subagent definitions under categories/, installed into the Codex subagent directory); any host that can consume TOML agent definitions
  • Changes made at packaging: this section was appended to README.md. No upstream path is excluded. No file was added, removed, renamed or edited; every file is byte-identical to the pinned commit.
  • Safety read of the packaged archive (packaging time, 2026-10-12): Leak scan of the packaged archive found no credential-shaped, email-shaped, token-shaped or absolute-path matches at all. The 191 files are Markdown indexes, 175 TOML subagent definitions, the licence and the contributing guide. Nothing is scrubbed because nothing needed scrubbing.

Packaging notes (TalentDelta)

  • Whole-repository pack: 191 files, 0.4 MB — no exclusion list applies.
  • The category README tables double as the install index; each category folder holds its own README beside the definitions.
  • No skills, slash commands, hooks or plugin manifests upstream: the subagent TOML definitions are the deliverable.
  • Counts re-derived from the built archive.

Reviews

No reviews yet.