robots.txt
# Codex Workshop - agent and search crawler policy (RFC 9309)
# Public marketing pages are allowed for search indexing and AI input.
# Admin, API, and redirect paths stay disallowed.
# Content-Signal declares search/ai-input/ai-train preferences per group.
User-agent: GPTBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /r/
User-agent: OAI-SearchBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /r/
User-agent: ChatGPT-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /r/
User-agent: ClaudeBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /r/
User-agent: anthropic-ai
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /r/
User-agent: PerplexityBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /r/
User-agent: Google-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /r/
User-agent: Applebot-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /r/
User-agent: Bytespider
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /r/
User-agent: CCBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /r/
User-agent: Amazonbot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /r/
User-agent: meta-externalagent
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /r/
User-agent: FacebookBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /r/
User-agent: cohere-ai
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /r/
User-agent: Diffbot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /r/
User-agent: Omgilibot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /r/
User-agent: YouBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /r/
User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /r/
Host: www.codexworkshop.com
Sitemap: https://www.codexworkshop.com/sitemap.xml
llms.txt
# Codex Workshop
> Official Codex ambassadors delivering hands-on workshops and AI coding training for engineering teams.
## Services
- Team Codex CLI Workshops: Hands-on workshops teaching teams to use Codex CLI safely and effectively
- AI Coding Review Training: Best practices for code review habits with AI assistance
- Agent Workflow Setup: Shared agent workflows for team adoption
## Docs
- [Homepage](https://www.codexworkshop.com)
- [Training](https://www.codexworkshop.com/training)
- [Training topics](https://www.codexworkshop.com/topics)
- [Services](https://www.codexworkshop.com/services)
- [Pricing](https://www.harness.institute/pricing)
- [Methodology](https://www.codexworkshop.com/methodology)
- [About](https://www.codexworkshop.com/about)
- [Research index](https://www.codexworkshop.com/research)
- [Book a 15-minute sync](https://www.harness.institute/call)
- [Sitemap](https://www.codexworkshop.com/sitemap.xml)
- [Research feed](https://www.codexworkshop.com/feed.xml)
## Topic Guides
- [Codex agents: AGENTS.md, skills, team use](https://www.codexworkshop.com/topics/subagents-and-skills): Adding more subagents rarely speeds a team up; runs get abandoned and review piles up when nobody owns the result. Effective subagents delegation starts with agent boundaries: which tasks delegate safely, and which instructions, MCP, and skills control each run. This guide covers AI team skills and team AI workflows, plus the skill integration that lets engineers inspect and improve delegated work.
- [Codex team conventions for engineering orgs](https://www.codexworkshop.com/topics/team-conventions): Inconsistent usage across engineers, not tool access, is what slows AI coding adoption on real teams. Shared team conventions cut that variability: repository instructions everyone follows, code review standards that set clear thresholds, and AI coding standards reinforced by examples from your own codebase. Teams then compare outcomes against a baseline instead of trading anecdotes about which prompt worked.
- [Codex workflows: CLI, MCP, and review](https://www.codexworkshop.com/topics/cli-workflows): OpenAI Codex CLI workflows work for engineering teams when every run has a task brief, repository instructions, bounded permissions, verification loops, and a reviewable diff. This page explains how teams adopt Codex CLI without turning agent speed into review debt.
- [Codex MCP servers: which to add first and the team rules to set](https://www.codexworkshop.com/topics/mcp-team-skills): Codex CLI reads MCP servers from config.toml, supports per-tool approval modes, and can allowlist or block individual tools. This page lists the servers worth adding first, the ones to hold back, and the team rules that keep every MCP call reviewable.
- [Agentic coding workshops for engineering teams](https://www.codexworkshop.com/topics/agentic-coding-workshops): Most teams adopt AI coding tools individually and never build a shared way of working, so output stays inconsistent. This agentic coding workshop trains engineers as a team on real repositories, not demos. You leave with a tested AI coding workflow, clear rules for using coding agents, and a team adoption plan that survives past the first week.
- [Safe AI coding practices for development teams](https://www.codexworkshop.com/topics/safe-ai-coding-practices): Train a development team to adopt safer AI coding practices by making the workflow concrete: bounded scopes, approved context, verification habits, and review gates before merge. AI coding safety holds when the model knows when it can implement, advise, or hand the call to an engineer, and when reviewers can see the evidence behind every AI-assisted change.
- [AI code review habits for generated code](https://www.codexworkshop.com/topics/ai-code-review-habits): The best way to implement code review habits for AI-generated code is to review the task brief, diff shape, test evidence, and ownership boundary before merge. AI-generated code can pass tests and read cleanly while hiding context mistakes, weak coverage, or risky abstractions, so reviewers need a repeatable AI code critique workflow rather than a rubber stamp.
- [How can platform and infrastructure teams use shared OpenAI Codex agent workflows?](https://www.codexworkshop.com/topics/shared-agent-workflows): Codex Workshop teaches platform and infrastructure teams to share OpenAI Codex agent workflows by publishing one repository standard, one MCP allowlist, and one CI evidence bar. Product, SRE, and platform engineers then run the same delegation and review loop instead of twelve private prompt habits.
- [UK AI coding workshops for engineering teams](https://www.codexworkshop.com/topics/uk-ai-coding-workshops): Teams that book a generic AI talk rarely change how anyone ships code. This hands-on training runs remotely or onsite for UK and European engineering teams that want practical AI coding adoption, not theory. Exercises follow your real workflow: planning, implementation, code review of AI-generated changes, testing, and documentation, so habits stick after the day ends.
- [What should a two-day OpenAI Codex curriculum for senior engineers cover?](https://www.harness.institute/training): Codex Workshop two-day OpenAI Codex curriculum for senior engineers covers Delegate, Review, Own, repo context, large or legacy codebases, debug and verification, AI-assisted review, and org standards across Day 1 and Day 2. This is independent team training from Harness Institute, not an official vendor workshop. The default shape is two days, onsite or offsite. Intermediate cohorts are usually 12-35 people. Mastery cohorts are usually 8-24.
- [How much does instructor-led OpenAI Codex training cost for 10 to 20 engineers?](https://www.harness.institute/pricing): Codex Workshop prices instructor-led OpenAI Codex training at USD 1,000 per person per day. Two days for 10 to 20 engineers is USD 20,000 to USD 40,000 before VAT, including the first month of Harness Pulse.
- [What ROI should an engineering team expect from OpenAI Codex training?](https://www.harness.institute/pricing): Codex Workshop measures OpenAI Codex training ROI as review time, escaped defects, cycle time, and the share of AI-assisted work that ships with explicit verification. We do not publish a 20 to 40 percent productivity number. Those proxies are the ones we already teach teams to measure.
- [How should an engineering manager roll out OpenAI Codex across a development team?](https://www.harness.institute/training): Codex Workshop teaches an engineering manager to roll out OpenAI Codex with Delegate, Review, Own, a small champion group, and a 30/60/90 plan. The first 90 days prove one workflow on real pull requests before the rest of the team copies it. Large-rollout cohorts stay at 30-35 engineers.
- [Codex CLI training for software teams](https://www.codexworkshop.com/topics/codex-cli-training): Codex CLI training for engineering teams turns OpenAI Codex from an individual tool into a shared delivery workflow. Teams practice install and update habits, AGENTS.md instructions, bounded tasks, scoped permission profiles, and verification loops that produce reviewable diffs. The goal is practical Codex adoption inside production codebases, so output ships instead of stalling in review.
- [Codex MCP training for engineering teams](https://www.codexworkshop.com/topics/codex-mcp-training): Connecting Codex to your repository, docs, and APIs through MCP servers opens real security gaps when no team rules exist. This training covers model context protocol configuration, permission profiles that scope what each MCP server can read or write, allowed workflows, failure handling, and the evidence engineers must attach before any merge. Teams leave able to govern Codex MCP usage safely.
- [OpenAI Codex team training and workshop](https://www.codexworkshop.com/topics/openai-codex-training-engineering-teams): OpenAI Codex training for engineering teams gives teams a practical answer to how Codex CLI should be adopted: which work the agent owns, which evidence reviewers expect, and which tasks stay human-led. The workshop sets shared standards for prompting, AGENTS.md, MCP, verification, and review so Codex adoption becomes predictable across the whole team.
- [Codex code review training for engineering teams](https://www.codexworkshop.com/topics/codex-code-review-training): Codex moves through planning, edits, and tests faster than any reviewer can read line by line, so teams accept work they never inspected. This Codex code review training gives engineers a repeatable code review workflow: read the task, the diff, and the verification evidence, then flag risk before merge. Shared review standards and review habits keep agent-generated code safe.
- [Codex workshop AI coding standards](https://www.codexworkshop.com/topics/codex-workshop-ai-coding-standards): Written AI coding standards get ignored the moment they live in a wiki nobody opens. Codex standards stick when they become repository instructions the model reads on every task: scoped task boundaries, required reviews, and verification evidence attached to each pull request. This guide shows the rollout that turns team policy into AI coding standards engineers actually follow.
- [Codex best practices training for engineering teams](https://www.codexworkshop.com/topics/codex-best-practices-training): Without shared standards, every engineer builds a private operating model and code review stalls reconciling clashing habits. Codex best practices stick only when they are documented as team standards: an AGENTS.md that fixes prompt engineering patterns, allowed tool boundaries, task briefs, and verification expectations. Writing these workflow practices down turns scattered individual prompting into one repeatable way the whole team ships.
- [Codex versus Claude Code for engineering teams](https://www.codexworkshop.com/topics/codex-vs-claude-code-for-teams): Picking between Codex and Claude Code rarely comes down to raw model quality. The real split is how each fits your team's workflow: how engineers frame tasks, hand off context, run CLI work, wire up MCP integration, and review diffs before merge. This tool comparison helps you match each to an honest adoption strategy and decide which workflows are safe to delegate.
- [Hands-on OpenAI Codex workshops for teams](https://www.codexworkshop.com/topics/hands-on-openai-codex-workshops-for-teams): Most Codex training stops at scripted demos, so engineers never practice the work that matters. This hands-on Codex workshop puts teams inside real production codebases, where they run planning, bounded implementation, test repair, and review loops on actual tasks. Practical training built around production workflows means a team workshop your engineers can apply the next morning.
- [Codex Workshop versus AI coding training providers](https://www.codexworkshop.com/topics/codex-workshop-vs-ai-coding-training-providers): Most AI coding training stops at tool features and prompt tips, so habits never reach the codebase. This Codex Workshop comparison shows the difference: practical training built on team standards you can audit. Teams leave with repository instructions, bounded delegation, reviewable diffs, and test evidence. Use this provider comparison when generic courses leave your engineers without shared working rules.
## Research
- [Install Codex CLI for Team Workflows](https://www.codexworkshop.com/research/install-codex-cli-for-team-workflows): Install Codex CLI as a team workflow with AGENTS.md, MCP boundaries, and a verification loop developers can reuse.
- [Run Codex Agents With Team Guardrails](https://www.codexworkshop.com/research/run-codex-agents-with-team-guardrails): Set a Codex agent convention with AGENTS.md, MCP boundaries, and verification loops your team can review.
- [Codex CLI Workflows for Engineering Teams](https://www.codexworkshop.com/research/codex-cli-workflows-for-engineering-teams): Set up Codex CLI workflows with AGENTS.md, MCP boundaries, and a verification loop your team can reuse.
- [Codex CLI Tool for Team Workflows](https://www.codexworkshop.com/research/codex-cli-tool-for-team-workflows): Set up Codex CLI workflows with AGENTS.md, MCP limits, and verification loops your team can review.
- [OpenAI Codex CLI Team Workflow](https://www.codexworkshop.com/research/openai-codex-cli-team-workflow): Turn Codex CLI docs into a team workflow with AGENTS.md rules, MCP boundaries, and verification loops.
- [Codex CLI with GitHub Repos](https://www.codexworkshop.com/research/codex-cli-with-github-repos): Use Codex CLI with GitHub repos through scoped AGENTS.md rules, narrow MCP access, and a repeatable verification loop.
- [Add MCP to Codex CLI Workflows](https://www.codexworkshop.com/research/add-mcp-to-codex-cli-workflows): Learn how to add MCP to Codex CLI with AGENTS.md boundaries, read-only access, and a verification loop.
- [Codex CLI Workflows from GitHub](https://www.codexworkshop.com/research/codex-cli-workflows-from-github): Use Codex CLI with GitHub, AGENTS.md, MCP, and verification loops without turning repo automation into guesswork.
- [Agents API computer use: build a browser agent step by step](https://www.codexworkshop.com/research/agents-api-computer-use-browser-agent): Build a first browser agent with OpenAI Agents API computer use: create the session, approve website origins, send a task, handle sign-in safely, and clean up.
- [Bedrock Managed Agents OpenAI vs the Agents API](https://www.codexworkshop.com/research/bedrock-managed-agents-openai-vs-agents-api): Compare Bedrock Managed Agents, powered by OpenAI, with the OpenAI Agents API: endpoints, auth, execution environments, and where Codex fits on AWS.
- [Build a ChatGPT plugin extension: sidebar, panels and file viewers](https://www.codexworkshop.com/research/build-chatgpt-plugin-extension): A hands-on guide to OpenAI MCP Extensions: add a sidebar app, a conversation panel or a file viewer to your plugin, then test it in ChatGPT and Codex.
- [ChatGPT collaborative slides for sprint and incident reviews](https://www.codexworkshop.com/research/chatgpt-collaborative-slides-sprint-incident-review): What OpenAI announced for ChatGPT collaborative slides, what is still undocumented, and how Codex teams can prepare sprint and incident review material now.
- [ChatGPT in Slack: turn a bug thread into a pull request](https://www.codexworkshop.com/research/chatgpt-in-slack-bug-thread-to-pull-request): A step-by-step path from a bug report in a Slack thread to a Codex Cloud task and a reviewed pull request, using the new @ChatGPT app.
- [ChatGPT Meetings plugin: from design review to Codex tasks](https://www.codexworkshop.com/research/chatgpt-meetings-plugin-design-review-to-codex-tasks): How to capture a technical design meeting with the ChatGPT Meetings plugin on macOS and turn its action items into scoped Codex tasks and a decision record.
- [ChatGPT Pages: build a self-updating engineering status page](https://www.codexworkshop.com/research/chatgpt-pages-engineering-status-page): A hands-on build of a release notes and blockers page in ChatGPT Pages, kept current with a scheduled task that Codex users can prepare and test.
- [ChatGPT Plugin Creator: from idea to a submitted plugin](https://www.codexworkshop.com/research/chatgpt-plugin-creator-submit-plugin): Use Plugin Creator in ChatGPT Work or Codex to scaffold a plugin, test it locally, then upload, pass review and publish it in the shared directory.
- [ChatGPT Pro 500 for Codex: Pro 100, 200 and 500 compared](https://www.codexworkshop.com/research/chatgpt-pro-500-codex-plan-comparison): Compare the three ChatGPT Pro tiers for Codex work: price, Ultrafast access, how credits behave, and what changes for Pro 200 subscribers after 29 October 2026.
- [ChatGPT shareable profiles: Codex usage, Sites and skills](https://www.codexworkshop.com/research/chatgpt-shareable-profiles-codex-usage-sites-skills): What the new ChatGPT profile shows about your Work and Codex token usage, how to put Sites built from a Codex project on it, and how skill sharing works.
- [ChatGPT Sites plugins: deploy a Codex project with live data](https://www.codexworkshop.com/research/chatgpt-sites-plugins-deploy-codex-project): How to turn a Codex project into a ChatGPT Site, let a workspace plugin show each visitor their own data, and which plans can use it today.
- [ChatGPT Space for Codex users: setup, sharing and context](https://www.codexworkshop.com/research/chatgpt-space-shared-context-for-codex): How developers set up ChatGPT Space as shared engineering context next to Codex: spaces, pages, access levels, and what changed from Library.
- [ChatGPT team tasks for a weekly engineering update](https://www.codexworkshop.com/research/chatgpt-team-tasks-weekly-engineering-update): Set up a ChatGPT team task that writes a Monday engineering update from GitHub, plus a triage task that runs on pull request events.
- [Codex CLI Update: Voice, the /agents View, Resume and Worktrees](https://www.codexworkshop.com/research/codex-cli-update-voice-agents-worktrees): A hands-on guide to the refreshed Codex CLI: talk to Codex with voice, track parallel work in the agents view, edit earlier prompts, resume sessions, and use worktrees.
- [Codex Cloud Setup: Reusable Environments and Cloud Tasks](https://www.codexworkshop.com/research/codex-cloud-environments-setup-guide): A step-by-step Codex Cloud guide: create and publish a reusable environment, start and follow cloud tasks, and decide when local work is the better fit.
- [Codex Code Review in the ChatGPT Desktop App: Setup and Use](https://www.codexworkshop.com/research/codex-code-review-desktop-app-setup): Step-by-step setup for Codex Code Review: open pull requests in the ChatGPT desktop app, ask Codex about risks, send feedback to GitHub, and turn on automatic cloud reviews.
- [Codex Security Cloud setup: connect GitHub and run a first scan](https://www.codexworkshop.com/research/codex-security-cloud-setup-first-scan): A step-by-step Codex Security Cloud setup guide: install the plugin, connect GitHub, pick a Cloud environment, review a validated finding, and monitor commits.
- [GPT-6.1 Sol pricing, model id, and Sol vs Astra in Codex](https://www.codexworkshop.com/research/gpt-6-1-sol-pricing-and-sol-vs-astra-in-codex): GPT-6.1 Sol costs $2 per million input tokens and $10 per million output tokens. Here is the model id, the benchmark picture, and how to choose Sol or Astra in Codex.
- [MCP Events: build an event-emitting MCP server for ChatGPT](https://www.codexworkshop.com/research/mcp-events-build-event-server-for-chatgpt): A developer guide to the MCP Events methods ChatGPT supports, from events/list to signed webhook delivery, with a Codex workflow to build and test it.
- [OpenAI Decisions API: where Luna fits in an agent pipeline](https://www.codexworkshop.com/research/openai-decisions-api-luna-agent-routing): What the OpenAI Decisions API does, what is still undocumented in the limited preview, and how to map the routing and triage calls in your agent code with Codex.
- [OpenAI dots for developers: bug reports to tested PRs](https://www.codexworkshop.com/research/openai-dots-for-developers-bug-reports-to-prs): A hands-on guide to ChatGPT dots for developer work: turning Slack bug reports and user feedback into tested pull requests through Codex, with the controls to set first.
- [OpenAI Marketplace partners for engineering teams](https://www.codexworkshop.com/research/openai-marketplace-developer-tools-partners): Which developer tools sit in the first OpenAI Marketplace partner list, what committed spend means for engineers, and how to test Codex review against them first.
- [OpenAI Private Intelligence: set up Private Safety Processing](https://www.codexworkshop.com/research/openai-private-intelligence-private-safety-processing): How Zero Data Retention with Private Sa
