AI-Assisted Coding·8 min read
Codex Opens Its Agent Harness
OpenAI’s Codex platform release explains the open agent harness and how to test it safely in one repo.
August 25, 2026·Rogier Muller
Codex CLI guides: AGENTS.md and review
Practical Codex CLI guides for AGENTS.md, MCP permissions, auto-review, verification evidence, and production workflows.
Start with Codex CLI training, OpenAI Codex for teams, and Codex CLI workflows.
Want to apply these guides with your team? Explore Codex CLI training.
Open Source·8 min read
Sloppie Is a Linux Agentic Coding Environment
Sloppie is a Linux development environment that turns coding-agent work into review comments, diffs, and terminals.
August 25, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Hands Lets MCP Click Real Chrome
Hands shows a Windows MCP path where Codex can observe, click, and type in a real Chrome profile safely.
August 24, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Simon Willison on Coding Agent Review
Simon Willison argues that coding agent review is really about proving changes, not reading every generated line.
August 24, 2026·Rogier Muller
AI-Assisted Coding·10 min read
A Week Choosing Codex Over Claude
A developer’s week with Codex over Claude turned into a sharper question: which agent makes smaller, faster patches?
August 23, 2026·Rogier Muller
Open Source·7 min read
fx Is a Tiny Native Coding Agent
fx is a tiny native coding agent from Vercel Labs. Learn why its small shape matters and how to test it safely.
August 23, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Codex CLI 0.149.0 Adds Agent Dashboard
OpenAI Codex CLI 0.149.0 adds an agent dashboard, queue commands, better doctor checks, and safer session restores.
August 22, 2026·Rogier Muller
AI-Assisted Coding·10 min read
Show HN: Frugal Tokens Shows Agent Costs
Frugal Tokens explores coding-agent session costs, cache misses, and usage patterns so developers can inspect spend before changing workflows.
August 22, 2026·Rogier Muller
Open Source·9 min read
Codex on AWS Bedrock 10x Charges
A Codex CLI issue on Amazon Bedrock showed expensive cache writes. Learn what happened and the safe checks to run first.
August 21, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Speko Launches Voice AI Router
Speko routes voice AI stacks across STT, LLM, and TTS choices, with a useful lesson for coding-agent evals.
August 21, 2026·Rogier Muller
Open Source·8 min read
neal Runs Claude and Codex Together
neal shows how Claude and Codex can split planner, coder, and reviewer roles in a local repo workflow.
August 16, 2026·Rogier Muller
Open Source·9 min read
Show HN: Remarc Feedback via MCP
Remarc captures comments on text, screenshots, web elements, and voice so coding agents can resolve them through MCP.
August 16, 2026·Rogier Muller
Methodology·3 min read
Running an agent team in Codex without chaos
How to run an agent team on Codex: splitting work so parallel agents do not collide, giving each one a verifiable exit, and knowing when one agent is better.
August 15, 2026·Rogier Muller
Methodology·3 min read
Agent teams in Codex and when the extra agents pay off
Running agent teams in Codex helps on tasks that split cleanly and hurts on everything else. Here is how to tell the difference.
August 15, 2026·Rogier Muller
Methodology·3 min read
How agents in Codex actually decide what to do
A plain explanation of how agents in Codex read a repo, pick tools, and recover from failure, plus the three habits that make them useful.
August 15, 2026·Rogier Muller
Methodology·3 min read
AI code review tools with team governance and policies
What to check before buying AI code review tools with team-based governance and policies, and which controls actually change behaviour.
August 15, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Artifex Gives Agents a Media Graph
Artifex is a headless CLI runtime for agent-built media graphs, with practical checks for trying it safely in Codex workflows.
August 15, 2026·Rogier Muller
Methodology·3 min read
Autoreview in Codex and how teams get value from it
Autoreview in Codex catches a narrow class of bugs well. Here is where it helps, where it wastes time, and how to tune it.
August 15, 2026·Rogier Muller
Open Source·8 min read
cliclaw Runs Coding CLIs From Telegram
cliclaw is a Telegram-controlled macOS daemon for local coding CLIs, with safety checks that make it worth trying.
August 15, 2026·Rogier Muller
Methodology·3 min read
Designing a Codex agent team for one feature
A worked example of splitting a single feature across a Codex agent team, including the handoff format and the parts you should keep for yourself.
August 15, 2026·Rogier Muller
Methodology·3 min read
Codex agent teams and the review bottleneck
Codex agent teams sound like parallel throughput. In practice the limit is human review. How to structure the work so the parallelism actually pays.
August 15, 2026·Rogier Muller
Methodology·3 min read
Standardising Codex agents across an engineering team
Rolling out Codex agents to a team: shared repo context, an agreed review policy, sane sandbox defaults, and the metrics that tell you it is working.
August 15, 2026·Rogier Muller
Methodology·4 min read
Codex agents, and when they stop helping
How Codex agents behave on real repositories, what AGENTS.md should contain, and the point at which adding more agents makes the work slower.
August 15, 2026·Rogier Muller
Methodology·3 min read
Codex AI training that changes what a team merges
What Codex AI training should cover for a working engineering team, how to structure it, and the measures that show whether it worked.
August 15, 2026·Rogier Muller
Methodology·3 min read
The codex-auto-review model and why it appears
Why the codex-auto-review model label shows up in your logs and PR comments, what it tells you, and how to reason about review quality without it.
August 15, 2026·Rogier Muller
Methodology·4 min read
What Codex auto review actually catches
Codex auto review reads your diff and comments before a human does. Here is what it catches, what it misses, and how to wire it into a real team.
August 15, 2026·Rogier Muller
Methodology·3 min read
Codex autoreview settings worth changing
Codex autoreview defaults are fine for a demo and noisy for a real team. The settings and repo rules that make the comments worth reading.
August 15, 2026·Rogier Muller
Methodology·3 min read
What a Codex bootcamp should cover, and what to skip
What a codex bootcamp needs to teach engineers in two days, which exercises work, and the parts that waste everyone's time.
August 15, 2026·Rogier Muller
Methodology·3 min read
Codex CLI auto-review and what it catches
How Codex CLI auto-review behaves on a real diff, the bug classes it reliably finds, and the ones it will walk straight past.
August 15, 2026·Rogier Muller
Methodology·4 min read
Setting up Codex CLI MCP without regret
Codex CLI MCP support means the agent can call tools provided by an external process: a database client, a docs index, an issue tracker, a browser.
August 15, 2026·Rogier Muller
Methodology·3 min read
A Codex CLI workflow that holds up on a Tuesday
The Codex CLI workflow we teach engineering teams: plan in read-only, execute in a worktree, verify with one command, and keep sessions short.
August 15, 2026·Rogier Muller
Methodology·3 min read
Codex cls, and why clearing context is a real skill
People search codex cls looking for a clear command. The useful answer is about when to clear context in a Codex session, and why it matters.
August 15, 2026·Rogier Muller
Methodology·3 min read
What a Codex course should teach your engineers
How to judge a Codex course before you buy one, what a good syllabus contains, and when a team is better off skipping training entirely.
August 15, 2026·Rogier Muller
Methodology·3 min read
How to pick between Codex courses for a working team
Most Codex courses teach the interface. Here is how to tell which ones change how a team actually ships, and what to ask before you buy.
August 15, 2026·Rogier Muller
Methodology·3 min read
Codex delegate patterns that survive a real codebase
How to Codex delegate a task properly: scoping the handoff, writing the acceptance check first, and picking the sandbox mode that matches the risk.
August 15, 2026·Rogier Muller
Methodology·4 min read
Codex GitHub reviews without the noise
Codex GitHub integration puts an agent inside your pull requests. What to hand it, what to keep on your laptop, and how to stop the comment flood.
August 15, 2026·Rogier Muller
Methodology·4 min read
Codex MCP servers, and when they are worth the tokens
A practical guide to Codex MCP setup: what to connect, what to leave out, and the failure modes that cost teams a whole context window.
August 15, 2026·Rogier Muller
Methodology·3 min read
Choosing between Codex models on real work
Codex models differ in speed, cost, and how long they hold a plan. How to pick one per task instead of picking once.
August 15, 2026·Rogier Muller
Methodology·3 min read
Codex opt out of training, and what to verify
We are deliberately not quoting exact menu paths or policy clauses here, because these change and a stale instruction is worse than none.
August 15, 2026·Rogier Muller
Methodology·3 min read
Setting a codex SLI your team will actually watch
A codex SLI turns vague agent adoption talk into a number. Which indicators are worth tracking, which are vanity, and how to instrument them.
August 15, 2026·Rogier Muller
Methodology·3 min read
When Codex sub agents help and when they hurt
Codex sub agents split a task across separate contexts. Useful for parallel search, risky for anything that needs shared state.
August 15, 2026·Rogier Muller
Methodology·3 min read
Codex subagents and skills, honestly compared
What people mean by Codex subagents and skills, what the tool actually gives you today, and how to get the same effect with prompts and scoped runs.
August 15, 2026·Rogier Muller
Methodology·3 min read
Codex subagents: what they buy you
Codex subagents split work into fresh contexts. Here is when that helps, when it costs you, and how to structure a delegation that returns something usable.
August 15, 2026·Rogier Muller
Methodology·3 min read
Setting up one Codex team agent everyone shares
A shared Codex team agent gives you one identity, one config, and an audit trail. Here is how to set it up and what it should never be allowed to do.
August 15, 2026·Rogier Muller
Methodology·3 min read
Running Codex team agents without stepping on each other
Codex team agents work when the shared rules live in the repo and the work is split by boundary. Here is the setup we teach and the failures we see.
August 15, 2026·Rogier Muller
Methodology·3 min read
What codex team mode actually means for a shared repo
Codex team mode is mostly convention, not a setting. What shared config, review rules, and task ownership look like when a whole team runs Codex.
August 15, 2026·Rogier Muller
Methodology·3 min read
Running a Codex team of agents without a mess
When a Codex team of agents beats a single session, how to keep parallel work from colliding, and the point where it stops paying off.
August 15, 2026·Rogier Muller
Methodology·3 min read
Running Codex across a team without chaos
A Codex team needs shared config, shared review habits, and one owner. Here is the setup that survives contact with a real backlog.
August 15, 2026·Rogier Muller
Methodology·3 min read
Rolling out Codex to teams without losing the review gate
How Codex teams share configuration, keep review honest, and avoid the two rollout patterns that quietly waste a quarter.
August 15, 2026·Rogier Muller
Methodology·3 min read
Codex training that survives contact with your repo
Most Codex training teaches the interface. What teams need is the operating discipline.
August 15, 2026·Rogier Muller
Methodology·3 min read
Codex vs Claude Code, from teams running both
Codex vs Claude Code without the benchmark theatre. Where each one wins in day-to-day work, and why most teams end up keeping both installed.
August 15, 2026·Rogier Muller
Methodology·3 min read
How Codex works, and where it stops working
A practitioner view of how Codex work gets done: the read-plan-edit-verify loop, what the sandbox allows, and the tasks where it reliably falls over.
August 15, 2026·Rogier Muller
Methodology·3 min read
A Codex workflow that survives contact with a real repo
The Codex workflow we teach: shape the task, plan, small diff, verify, commit. Plus the three points where teams reliably lose time.
August 15, 2026·Rogier Muller
Methodology·3 min read
Four Codex workflows that hold up under load
Most Codex workflows fall apart on real code. These four survive, and each one has a clear failure mode you should know.
August 15, 2026·Rogier Muller
Methodology·3 min read
Codex xli is nearly always a typo for Codex CLI
Searching codex xli usually means you wanted the Codex CLI. Here is what the terminal agent does, how to run it, and where teams get stuck.
August 15, 2026·Rogier Muller
Methodology·3 min read
Onsite programming sessions that survive contact with agents
What an onsite programming day with AI coding agents should look like, who it works for, and where the format falls down.
August 15, 2026·Rogier Muller
Methodology·3 min read
What is codex-auto-review, in plain terms
A short answer to what is codex-auto-review, what shows up in your pull requests, and how much of it you should trust.
August 15, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Codex in ChatGPT Linux Preview
OpenAI’s Linux preview brings Codex into the ChatGPT desktop app, with a safe first repo workflow to try.
August 14, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Read it easy Is a Read-Only Code Editor
Read it easy is a read-only desktop code editor built for source reading. Here is why its Go to Definition idea matters.
August 14, 2026·Rogier Muller
AI-Assisted Coding·8 min read
FEDERaiDE Routes Agents in Your Terminal
FEDERaiDE is a terminal multi-agent harness with P2P routes, memories, and an IDE. Here is when to try it safely.
August 13, 2026·Rogier Muller
Open Source·9 min read
tmux-agent-switcher Watches Coding Agents
tmux-agent-switcher tracks AI coding agents in tmux so you can spot blocked Codex or Claude panes quickly.
August 13, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Hoplite Brings Coding Agents to Cloud
Hoplite (YC S26) moves local coding-agent setup into cloud sandboxes and raises the right questions about QA.
August 12, 2026·Rogier Muller
Open Source·10 min read
keen-code: A Go Coding Agent
keen-code is a Go terminal coding agent that shows what a small, opinionated agent harness can teach Codex users.
August 12, 2026·Rogier Muller
Open Source·8 min read
Airship Visually Edits Your Running App
Airship is a visual editor for running apps that lets Codex, Claude Code, or OpenCode change real source.
August 11, 2026·Rogier Muller
Open Source·11 min read
Ante Ships Offline Coding in One Binary
Ante packages an offline coding agent into one binary, with the review habits needed before trusting its diffs.
August 11, 2026·Rogier Muller
Open Source·9 min read
Qwen3.8-Max Local Coding via MCP
qwen3.8-max-local-coding connects Qwen Studio to local files through MCP, with a clear lesson on safe permissions.
August 9, 2026·Rogier Muller
Open Source·9 min read
Mirafold Wraps Coding Agents in Browser UI
Mirafold puts Codex, Claude Code, and Gemini CLI output in a browser UI without changing the agent underneath.
August 8, 2026·Rogier Muller
Open Source·9 min read
Aident Loadout Gives Codex Real App Actions
Aident Loadout packages a skill that lets coding agents use connected apps, with audit history and safer trials.
August 7, 2026·Rogier Muller
Open Source·10 min read
mcp-use v2 Gets a Stateless Rebuild
mcp-use v2 was rebuilt for stateless MCP, with faster launches, smaller installs, and sharper integration boundaries.
August 7, 2026·Rogier Muller
Open Source·9 min read
Frontrun Tests Python Races
Frontrun explores Python thread, async, and process interleavings so race conditions become reproducible.
August 6, 2026·Rogier Muller
AI-Assisted Coding·10 min read
Armature Instruments MCP Agent Sessions
Armature reconstructs MCP agent sessions so builders can see use cases, failures, and safer review boundaries.
August 4, 2026·Rogier Muller
Open Source·7 min read
Rudder Measures Your Input on AI Code
Rudder turns prompt history into tests so Codex users can see whether generated code reflects their intent.
August 4, 2026·Rogier Muller
Open Source·8 min read
Sprocket Lets an Agent Buy Parts
Sprocket is a Show HN agent for hardware, software, and web purchases. Here is what mattered and how to test it safely.
August 3, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Claude MIDI Twister Shows Agent State
Claude MIDI Twister turns a MIDI controller into a live status board for coding-agent sessions.
August 1, 2026·Rogier Muller
Open Source·9 min read
Agent-Manager Gives Codex a tmux Dashboard
Agent-Manager puts Claude Code, Codex, OpenCode, Grok Build, and Gemini CLI sessions into one tmux dashboard.
July 31, 2026·Rogier Muller
Open Source·9 min read
codex-security Tests the Repo Boundary
OpenAI’s codex-security scans code for vulnerabilities, but the real lesson is where to draw the repo boundary before agents fix code.
July 29, 2026·Rogier Muller
Open Source·9 min read
verified-3d-mesh-intersection Verifies 3D Mesh CSG
A Lean 4 mesh-intersection project shows why reviewers can trust a small spec, a checker, and sharp boundary tests.
July 29, 2026·Rogier Muller
Open Source·10 min read
FeyNoBg Ships Background Removal Library
Feyn released FeyNoBg and NoBg, showing how to test an AI image tool before wiring it into real repos.
July 28, 2026·Rogier Muller
Open Source·9 min read
Boffin Adds Per-Edit Agent Guardrails
Boffin routes file-specific constraints to coding agents, then asks them to verify the edit before it lands.
July 27, 2026·Rogier Muller
Open Source·8 min read
Termic Runs CLI Coding Agents
Termic is an open source desktop app for running CLI coding agents in checkouts and worktrees.
July 27, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Argus Manages VS Code Worktree Agents
Argus is a VS Code extension that manages parallel Codex and Claude Code worktree sessions in one window.
July 26, 2026·Rogier Muller
Open Source·9 min read
claude-code-survival-kr Guards Working Code
A Show HN repo turns vague AI coding advice into hard repo rules that keep agents from breaking stable code.
July 26, 2026·Rogier Muller
Open Source·10 min read
Show HN: WhipDesk Controls Dev Machines From Phones
WhipDesk is an open-source phone remote desktop for AI coding agents, with a safe Codex handoff checklist.
July 25, 2026·Rogier Muller
AI-Assisted Coding·10 min read
Echo Tests Cheaper Open-Weight Routing
Echo routes open-weight models per task, raising useful questions about evals, cost, and review habits for AI code.
July 24, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Code Review Habits for Coding Agents
Learn a practical team workflow for reviewing AI-generated code from Codex, Codex Agent, MCP boundaries, and PR checks.
July 23, 2026·Rogier Muller
Open Source·9 min read
Yorishiro Gives Coding Agents a Body
Yorishiro is a macOS terminal that gives coding agents a body, and shows why visible agent state matters.
July 23, 2026·Rogier Muller
Open Source·10 min read
CodeAlmanac Saves What Agent Chats Forget
CodeAlmanac turns coding-agent chats into a local wiki, so agents can reuse decisions, flows, and gotchas.
July 22, 2026·Rogier Muller
Open Source·9 min read
joydex Turns a Flight Throttle Into Codex Controls
Joydex maps flight-sim hardware to OpenAI Codex controls and shows when a physical agent interface is worth trying.
July 22, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Bloomy Tests AI Tutoring for K-12
Bloomy pairs an AI tutor with adaptive K-12 lessons, raising useful questions about trust, scope, and review.
July 21, 2026·Rogier Muller
AI-Assisted Coding·8 min read
claw-coder Takes Autonomous Coding Local
Gabriel Blessed’s claw-coder pitch makes local agent safety concrete, with a safe-first way to try it.
July 21, 2026·Rogier Muller
AI-Assisted Coding·10 min read
Codex and Codex Hit by Sandbox Escapes
Sandbox escapes in Codex, Codex, Gemini CLI, and Antigravity show why agent review needs a tighter repo boundary.
July 21, 2026·Rogier Muller
AI-Assisted Coding·7 min read
OpenAI Cuts Codex Context Window
OpenAI changed Codex CLI model metadata from 372k to 272k context, exposing a real workflow lesson.
July 21, 2026·Rogier Muller
Open Source·9 min read
Agent-talk Adds Agent-to-Agent Messaging
Agent-talk lets Claude Code sessions message through retalk, and shows how to test agent collaboration safely.
July 18, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Hermes Agent Runs Kimi K3 in a Sandbox
Hermes Agent’s Show HN demo runs Kimi K3 in Sanbox, with a safe Codex CLI review loop before patches land.
July 18, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Codex Micro Makes Agent Control Physical
Codex Micro is a compact OpenAI and Work Louder device for steering coding agents with explicit, physical controls.
July 17, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Google Vids Adds AI Personal Avatars
Google Vids now uses Gemini Omni and personal avatars; Codex users learn the repo-safe review habit to borrow.
July 17, 2026·Rogier Muller
Open Source·10 min read
deja-vu Adds Local Memory Over SSH
deja-vu turns local agent logs into searchable memory, with MCP recall, redaction, and sync for Codex-style workflows.
July 16, 2026·Rogier Muller
AI-Assisted Coding·10 min read
Codex Encrypts Sub-Agent Prompts
Codex encrypted sub-agent messages, and one GitHub issue shows why readable agent trails still matter.
July 15, 2026·Rogier Muller
Open Source·10 min read
Juggler Turns Coding Agents Into a Workbench
Juggler is an open-source GUI coding agent that makes tool calls, context, and review trails easier to inspect.
July 15, 2026·Rogier Muller
Open Source·9 min read
clawk Runs Coding Agents in Disposable VMs
clawk gives coding agents a throwaway Linux VM, with safer command execution, network limits, and a useful training lesson.
July 14, 2026·Rogier Muller
AI-Assisted Coding·10 min read
Evaluate Prompt Quality in Claude Code and Codex
Learn how a prompt-quality measurement post turns Claude Code and Codex prompts into repeatable engineering checks.
July 14, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Sanbox Gives AI Agents MicroVM Sandboxes
Sanbox runs AI agents in isolated, resumable sandboxes with filesystem state, run events, and Codex review use cases.
July 13, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Terry Tao’s Old and New Coding-Agent Apps
Terry Tao’s coding-agent app notes show how small visual tools can be worth building when review risk stays bounded.
July 13, 2026·Rogier Muller
Open Source·9 min read
searxng-ai-kit Brings SearXNG to MCP
searxng-ai-kit packages SearXNG as a CLI and MCP server, with safe Codex setup boundaries for local search.
July 12, 2026·Rogier Muller
Open Source·9 min read
9lives Heals Playwright Tests Safely
9lives repairs broken Playwright selectors, shows a diff, and gives Codex users a safer test-healing pattern.
July 11, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Databricks Benchmarks Coding Agents on Its Codebase
Databricks tested coding agents on a huge real codebase, and the useful lesson is cost per finished task.
July 10, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Kastra Enforces Policies for Claude Code, Codex, and Codex
Kastra intercepts coding-agent tool calls before they run, so risky database, shell, and MCP actions can be checked.
July 10, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Ask HN: What Agent Sandboxes Are Missing
Ask HN’s agent sandbox thread shows why Codex work needs clear MCP edges, network controls, and review receipts.
July 9, 2026·Rogier Muller
Open Source·9 min read
Moo Versions Machines for Agent Branches
Moo gives each agent branch its own Linux machine state, so file changes and runtime services stop colliding.
July 9, 2026·Rogier Muller
Open Source·9 min read
Rowboat vs Claude Desktop: Local Work Surfaces
Rowboat brings a local-first workbench to Claude-style desktop AI, and shows where Codex CLI still fits best.
July 8, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Clean Repos Make Coding Agents Cheaper
A May 2026 arXiv study found clean code did not raise pass rates, but it made coding agents cheaper to run and easier to review.
July 7, 2026·Rogier Muller
Open Source·8 min read
TikZ Editor Makes LaTeX Figures Less Painful
TikZ Editor lets LaTeX users move figure elements visually while keeping source code visible and easier to review.
July 6, 2026·Rogier Muller
AI-Assisted Coding·10 min read
What Dan Luu Learned About Agentic Coding
Dan Luu published field notes on coding with AI agents. This piece explains what he found and why bounded loops keep Codex work reviewable.
July 5, 2026·Rogier Muller
AI-Assisted Coding·10 min read
Ask HN’s LLM Coding Flow Debate
Why a Hacker News debate about LLM coding flow matters for Codex CLI, MCP, specs, and verification loops.
July 5, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Manufact Brings MCP to the Cloud
A story-first look at Manufact (YC S25), MCP Cloud, and the permission boundaries Codex users should care about.
July 3, 2026·Rogier Muller
Open Source·10 min read
OpenAI Codex Sensitive Files Issue
Codex Workshop research on issue #2847, agent ignore files, and safer Codex CLI workflows around secrets.
July 3, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Codex Team Rollouts for Real Repos
A Codex-ready team rollout plan for shared agent workflows, MCP boundaries, and safer review habits.
July 2, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Codex Agent Rules for Real Repos
Set up Codex agents with scoped AGENTS.md rules, safe MCP access, verification commands, and reviewable handoffs.
July 2, 2026·Rogier Muller
AI-Assisted Coding·10 min read
Safer Codex Rollouts for Teams
A practical Codex rollout for team AI coding governance with MCP boundaries, AGENTS.md rules, and review guardrails.
July 1, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Codex CLI MCP Setup
Connect Codex CLI to MCP with scoped AGENTS.md rules, safe permissions, and a verification loop your team can review.
July 1, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Safe AI Coding Team Rollouts
A practical rollout plan for training engineering teams to use Codex and coding agents with guardrails.
June 30, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Codex Remote in Real Repos
Use Codex Remote with GitHub, AGENTS.md, MCP boundaries, and reviewable diffs in Codex CLI workflows.
June 30, 2026·Rogier Muller
AI-Assisted Coding·8 min read
A Practical AI Review Workflow
A Codex-first convention for aligning AI code assistants, MCP boundaries, and review guardrails across a team.
June 29, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Codex Remote for GitHub Workflows
A practical Codex Remote GA guide for teams using GitHub, AGENTS.md, MCP, and Codex CLI verification loops.
June 29, 2026·Rogier Muller
AI-Assisted Coding·7 min read
Codex Review Guardrails That Stick
A practical Codex convention for safer agent-assisted reviews, MCP boundaries, and team-owned AGENTS.md checks.
June 28, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Run Codex as an Engineering Team
Team workflow for Codex CLI, AGENTS.md, verification loops, and reviewable diffs after Codex Remote GA.
June 28, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Give Coding Agents Team Rules
A practical team convention for orchestrating Codex and other agents with clear roles, MCP limits, and review rules.
June 27, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Wire Codex to MCP Safely
A practical Codex CLI workflow for MCP servers, AGENTS.md rules, Remote runs, and reviewable verification.
June 27, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Run Review Agents With Receipts
A practical Codex workflow for llm code review, with AGENTS.md guardrails, MCP boundaries, and a copyable review receipt.
June 26, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Train Your Team on Codex Remote
A practical Codex training guide for teams adopting Codex Remote, AGENTS.md, MCP, and reviewable CLI workflows.
June 26, 2026·Rogier Muller
AI-Assisted Coding·10 min read
Compare Coding Agents for Teams
A practical governance matrix for comparing Codex, Claude Code, and Codex across repo rules, MCP boundaries, and review loops.
June 25, 2026·Rogier Muller
AI-Assisted Coding·8 min read
AGENTS.md for Codex Teams
A practical AGENTS.md convention for Codex CLI teams that want safer MCP access, verification loops, and reviewable diffs.
June 25, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Verify Coding Agents in Isolation
Signed isolation bundles help teams test coding agents with clear tool boundaries, review guardrails, and repeatable evidence.
June 24, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Review Code With Codex CLI
A practical Codex CLI review workflow with AGENTS.md rules, MCP checks, verification loops, and a PR receipt.
June 24, 2026·Rogier Muller
AI-Assisted Coding·8 min read
How Autonomous Coding Agents Ship Safely
A practical Codex team convention for autonomous coding agents, MCP boundaries, and code review guardrails.
June 23, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Govern Codex Agents With Workflows
A practical Codex team convention for autonomous coding agents, review guardrails, MCP boundaries, and safe verification loops.
June 23, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Govern Autonomous Codex Workflows
A practical Codex workflow convention for governing autonomous coding agents with states, MCP boundaries, and review checks.
June 23, 2026·Rogier Muller
AI-Assisted Coding·7 min read
Check Codex MCP Access
A practical Codex CLI MCP checklist for AGENTS.md, verification loops, and reviewable team workflows.
June 23, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Verify Codex MCP Access
A practical Codex CLI MCP checklist for AGENTS.md rules, verification loops, and reviewable diffs after app updates.
June 23, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Check MCP Access in Codex
A practical Codex CLI workflow for verifying MCP servers, setting AGENTS.md boundaries, and keeping diffs reviewable.
June 23, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Skill Rubrics for Coding Agents
A team convention for reviewing agent skills, Codex workflows, MCP boundaries, and mixed-experience AI coding.
June 22, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Codex Conventions for Mixed-Skill Teams
A practical Codex convention for AI coding training, skill rubrics, MCP boundaries, and review guardrails.
June 22, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Codex Workflow After App 26.616
A practical Codex workflow response to app 26.616: AGENTS.md rules, CLI verification, MCP boundaries, and reviewable diffs.
June 22, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Codex 26.616 Workflow Check
How to respond to Codex app 26.616 with AGENTS.md rules, CLI verification, MCP boundaries, and review habits.
June 22, 2026·Rogier Muller
AI-Assisted Coding·8 min read
AI Code Review Needs a Receipt
A practical Codex-first review workflow for governing coding agents across tools, MCP servers, and team rules.
June 21, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Codex AGENTS.md Team Rules
A team convention for Codex AGENTS.md files, with scoped rules, MCP boundaries, and a reviewable verification loop.
June 21, 2026·Rogier Muller
AI-Assisted Coding·9 min read
ROI Guardrails for Coding Agents
A practical governance workflow for Codex teams using AGENTS.md, MCP boundaries, skills, and review checks.
June 20, 2026·Rogier Muller
AI-Assisted Coding·7 min read
A Safer Codex Review Loop
Use Codex CLI, AGENTS.md, verification, and review receipts to make AI-assisted code review safer for teams.
June 20, 2026·Rogier Muller
AI-Assisted Coding·9 min read
Team AI Coding Training Plan
A team training guide for Codex, MCP boundaries, AGENTS.md rules, skills, and review guardrails.
June 19, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Add MCP to Codex Safely
A practical Codex CLI MCP guide for teams: configure one server, document AGENTS.md boundaries, and verify diffs.
June 19, 2026·Rogier Muller
AI-Assisted Coding·8 min read
Install Codex CLI for Teams
Install Codex CLI with AGENTS.md, MCP boundaries, and a verification loop your team can reuse for reviewable diffs.
June 18, 2026·Rogier Muller
AI-Assisted Coding·7 min read
AI Code Review Tools Need Receipts
A practical read on the workflow, tradeoffs, and next steps. Read the workflow, review rules, and team training patterns for AI coding tooling.
June 17, 2026·Rogier Muller
AI-Assisted Coding·7 min read
OpenAI Codex-1 Agent Maximum Context Tokens
Team convention for Codex CLI context limits, AGENTS.md rules, MCP boundaries, and verification loops.
June 17, 2026·Rogier Muller
AI-Assisted Coding·7 min read
AI Code Review Workflow for Teams
A practical team convention for reviewing AI-assisted code without slowing delivery or losing ownership.
June 16, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Codex Code Review for CLI Teams
A Codex CLI review workflow for AGENTS.md rules, MCP boundaries, verification loops, and review receipts.
June 16, 2026·Rogier Muller
Methodology·6 min read
How to set up an AI coding workshop for your engineering team
How to set up an AI coding workshop: pick a format, scope it to your real repos and review habits, run hands-on labs, and leave with a shared playbook.
June 7, 2026·Rogier Muller
·6 min read
AI coding training requirements for DevOps teams on Codex CLI
The five operational training modules DevOps teams need before Codex CLI touches delivery paths: guardrails, secrets, CI evidence, rollback, ownership.
June 2, 2026·Rogier Muller
·5 min read
What is MCP in Codex? The answer for Codex CLI teams
The practical answer to what is MCP in Codex, plus the repo contract Codex CLI teams need before connectors touch shared code.
June 2, 2026·Rogier Muller
AI-Assisted Coding·5 min read
Codex Windows review loop
Codex CLI review workflow for openai codex cli review code changes, AGENTS.md, MCP, and verification loops.
May 31, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Codex Windows update: MCP and mobile use
A Codex CLI workflow guide for how to add mcp to codex, AGENTS.md, and reviewable verification loops.
May 30, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Codex CLI 0.135.0 workflow
A Codex CLI guide for how to install codex cli, AGENTS.md, MCP, and reviewable verification loops.
May 29, 2026·Rogier Muller
Open Source·6 min read
Codex CLI boundaries
A Codex CLI guide for AGENTS.md, MCP, verification loops, and reviewable diffs. Read the workflow, review rules, and team training patterns for MCP.
May 28, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Codex CLI review receipts
A Codex code review workflow for AGENTS.md, MCP, and verification loops that turns CLI diffs into reviewable receipts.
May 27, 2026·Rogier Muller
AI-Assisted Coding·7 min read
Agentic coding guardrails
Practical ai coding training for large teams: review guardrails, MCP boundaries, and team habits that improve delivery.
May 25, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Codex CLI workflows for reviewable diffs
A Codex CLI workflow guide for openai codex cli github, AGENTS.md, MCP, and reviewable verification loops.
May 25, 2026·Rogier Muller
AI-Assisted Coding·5 min read
Codex CLI, Appshots, and Goal Mode
A practical Codex CLI comparison for codex cli vs claude code, with AGENTS.md, MCP, and verification loops.
May 24, 2026·Rogier Muller
Open Source·6 min read
Codex CLI review loops
A Codex CLI workflow guide for codex cli mcp, AGENTS.md, MCP boundaries, and verification loops teams can use to ship reviewable production work.
May 22, 2026·Rogier Muller
AI-Assisted Coding·6 min read
MCP training for engineering teams
Practical mcp training for engineering teams using agentic coding, review guardrails, and connector boundaries.
May 21, 2026·Rogier Muller
AI-Assisted Coding·7 min read
Codex CLI, GitHub, and MCP
A Codex CLI workflow guide for codex github, AGENTS.md, MCP, and reviewable diffs in production repos.
May 21, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Codex CLI 0.132.0: workflows and integrations
Codex CLI 0.132.0 tightens AGENTS.md, MCP, and verification loops for reviewable diffs.
May 20, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Codex governance: four contracts that hold in review
A codex governance note for engineering teams: the slash catalog, verification latch, browser bridge note, and model pin that keep Codex CLI work reviewable.
May 17, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Codex mobile CLI: runs that survive review
A codex mobile cli pattern for running Codex CLI from anywhere: verification latches, model pins, and connector rosters that keep remote runs reviewable.
May 16, 2026·Rogier Muller
AI-Assisted Coding·5 min read
Why agentic coding governance beats raw speed
Agentic coding governance beats speed: connector cards, child receipts, decision stubs, and scope ledgers that make agent diffs defensible after merge.
May 15, 2026·Rogier Muller
AI-Assisted Coding·6 min read
How to set up agentic coding workflows and guardrails
A field guide to agentic coding workflows and guardrails: handoff receipts, connector ownership, and review gates for engineering teams under deadline.
May 15, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Codex workflows for mobile handoffs
Codex workflows for mobile handoffs: the repo contract of model pins, connector rosters, done checklists, and slash catalogs that lets agent work change hands.
May 15, 2026·Rogier Muller
AI-Assisted Coding·5 min read
Codex mobile CLI docs your team can read anywhere
The codex mobile cli question is a docs question: how a team keeps AGENTS.md rules, run notes, and verification transcripts readable away from the desk.
May 15, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Codex workspace agents need repo rules
Codex workspace agents and Codex cloud agents need repo rules: scoped boundary files, connector cards, and replay receipts reviewers can check.
May 14, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Codex workflows: governance that lives in the repo
How to govern codex workflows from the repo: a connector roster, a ten-line done checklist, a slash catalog, and a verification latch reviewers can replay.
May 14, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Fast mode is not the default: when fast models earn it
The fast model is a tradeoff you make on purpose: scope ledgers, replay sandwiches, and connector cards that keep fast agent runs reviewable.
May 13, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Codex-auto-review: what it catches and misses
Codex-auto-review trials showed Codex catching syntax drift and missing permission drift. The fix is transcript evidence and repo contracts, not more autonomy.
May 13, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Is Codex CLI giving MCP more reach than reviewers expect?
An operational memo for Codex CLI 0.129.0: MCP boundaries, connector owners, allowed actions, AGENTS.md instructions, and reviewable diffs.
May 11, 2026·Rogier Muller
AI-Assisted Coding·5 min read
AI agent guardrails that hold
A field guide to AI agent guardrails for recursive agent chains: connector ownership, child receipts, and review evidence that survives the merge queue.
May 10, 2026·Rogier Muller
AI-Assisted Coding·5 min read
Codex workflows for Chrome and the CLI
Codex workflows that cross into Chrome: the browser bridge note, model pin, connector roster, and done checklist that keep two surfaces telling one story.
May 10, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Agentic workflows from PR to merge
A PR review workflow for agentic coding teams: connector ownership, scoped tasks, replay transcripts, and human approval lanes from PR to merge.
May 9, 2026·Rogier Muller
AI-Assisted Coding·5 min read
Codex CLI 0.130.0: AGENTS.md and MCP
What Codex CLI 0.130.0 means for production repos: check AGENTS.md boundaries, MCP permissions, and review evidence before and after the update.
May 9, 2026·Rogier Muller
Open Source·6 min read
Codex CLI 0.121.0 for repo workflows
Codex CLI 0.121.0 repo workflows: named connector owners, a pinned model in AGENTS.md, and PR receipts that survive reviewer handoffs.
May 7, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Codex CLI workspace tools that make runs reviewable
Codex CLI workspace tools that carry the operating contract: model pin, connector roster, done checklist, and slash catalog for reviewable agent runs.
May 6, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Codex CLI 0.122.0: workflows, permissions, MCP
A Codex CLI 0.122.0 workflow guide: AGENTS.md instructions, permission boundaries, MCP rosters, and verification reviewers can replay.
May 5, 2026·Rogier Muller
AI-Assisted Coding·5 min read
Codex CLI 0.123.0: workflows that hold up
Codex CLI 0.123.0 workflows that hold up in review: replay recipes in the diff, a pinned model, a connector roster, and a ten-line done checklist.
May 4, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Codex CLI 0.124.0: tighter rollback loops
Codex CLI 0.124.0 as a workflow moment: shrink the rollback contract, pin the model, and keep a connector roster and done checklist where reviewers live.
May 3, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Codex 5.5: pin the model before you swap it
Codex 5.5 questions are model governance questions: pin the default model and escalation rule in AGENTS.md, and keep browser checks bridged to CLI receipts.
May 2, 2026·Rogier Muller
AI-Assisted Coding·6 min read
Codex CLI /goal and AGENTS.md workflow
Use Codex CLI /goal to keep task intent and AGENTS.md to keep repository boundaries, verification checks, and handoff evidence clear.
May 1, 2026·Rogier Muller
AI-Assisted Coding·5 min read
Codex-CLI 0.125.0: Reviewable Agent Loops
An operational memo for codex-cli 0.125.0: reviewable agent loops, AGENTS.md pins, verification transcripts, and connector rosters.
April 29, 2026·Rogier Muller