Coding-agent monitoring · OpenAI Codex

    OpenAI Codex monitoring for teams

    OpenAI Codex monitoring means reading every Codex session your team runs to find what keeps going wrong: the same failure again, instructions retyped by hand, AGENTS.md rules nobody follows, secrets in prompts. Hervé does it across the whole team, fixes the cause in AGENTS.md and skills, and checks the next sessions.

    Last updated

    Why one OpenAI Codex session can't show you the problem

    OpenAI Codex reads every AGENTS.md from the repository root down to the working directory, and the skills in .agents/skills/ to know how your team works. In its own docs: “Codex reads AGENTS.md files before doing any work. By layering global guidance with project-specific overrides, you can start each task with consistent expectations, no matter which repository you open.”[1]

    Each developer only sees their own sessions. Nobody sees that three people hit the same wall last week, that the same instruction gets typed by hand every morning, or that a rule in AGENTS.md has not changed what the agent does in a month. 84% of developers use or plan to use AI tools in their development process, up from 76% a year earlier.[3] The more of the team runs OpenAI Codex, the bigger that blind spot gets.

    What Hervé finds in OpenAI Codex sessions

    Hervé reads every captured session across the team and groups what keeps going wrong into findings, each with how many sessions and developers it touched:

    • Recurring failures: the same mistake across sessions and developers, with the human time or tokens it cost.
    • Repeated instructions: guidance team members retype by hand that belongs in one shared rule or skill.
    • Unused instructions: sections of AGENTS.md and skills that no session follows or uses, but that still take up context.
    • Leaks: a secret pasted into a prompt, or printed by the agent. AGENTS.md, the file Codex reads before doing any work, is used by over 60,000 open-source projects.[2]

    How Hervé fixes the cause at the source

    For each finding, Hervé proposes the fix where OpenAI Codex will read it next time: a change to every AGENTS.md from the repository root down to the working directory, and the skills in .agents/skills/. The fix is opened as a pull request on your repository, so it goes through your usual merge flow and reaches the whole team, not one developer's private memory.

    How Hervé guards the next OpenAI Codex sessions

    Once a fix is merged, Hervé checks every new session against your rules and compares the before and after, so you see whether the problem stopped. You get a weekly update, and you stay in control of what the agents are told.

    How to set up OpenAI Codex monitoring

    1. Install the rv CLI. Follow the one-minute setup for macOS, Linux or Windows.
    2. Enable capture for OpenAI Codex. In each repository, run:
      my_repo $ rv install --agent codex

      Sessions are saved to a branch of your own repository, and the last 30 days of local sessions are backfilled by default.

    3. Have every team member do the same once. Hervé only sees the sessions it captures, so each developer runs rv install once. The first findings come in week 2.

    Common questions

    What does Hervé read in a OpenAI Codex session?

    The prompts, the steps the agent took and the files it touched, from the branch rv install writes to your own repository. Hervé reads sessions and code on demand: transcripts, diffs and file contents never go into our database. We keep findings, counts and file names.

    Can't I just ask OpenAI Codex to clean up AGENTS.md?

    You can, for one session. OpenAI Codex sees what happened in front of it; it can't see that three developers hit the same wall last week, or which rules no session has followed in a month. Hervé reads every session across the team, then checks whether the fix held.

    Which files does Hervé change to fix a OpenAI Codex problem?

    The ones OpenAI Codex reads its instructions from: AGENTS.md files and .agents/skills/. Each fix is opened as a pull request on your repository, so it goes through your usual merge flow and reaches the whole team.

    Do we have to change how we use OpenAI Codex?

    No. Each team member runs rv install once. Everyone keeps using OpenAI Codex, GitHub or GitLab, and your merge flow exactly as they are.

    What if the team uses more than one coding agent?

    Hervé captures sessions from Claude Code, Cursor, GitHub Copilot CLI, OpenAI Codex, and OpenCode, so a team that mixes agents is covered by the same install.

    How do we start?

    With a 6-week paid pilot for your whole team, fully refunded if we find nothing actionable. Talk to a founder to set it up; the pilot details and price are on the pricing page.

    See pilot details & pricing →

    Sources

    1. Custom instructions with AGENTS.md, OpenAI.
    2. AGENTS.md, agents.md.
    3. 2025 Developer Survey: AI, Stack Overflow.

    Monitoring other coding agents

    See what your team's OpenAI Codex sessions are hiding.

    Talk to a founder

    6-week paid pilot, fully refunded if we find nothing actionable.