agentleFS
Sign inStart free
vikas8520-codervikas8520-coder/nerve/skills/config-codex-cli/SKILL.md

config-codex-cli

Skill0 starsChanged 3 months agoMITView on GitHub

Step-by-step agent workflow to configure the OpenAI Codex CLI on any machine (Linux, macOS, Windows) to use Nerve as an OpenAI-compatible backend. Detects OS and shell, writes config.toml and 7 named profiles, sets environment variables, and verifies the setup.

  • Installs packages

3 other projects use a version of this, 3 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Default 0 = disabled. Each turn can land on a different account and break prompt-cache / session continuity.

    line 31
  2. Very specific:

    Do not flip ship defaults in code for this skill: sessionAffinityTtlMs stays 0 and STREAM_IDLE_TIMEOUT_MS stays 600000.

    line 55

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- generated by src/lib/agentSkills/generator.ts; manual edits will be overwritten -->

Overview

Step-by-step agent workflow to configure the OpenAI Codex CLI on any machine (Linux, macOS, Windows) to use Nerve as an OpenAI-compatible backend. Detects OS and shell, writes config.toml and 7 named profiles, sets environment variables, and verifies the setup.

Quick install

npm install -g nerve   # or: npx nerve
nerve --version

Subcommands

No CLI subcommands mapped for this family yet.

<!-- skill:custom-start -->

Long-running Codex tasks (#7287)

Two Nerve defaults silently break multi-hour Codex sessions. Document them whenever configuring Codex for overnight / multi-hour work. Full guide: docs/guides/CODEX-CLI-CONFIGURATION.md → Long-running tasks.

Session affinity (default off)

  • Setting: sessionAffinityTtlMs (ms; UI shows Affinity TTL (seconds) under Dashboard → Settings → Routing → Session affinity). Legacy alias: codexSessionAffinityTtlMs.
  • Default 0 = disabled. Each turn can land on a different account and break prompt-cache / session continuity.
  • Codex session keys (x-codex-session-id, x-session-id, x-nerve-session, body prompt_cache_key / session_id) are only used for pinning when TTL > 0.
  • Max: 86400 seconds / 86400000 ms (24h). Set TTL above the expected task length (e.g. 43200 s for ~12h).

Stream idle timeout (default 10 minutes)

  • Env: STREAM_IDLE_TIMEOUT_MS (default 600000). Also consider FETCH_BODY_TIMEOUT_MS (same baseline; 0 disables).
  • Synthetic SSE heartbeats do not reset the idle clock — only real upstream chunks do.
  • A quiet reasoning turn past the idle window is force-closed (stream_idle_timeout / StreamIdleTimeoutError). Grep logs for Idle timeout: no data from.

Recommended multi-hour recipe

  1. Dashboard → Settings → Routing → Session affinity → Affinity TTL = 43200 (12h) or 86400 (24h max).
  2. Nerve environment:
STREAM_IDLE_TIMEOUT_MS=0
FETCH_BODY_TIMEOUT_MS=0
  1. Restart Nerve. Leave Codex config.toml as usual (wire_api = "responses", correct base_url).

Defaults decision

Do not flip ship defaults in code for this skill: sessionAffinityTtlMs stays 0 and STREAM_IDLE_TIMEOUT_MS stays 600000. Long-running operators must opt in. See Discussion #5718 and issue #7287.

<!-- skill:custom-end -->

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free