A setup command that checks whether the local Codex command-line tool is ready to use and can enable an optional review check when work stops. It can also point out missing sign-in, provider settings, or workspace configuration.

Use it to check installation and authentication, enable the stop-time review gate, configure workspace role defaults, verify status, or inspect runtime and saved-state problems with the related doctor command.

It helps identify setup problems before you rely on Codex in a workspace. When Codex is unavailable, it can guide the user through deciding whether to install it.

setup — Command by vsladkov

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/vsladkov/claudex-stereo/setup

Clone the repo

git clone --depth 1 https://github.com/vsladkov/claudex-stereo

Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 571 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00017	$0.00571
Opus 5	$0.00009	$0.00285
Sonnet 5	$0.00003	$0.00114
Haiku 4.5	$0.00002	$0.00057

Measured 2d ago against content hash 1d4374c8bfb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/stereo/commands/setup.md · 62 lines

What it actually says

Happy path:

Install the Stereo plugin.
When the report's - auth: line is not ready, run !codex login; use !codex login --device-auth or !codex login --with-api-key when the report names those fallbacks.
Configure optional third-party provider keys only when the report lists unconfigured aliases or missing provider environment variables.
Optionally run /stereo:setup --enable-review-gate when - review gate: is disabled.
Optionally run /stereo:config to set workspace role defaults when - role defaults: says none are configured.
Verify the workspace with /stereo:status after the - codex: and - auth: checks are ready.

Use /stereo:doctor when install readiness is healthy but workspace runtime or durable state needs inspection.

Run:

node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-companion.ts" setup "$ARGUMENTS --json"

If the result says Codex is unavailable and npm is available:

Use AskUserQuestion exactly once to ask whether Claude should install Codex now.
Put the install option first and suffix it with (Recommended).
Use these two options:
- Install Codex (Recommended)
- Skip for now
If the user chooses install, run:

npm install -g @openai/codex

Then rerun:

node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-companion.ts" setup "$ARGUMENTS --json"

If Codex is already installed or npm is unavailable:

Do not ask about installation.

Output rules:

Present the final setup output to the user.
If installation was skipped, present the original setup output.
Setup reports needs attention when Node is older than 24. Relay the Node >= 24 requirement with the exact found version because the plugin runs its .ts sources natively.
If Codex is installed but not authenticated, preserve the guidance to run !codex login.
Preserve the provider section verbatim when present: the active provider, each configured provider's key status, per-alias readiness, and any provider next steps. Exact environment-variable names matter.
Always preserve stranded-reservation next steps with their exact file paths.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 62 lines · 17 tokens per session scan A 1d4374c8bfb9

Subscribe to this mod's changes

setup is a command published in the GitHub repository vsladkov/claudex-stereo (3 stars, last pushed 23d ago), licensed Apache-2.0. It adds 17 tokens to every session and 571 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

ai-pair-programming claude claude-code claude-code-plugin cli

setup

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

audit-agents-skills

audit-repo-docs

boldguy-linkedin-answer

release

security-audit

update-infos-release