codex

An adapter for running OpenAI Codex, a command-line coding agent, through the adapters tool. It supports API-key login, sessions, plugins, MCP servers, and resuming or forking sessions.

In plain words
What is it for?
It is for running prompts such as asking for a unit test, choosing a model, using automatic approval, and managing Codex plugins or MCP servers.
Why use it?
It gives one documented way to install, authenticate, run, and manage Codex from the command line.

Agent

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 agents/a5c-ai/babysitter/codex
Clone the repo
git clone --depth 1 https://github.com/a5c-ai/babysitter
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 399 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00399
Opus 5 $0.00000 $0.00199
Sonnet 5 $0.00000 $0.00080
Haiku 4.5 $0.00000 $0.00040

Measured 2d ago against content hash 56f73325b801, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

codex scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Config file: `~/.codex/config.json`.
docs/adapters/reference/agents/codex.md · 65 lines

What it actually says

OpenAI Codex

Adapter for OpenAI's Codex CLI.

Install

adapters install codex

Minimum CLI version: 1.0.0. Supported on macOS, Linux and Windows.

Auth

  • API key only — set OPENAI_API_KEY in your environment.

Config file: ~/.codex/config.json.

Minimal run

adapters run codex --prompt "Write a unit test for utils.ts"

Notable flags

  • --model <id> — default o4-mini; codex-mini-latest also available.
  • --full-auto — emitted when approvalMode: 'yolo'.
  • --quiet <prompt> — used by the adapter to stream prompt output.

Session files

  • Location: ~/.codex/sessions/*.jsonl
  • Parsed via the standard JSONL session reader.
  • Resume/fork supported by the adapter layer.

Plugins

Plugin support: yes. Codex has a plugin directory with @plugin-creator skill.

Plugin Management

adapters plugin install codex <plugin>
adapters plugin list codex

MCP Servers

adapters mcp install codex <mcp-server>
adapters mcp list codex

Registry: https://modelcontextprotocol.io for MCP servers.

Capabilities

Thinking models (o4-mini) with low/medium/high effort levels, tool calling with parallel calls, JSON / structured output, text streaming.

Known limitations

  • No image input/output, no file attachments.
  • No MCP or plugin ecosystem — bring-your-own tooling only.
  • Only two bundled models; other Codex variants must be specified explicitly via --model.
  • Project-level config is not supported (supportsProjectConfig: false); configuration is global.
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.

  1. 2d ago First seen · 65 lines · 0 tokens per session scan B 56f73325b801

Subscribe to this mod's changes

codex is an agent published in the GitHub repository a5c-ai/babysitter (1,757 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 399 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

rn-tester

Tests React Native features on simulator/emulator. Verifies UI renders correctly, user flows work, and internal state matches expectations. Use when a feature has been implemented and needs verification. PARENT-SESSION-ONLY: requires MCP tools (cdp, device) — do NOT spawn via Task tool, run protocol inline in parent…

Lykhoyda/rn-dev-agent · 337 tokens

rn-debugger

Diagnoses broken or unexpected behavior in a React Native app running on simulator/emulator. Gathers parallel evidence (component tree, logs, network, store), narrows root cause, applies a fix, and verifies recovery. PARENT-SESSION-ONLY: requires MCP tools (cdp, device, collectlogs) — do NOT spawn via Task tool, run…

Lykhoyda/rn-dev-agent · 341 tokens

rn-code-architect

Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…

Lykhoyda/rn-dev-agent · 238 tokens

rn-code-reviewer

Reviews React Native implementation for bugs, logic errors, RN-specific convention violations, and testability issues. Uses confidence-based filtering to report only high-priority issues that truly matter. Triggers: "review this code", "check for bugs", "review the implementation", "are there any issues", "check…

Lykhoyda/rn-dev-agent · 234 tokens

design-author

Use after research is complete to draft the approach before any code is written. Drafts a 200-line design document covering current state, desired end state, patterns to follow, and decisions made. Resolves its own open questions autonomously, recording each as an explicit, auditable assumption in the design.

bostonaholic/team · 64 tokens

questioner

Use as the first agent of the QRSPI pipeline. Decomposes a user's task description into a full task record (task.md) and neutral research questions (questions.md), plus conditional artifacts — a prd.md when the PRD criteria apply, and a repos.md listing the repos the topic touches when the description names more than…

bostonaholic/team · 89 tokens