codex

A Codex plugin adapter specification describing how plugins are packaged in a `.codex-plugin` folder with a `plugin.json` manifest. It defines required metadata and how Codex discovers skills, hooks, and MCP servers.

In plain words
What is it for?
Use it to build or check a Codex plugin package, including its manifest, skill directory, hook files, and MCP server configuration.
Why use it?
It removes uncertainty when preparing a plugin for Codex by documenting the required files, fields, and supported parts. It also makes clear that agents, commands, and apps are not supported.

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/rbbtsn0w/adg/codex
Clone the repo
git clone --depth 1 https://github.com/RbBtSn0w/adg
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 780 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00780
Opus 5 $0.00000 $0.00390
Sonnet 5 $0.00000 $0.00156
Haiku 4.5 $0.00000 $0.00078

Measured 2d ago against content hash f90b59eeb284, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex 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.

docs/agents/codex.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex (OpenAI) — Adapter Specification

Based on the Agent Adapter Template.


1. Official References


2. Projection Output

  • Output directory: .codex-plugin/
  • Manifest file: .codex-plugin/plugin.json
  • Adapter source: src/adapters/codex.ts

3. Manifest Schema

Required fields: name, version, description, skills

Optional fields: author, homepage, license, hooks, mcpServers

// Minimal projected manifest
{
  "name": "my-plugin",
  "version": "1.0.0",
  "description": "Example plugin",
  "skills": "./skills/"
}

4. Supported Components

Component Supported Manifest Key Discovery Mechanism
Skills skills (string root or bare-id array) Auto-scan skills/ dir; or explicit bare-id array
Agents Not supported by Codex
Commands Not supported by Codex
Hooks hooks Explicit file path (no auto-load)
MCP mcpServers .mcp.json path reference
Apps Not supported by Codex

5. Skills

  • Declared form: String root ("./skills/") or array of bare ids (e.g. ["foo", "bar"]).
  • Strict mode: Same as Claude. strict: true passes root string through; Codex discovers from directory.
  • Array encoding: Bare ids — NOT paths. This is the key difference from Claude. ADG resolves ./skills/<id> paths to bare ids during projection.
  • Auto-discovery: Codex natively scans a directory root.

6. MCP Servers

  • Config file name: Same as Claude (.mcp.json reference).
  • Config key: mcpServers
  • Special handling: Accepts ${CLAUDE_PLUGIN_ROOT} in configs.

7. Hooks

  • Canonical file: Not auto-loaded — requires explicit manifest reference.
  • Native override: hooks/hooks-codex.json — preferred over hooks/hooks.json when present. Adapter resolution order: hooks-codex.jsonhooks.json → sole *.json.
  • Supported events (10 total): SessionStart, SubagentStart, PreToolUse, PermissionRequest, PostToolUse, PreCompact, PostCompact, UserPromptSubmit, SubagentStop, Stop
  • Hook types: command (same as Claude)
  • Environment bridging: Same as Claude (${CLAUDE_PLUGIN_ROOT}, etc.).
  • ADG adapter note: Unlike Claude, Codex has no auto-load. The hooks config must be a file path (not a directory). The adapter resolves ./hooks/ to a concrete file.

Read the full file on GitHub · 90 lines

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 · 90 lines · 0 tokens per session scan A f90b59eeb284

Subscribe to this mod's changes

codex is an agent published in the GitHub repository RbBtSn0w/adg (3 stars, last pushed 28d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 780 tokens. 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.

Related

Other agents, from other repositories

security-auditor

Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.

addyosmani/agent-skills · 35 tokens

backend-api-security-backend-security-coder

Expert in secure backend coding practices specializing in input validation, authentication, and API security. Use PROACTIVELY for backend security implementations or security code reviews.

wshobson/agents · 40 tokens

codemap

Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…

alvinunreal/oh-my-opencode-slim · 0 tokens

design-reviewer

Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…

wasintoh/toh-framework · 85 tokens

conversation-analyzer

Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Triggered by /hookify without arguments.

sifxprime/kodelyth-ecc · 28 tokens

java-reviewer

Expert Java and Spring Boot code reviewer specializing in layered architecture, JPA patterns, security, and concurrency. Use for all Java code changes. MUST BE USED for Spring Boot projects.

Jamkris/everything-gemini-code · 40 tokens