Skip to content

majiayu000/spellbook / skills/codex-agent

codex-agent

Verified

Use when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative implementation proposals. Requires Codex CLI to be installed and authenticated.

FileKindSize
README.mdmarkdown4.9 KB
SKILL.mdskill md7.5 KB
advanced.mdmarkdown3.8 KB
examples.mdmarkdown4.3 KB
sandbox-modes.mdmarkdown2.0 KB
scripts/check-codex.shexecutablescript1.0 KB
scripts/codex-wrapper.shexecutablescript3.5 KB

advanced.md

View on GitHub
# Advanced Configuration

Advanced usage patterns, MCP integration, and configuration options.

## Configuration Files

Codex CLI reads configuration from `~/.codex/config.toml`.

### Basic Config

```toml
# ~/.codex/config.toml

# Default model
# Omit this to use the installed Codex default, or set a model supported by
# your current Codex CLI.
# model = "<codex-model>"

# Default sandbox mode
sandbox_mode = "read-only"

# Enable web search
search = true
```

### Profiles

Create a separate profile file for each use case. In Codex 0.134.0 and later,
`--profile <name>` overlays `$CODEX_HOME/<name>.config.toml` on top of the base
config; it does not read `[profiles.<name>]` tables from `config.toml`.

```toml
# ~/.codex/review.config.toml
sandbox_mode = "read-only"
```

```toml
# ~/.codex/implement.config.toml
sandbox_mode = "workspace-write"
```

Do not persist a `danger-full-access` + no-approval profile. If broad access is
unavoidable, use it as a one-off command after explicit user approval and record
what directory or system boundary required it.

Use with `-p` / `--profile`:

```bash
codex exec -p review -C /project "Analyze code"
codex exec -p implement -C /project "Add feature"
```

## MCP Integration

Codex supports Model Context Protocol (MCP) for external tool integration.

### Add MCP Server (stdio)

```bash
codex mcp add my-server -- /path/to/mcp-server
```

### Add MCP Server (HTTP)

```bash
codex mcp add remote-server --url https://mcp.example.com/api
```

### List MCP Servers

```bash
codex mcp list --json
```

### Run Codex as MCP Server

```bash
codex mcp-server
```

This allows other MCP clients to use Codex as a tool provider.

## Environment Variables

| Variable | Description |
|----------|-------------|
| `CODEX_API_KEY` | OpenAI API key (alternative to login) |
| `CODEX_MODEL` | Default model override |
| `CODEX_SANDBOX` | Default sandbox mode |

### CI/CD Usage

```bash
export CODEX_API_KEY="<load from your secret manager or environment>"
codex exec --json "Generate changelog from git log"
```

## Feature Flags

Enable/disable experimental features:

```bash
# Enable feature
codex exec --enable some-feature "task"

# Disable feature
codex exec --disable some-feature "task"
```

## Custom Instructions (AGENTS.md)

Create `AGENTS.md` in your project root to provide project-specific context:

```markdown
# Project Context

This is a TypeScript Node.js project using Express.

## Conventions
- Use async/await, not callbacks
- Use Zod for validation
- Tests use Jest with supertest

## Architecture
- src/api/ - Express routes
- src/services/ - Business logic
- src/models/ - Data models
```

Codex will read this file for context.

## Shell Completions

Generate shell completions:

```bash
# Bash
codex completion bash > /etc/bash_completion.d/codex

# Zsh
codex completion zsh > ~/.zfunc/_codex

# Fish
codex completion fish > ~/.config/fish/completions/codex.fish
```

## JSON Schema Validation

Enforce structured output:

```bash
# schema.json
{
  "type": "object",
  "properties": {
    "issues": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "file": { "type": "string" },
          "line": { "type": "integer" },
          "severity": { "type": "string" },
          "message": { "type": "string" }
        }
      }
    }
  }
}

# Use with Codex
codex exec -C /project --output-schema schema.json \
  "Find all security issues and output as structured JSON"
```

## Local/OSS Mode

Run with local models via Ollama:

```bash
# Requires Ollama installed with compatible model
codex exec --oss "Explain this code"
```

## Running in Sandbox

Test sandbox policies:

```bash
# Run a command through Codex's sandbox helper.
codex sandbox -C /project -- cat /etc/passwd

# Inspect available sandbox flags for the installed CLI.
codex sandbox --help
```
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall