Codex Subagent Skill

Spawn autonomous subagents to offload context-heavy work. Subagents burn their own tokens, return only final results.

Golden Rule: If task + intermediate work would add 3,000+ tokens to parent context → use subagent.

Intelligent Prompting

Critical: Parent agent must provide subagent with essential context for success.

Good Prompting Principles

1. Include relevant context - Give the subagent thorough context
2. Be specific - Clear constraints, requirements, output format
3. Provide direction - Where to look, what sources to prioritize
4. Define success - What constitutes a complete answer

Examples

❌ Bad: "Research authentication"

✅ Good: "Research authentication in this Next.js codebase. Focus on: 1) Session management strategy (JWT vs session cookies), 2) Auth provider integration (NextAuth, Clerk, etc), 3) Protected route patterns. Check /app, /lib/auth, and middleware files. Return architecture summary with code examples."

❌ Bad: "Search for Codex SDK"

✅ Good: "Find the most recent Codex SDK documentation and summarize key updates. Focus on: 1) Installation/quickstart, 2) Core API methods and parameters, 3) Breaking changes or deprecations. Prioritize official OpenAI docs and release notes. Return a concise summary with citations."

❌ Bad: "Find API endpoints"

✅ Good: "Find all REST API endpoints in this Express.js app. Look in /routes, /api, and /controllers directories. For each endpoint document: method (GET/POST/etc), path, auth requirements, request/response schemas. Return as markdown table."

Prompting Template

[TASK CONTEXT]
You are researching/analyzing [SPECIFIC TOPIC] in [LOCATION/CODEBASE/DOMAIN].

[OBJECTIVES]
Your goals:
1. [1st objective with specifics]
2. [2nd objective]
3. [3rd objective if needed]

[CONSTRAINTS]
- Focus on: [specific areas/files/sources]
- Prioritize: [what matters most]
- Ignore: [what to skip]

[OUTPUT FORMAT]
Return: [exactly what format parent needs]

[SUCCESS CRITERIA]
Complete when: [specific conditions met]

Model Selection

Use Mini Model (gpt-5.1-codex-mini + medium)

Pure search only - no additional work after gathering info.

Bash (Linux/macOS)

codex exec --dangerously-bypass-approvals-and-sandbox --skip-git-repo-check \
  -m gpt-5.1-codex-mini -c 'model_reasoning_effort="medium"' \
  "Search web for [TOPIC] and summarize findings"

PowerShell (Windows)

codex exec --dangerously-bypass-approvals-and-sandbox --skip-git-repo-check `
  -m gpt-5.1-codex-mini -c 'model_reasoning_effort="medium"' `
  "Search web for [TOPIC] and summarize findings"

Inherit Parent Model + Reasoning

Multi-step workflows - search + analyze/refactor/generate:

Bash (Linux/macOS)

codex exec --dangerously-bypass-approvals-and-sandbox --skip-git-repo-check \
  -m "$MODEL" -c "model_reasoning_effort=\"$REASONING\"" \
  "Find auth files THEN analyze security patterns and propose improvements"

PowerShell (Windows)

codex exec --dangerously-bypass-approvals-and-sandbox --skip-git-repo-check `
  -m $MODEL -c "model_reasoning_effort=`"$REASONING`"" `
  "Find auth files THEN analyze security patterns and propose improvements"

Decision Logic

Is task PURELY search/gather?
├─ YES: Any work after gathering?
│  ├─ NO → mini model
│  └─ YES → inherit parent
└─ NO → inherit parent

Basic Usage

Bash (Linux/macOS)

# Get parent session settings (respects active profile; falls back to top-level)
# NOTE: codex-parent-settings.sh prints two lines; use mapfile to avoid empty REASONING.
mapfile -t _settings < <(scripts/codex-parent-settings.sh)
MODEL="${_settings[0]}"
REASONING="${_settings[1]}"

# Spawn subagent (inherit parent)
codex exec --dangerously-bypass-approvals-and-sandbox --skip-git-repo-check \
  -m "$MODEL" -c "model_reasoning_effort=\"$REASONING\"" \
  "DETAILED_PROMPT_WITH_CONTEXT"

# Safer prompt construction (no backticks / command substitution)
PROMPT=$(cat <<'EOF'
[TASK CONTEXT]
You are analyzing /path/to/repo.

[OBJECTIVES]
1. Do X
2. Do Y

[OUTPUT FORMAT]
Return: path - purpose
EOF
)
codex exec --dangerously-bypass-approvals-and-sandbox --skip-git-repo-check \
  -m "$MODEL" -c "model_reasoning_effort=\"$REASONING\"" \
  "$PROMPT"

# Pure search (use mini)
codex exec --dangerously-bypass-approvals-and-sandbox --skip-git-repo-check \
  -m gpt-5.1-codex-mini -c 'model_reasoning_effort="medium"' \
  "SEARCH_ONLY_PROMPT"

# JSON output for parsing
codex exec --dangerously-bypass-approvals-and-sandbox --json "PROMPT" | jq -r 'select(.event=="turn.completed") | .content'

PowerShell (Windows)

# Get parent session settings (respects active profile; falls back to top-level)
$scriptPath = Join-Path $env:USERPROFILE ".codex\skills\codex-subagent\scripts\codex-parent-settings.ps1"
$settings = & $scriptPath
$MODEL = $settings[0]
$REASONING = $settings[1]

# Spawn subagent (inherit parent)
codex exec --dangerously-bypass-approvals-and-sandbox --skip-git-repo-check `
  -m $MODEL -c "model_reasoning_effort=`"$REASONING`"" `
  "DETAILED_PROMPT_WITH_CONTEXT"

# Use here-string for multi-line prompts (avoids escaping issues)
$PROMPT = @'
[TASK CONTEXT]
You are analyzing /path/to/repo.

[OBJECTIVES]
1. Do X
2. Do Y

[OUTPUT FORMAT]
Return: path - purpose
'@

codex exec --dangerously-bypass-approvals-and-sandbox --skip-git-repo-check `
  -m $MODEL -c "model_reasoning_effort=`"$REASONING`"" `
  $PROMPT

# Pure search (use mini)
codex exec --dangerously-bypass-approvals-and-sandbox --skip-git-repo-check `
  -m gpt-5.1-codex-mini -c 'model_reasoning_effort="medium"' `
  "SEARCH_ONLY_PROMPT"

# Method 1 (Recommended): Use -o to output directly to file
codex exec --dangerously-bypass-approvals-and-sandbox --skip-git-repo-check `
  -m $MODEL -c "model_reasoning_effort=`"$REASONING`"" `
  -o output.txt "PROMPT"
$content = Get-Content -Path output.txt -Raw

# Method 2: Parse JSONL event stream
$jsonl = codex exec --dangerously-bypass-approvals-and-sandbox --skip-git-repo-check --json "PROMPT"
$events = $jsonl -split "`n" | Where-Object { $_ } | ForEach-Object { $_ | ConvertFrom-Json }
$content = $events |
    Where-Object -Property type -EQ "item.completed" |
    Where-Object { $_.item.type -eq "agent_message" } |
    Select-Object -ExpandProperty item |
    Select-Object -ExpandProperty text

Parallel Subagents (Up to 5)

Spawn multiple subagents for independent tasks:

Bash (Linux/macOS)

# Research different topics simultaneously
codex exec --dangerously-bypass-approvals-and-sandbox -m "$MODEL" -c "model_reasoning_effort=\"$REASONING\"" "Research topic A..." &
codex exec --dangerously-bypass-approvals-and-sandbox -m "$MODEL" -c "model_reasoning_effort=\"$REASONING\"" "Research topic B..." &
wait

PowerShell (Windows)

Use PowerShell Jobs for parallel execution with -o to output to separate files:

# Parallel execution with file output
$job1 = Start-Job -ScriptBlock {
    param($m, $r, $out)
    codex exec --dangerously-bypass-approvals-and-sandbox --skip-git-repo-check `
      -m $m -c "model_reasoning_effort=`"$r`"" -o $out "Research topic A..."
} -ArgumentList $MODEL, $REASONING, 
how to use codex-subagent
CursorClaude CodeClineCodexWindsurfGooseGitHub CopilotVS CodeGemini CLIKiloOpencodeKimi CLIRoo ClineAiderContinueZedBolt.newLovablev0Replit AgentSweepSmol DeveloperDevinCavemanAmpAntigravity
How to use codex-subagent on Cursor
AI-first code editor with Composer
1
Prerequisites
Before installing skills in Cursor, ensure your development environment meets these requirements:
›Cursor installed and configured on your development machine
›Node.js version 16.0+ with npm package manager (verify with node --version)
›Active project directory or workspace where you want to add codex-subagent
2
Execute installation command
Execute the skills CLI command in your project's root directory to begin installation:
$npx skills add https://github.com/am-will/codex-skills --skill codex-subagentcopy
The skills CLI fetches codex-subagent from GitHub repository am-will/codex-skills and configures it for Cursor.
3
Select Cursor when prompted
The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:
◆ Which agents do you want to install to?
│
│ ── Universal (.agents/skills) ── always included ────
│   • Amp
│   • Antigravity
│   • Cline
│   • Codex
│ ●Cursor(selected)
│   • Cursor
│   • Windsurf
4
Verify installation
Confirm successful installation by checking the skill directory location:
.cursor/skills/codex-subagent
Reload or restart Cursor to activate codex-subagent. Access the skill through slash commands (e.g., /codex-subagent) or your agent's skill management interface.
⚠
Security & Verification Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.
Additional Resources
›View source code on GitHub›Skills CLI documentation›Learn more about Cursor›What are agent skills?