codex-companion（Codex companion 搜索）

Run the Codex companion runtime for $ARGUMENTS.

Script path:

$SKILL_DIR/scripts/codex-companion.mjs

Quick Start

node "$SKILL_DIR/scripts/codex-companion.mjs" review --base main       # 1. Review changes
node "$SKILL_DIR/scripts/codex-companion.mjs" task "fix the bug"       # 2. Delegate work
node "$SKILL_DIR/scripts/codex-companion.mjs" status                   # 3. Check progress
node "$SKILL_DIR/scripts/codex-companion.mjs" result <job-id>          # 4. Get output

When to Use This vs the codex Skill

Prerequisites

1. Verify Codex CLI is installed.

- Bash / zsh: command -v codex - PowerShell: Get-Command codex - If missing, tell the user to install it: npm install -g @openai/codex

1. If Codex is installed but not authenticated, run codex login.

- If browser login is blocked, retry with codex login --device-auth or codex login --with-api-key

Mode Router

Choose one primary subcommand:

If the user asks to "continue", "resume", "keep going", or "follow up" on prior Codex work, prefer task --resume-last.

Default Command Forms

Set a helper variable first when the session is command-heavy.

Bash / zsh

COMPANION="$SKILL_DIR/scripts/codex-companion.mjs"

PowerShell

$COMPANION = "$SKILL_DIR/scripts/codex-companion.mjs"

Then use:

node "$COMPANION" review --base main
node "$COMPANION" adversarial-review --base main
node "$COMPANION" task "investigate why the flaky test started failing"
node "$COMPANION" task --write "apply the smallest safe fix for the failing test"
node "$COMPANION" task --background --write "implement the approved refactor"
node "$COMPANION" task --resume-last "continue from the latest task and finish the next highest-value step"
node "$COMPANION" status
node "$COMPANION" result <job-id>
node "$COMPANION" cancel <job-id>

Execution Rules

• Prefer review or adversarial-review before task --write when the user wants validation first.
• Keep review and adversarial-review read-only. Do not turn findings into fixes unless the user separately asks for a write-capable task.
• Use task --write only when the user explicitly wants Codex to modify files.
• Use task --background for long-running or open-ended work.
• When the user did not explicitly ask for backgrounding, keep clearly bounded work in the foreground.
• If result shows touched files, inspect the diff or run follow-up verification before claiming the work is complete.

Structured Output

All commands support --json for machine-readable output. The adversarial review returns findings matching the schema in $SKILL_DIR/schemas/review-output.schema.json:

• verdict: approve or needs-attention
• findings[]: each with severity, title, body, file, line_start, line_end, confidence, recommendation
• summary: terse ship/no-ship assessment
• next_steps: suggested follow-up actions

Prompting

For delegated task runs, prefer compact, block-structured prompts. Read:

• $SKILL_DIR/references/COMMANDS.md for the full command surface and exit codes
• $SKILL_DIR/references/PROMPTING.md for prompt contracts and XML block patterns

Error Recovery

Notes

• The companion runtime stores per-workspace job state under the OS temp directory by default ($TMPDIR/codex-companion/).
• status, result, and cancel operate on those persisted job records.
• The companion skill deliberately does not implement Claude-only hooks or stop-time review gates.
• Maximum 50 jobs retained per workspace; older jobs are pruned automatically.