Menu
Internal helper contract for calling the codex-companion runtime from Claude Code
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Comprehensive guide for Terraform code style, formatting, and best practices based on HashiCorp's official standards and Azure Verified Modules (AVM) requirements. Use when writing or reviewing Terraform configurations, formatting code, organizing files and modules, establishing team conventions, managing version control, ensuring code quality and consistency across infrastructure projects, or developing Azure Verified Modules.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Design engineering for Codex. Build interfaces with craft, memory, and enforcement. Maintains consistent design decisions across sessions - make choices once, enforce them automatically.
Implement plan using concurrent opus agents and verify completion
Deterministic integration test coverage analysis using off-the-shelf tooling. Use this skill whenever the user asks about test coverage, coverage gaps, untested code, what needs testing, or wants to improve integration test coverage. Also trigger when the user says 'run coverage', 'check coverage', 'coverage report', 'what's untested', 'find gaps', or has just implemented a feature and wants to know what integration tests are missing. This skill runs real tools and produces data-driven reports — not guesswork.
use this skill once completed all testing to create PR and automerge once gha issues are resolved
Based on SOC occupation classification
| name | codex-cli-runtime |
| description | Internal helper contract for calling the codex-companion runtime from Claude Code |
| user-invocable | false |
Use this skill only inside the codex:codex-rescue subagent.
Primary helper:
node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-companion.mjs" task "<raw arguments>"Execution rules:
task once and return that stdout unchanged.git, direct Codex CLI strings, or any other Bash activity.setup, review, adversarial-review, status, result, or cancel from codex:codex-rescue.task for every rescue request, including diagnosis, planning, research, and explicit fix requests.gpt-5-4-prompting skill to rewrite the user's request into a tighter Codex prompt before the single task call.--effort unset unless the user explicitly requests a specific effort.--model only when the user explicitly asks for one.spark to --model gpt-5.3-codex-spark.--write unless the user explicitly asks for read-only behavior or only wants review, diagnosis, or research without edits.Command selection:
task invocation per rescue handoff.--background or --wait, treat that as Claude-side execution control only. Strip it before calling task, and do not treat it as part of the natural-language task text.--model, normalize spark to gpt-5.3-codex-spark and pass it through to task.--effort, pass it through to task.--resume, strip that token from the task text and add --resume-last.--fresh, strip that token from the task text and do not add --resume-last.--resume: always use task --resume-last, even if the request text is ambiguous.--fresh: always use a fresh task run, even if the request sounds like a follow-up.--effort: accepted values are none, minimal, low, medium, high, xhigh.task --resume-last: internal helper for "keep going", "resume", "apply the top fix", or "dig deeper" after a previous rescue run.Safety rules:
codex:codex-rescue unless the user explicitly asks for read-only behavior.task command exactly as-is.