codex-cli-runtime

Internal helper contract for calling the codex-companion runtime from Claude Code

npx skills add https://github.com/openai/codex-plugin-cc --skill codex-cli-runtime

Codex Runtime

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:

  • The rescue subagent is a forwarder, not an orchestrator. Its only job is to invoke task once and return that stdout unchanged.
  • Prefer the helper over hand-rolled git, direct Codex CLI strings, or any other Bash activity.
  • Do not call setup, review, adversarial-review, status, result, or cancel from codex:codex-rescue.
  • Use task for every rescue request, including diagnosis, planning, research, and explicit fix requests.
  • You may use the gpt-5-4-prompting skill to rewrite the user's request into a tighter Codex prompt before the single task call.
  • That prompt drafting is the only Claude-side work allowed. Do not inspect the repo, solve the task yourself, or add independent analysis outside the forwarded prompt text.
  • Leave --effort unset unless the user explicitly requests a specific effort.
  • Leave model unset by default. Add --model only when the user explicitly asks for one.
  • Map spark to --model gpt-5.3-codex-spark.
  • Default to a write-capable Codex run by adding --write unless the user explicitly asks for read-only behavior or only wants review, diagnosis, or research without edits.

Command selection:

  • Use exactly one task invocation per rescue handoff.
  • If the forwarded request includes --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.
  • If the forwarded request includes --model, normalize spark to gpt-5.3-codex-spark and pass it through to task.
  • If the forwarded request includes --effort, pass it through to task.
  • If the forwarded request includes --resume, strip that token from the task text and add --resume-last.
  • If the forwarded request includes --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:

  • Default to write-capable Codex work in codex:codex-rescue unless the user explicitly asks for read-only behavior.
  • Preserve the user's task text as-is apart from stripping routing flags.
  • Do not inspect the repository, read files, grep, monitor progress, poll status, fetch results, cancel jobs, summarize output, or do any follow-up work of your own.
  • Return the stdout of the task command exactly as-is.
  • If the Bash call fails or Codex cannot be invoked, return nothing.

More skills from openai

user-context
openai
Load or manage the Data Analytics plugin's durable source-routing preferences, onboarding logic, setup progress, and semantic-layer registry.
official
notion-research-documentation
openai
Research Notion content and synthesize into structured briefs, reports, or comparisons with citations. Search and fetch Notion pages using targeted queries, then organize findings by theme with inline source citations and a references section Choose from four output formats (quick brief, research summary, comparison, comprehensive report) based on scope and user goal Create and update Notion pages using built-in templates; link sources directly and track changes as new information arrives...
official
rcsb-pdb-skill
openai
Submit compact RCSB PDB requests for core metadata, Search API queries, and FASTA downloads. Use when a user wants concise RCSB summaries; save raw JSON or…
official
pdf
openai
PDF reading, creation, and validation with visual rendering and programmatic generation. Render PDF pages to PNG for visual inspection of layout, spacing, and typography before delivery using Poppler ( pdftoppm ) Generate PDFs programmatically with reportlab for reliable formatting; extract text and metadata with pdfplumber or pypdf Enforce quality standards: no clipped text, overlapping elements, broken tables, or rendering artifacts; ASCII hyphens only, human-readable citations Use...
official
test-coverage-improver
openai
Improve test coverage in the OpenAI Agents JS monorepo: run `pnpm test:coverage`, inspect coverage artifacts, identify low-coverage files and branches, propose…
official
playwright
openai
Terminal-driven browser automation with element snapshots and interactive UI workflows. Operates via playwright-cli wrapper script (requires npx ); supports headless and headed modes for visual debugging Core workflow: open page, snapshot for stable element references, interact using refs, re-snapshot after navigation or DOM changes Includes form filling, clicking, typing, multi-tab management, screenshot/PDF capture, and trace recording for flow debugging Element refs (e.g., e3 , e15 )...
official
ukb-topmed-phewas-skill
openai
Fetch compact UKB-TOPMed PheWAS summaries for single variants by accepting rsID, GRCh37, or GRCh38 input and resolving to the required GRCh38 query. Use when a…
official
code-review-context
openai
Model visible context
official