Run any Skill in Manus with one click

codex-cli-reference

Stars1

Forks0

UpdatedMay 29, 2026 at 20:56

Reference documentation for invoking Codex through the wrapper scripts. This skill should be used when calling Codex, invoking Codex CLI, delegating tasks to Codex, running Codex in background, or managing Codex sessions. Covers codex-start.sh, codex-wait.sh, codex-get-session-id.sh, query file handling, and session management.

Installation

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.

Run Skill in Manus

Source

hughescr

hughescr/claude-code-config

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

File Explorer

2 files

SKILL.md

readonly

name	codex-cli-reference
description	Reference documentation for invoking Codex through the wrapper scripts. This skill should be used when calling Codex, invoking Codex CLI, delegating tasks to Codex, running Codex in background, or managing Codex sessions. Covers codex-start.sh, codex-wait.sh, codex-get-session-id.sh, query file handling, and session management.

Codex Invocation Reference

Quickstart for invoking OpenAI Codex through the Claude Code wrapper scripts.

⛔ Critical Rules

NEVER use heredocs for file creation — they are blocked by hooks. Use the Write tool.

NEVER invoke codex exec directly — always use the wrapper scripts.

Workflow

Create query file — mktemp /tmp/claude/codex-query.XXXXXX
Write query — Write({ file_path, content }) (NOT heredoc)
Start Codex — codex-start.sh <workdir> <query-file> [session-id] → prints RUNDIR
Wait for completion — codex-wait.sh <rundir>; repeat until exit 0 (any nonzero = call again)
Read the response — it is the stdout of codex-wait.sh (the extracted agent reply). The <rundir>/output file is raw JSONL for debugging only.
Get session ID (for follow-ups) — codex-get-session-id.sh <rundir>

Minimal Session Example

Bash({ command: "mktemp /tmp/claude/codex-query.XXXXXX" })
# → /tmp/claude/codex-query.a1B2c3

Write({ file_path: "/tmp/claude/codex-query.a1B2c3", content: "Analyze the codebase" })

Bash({
  command: "~/.claude/scripts/codex/codex-start.sh /path/to/workspace /tmp/claude/codex-query.a1B2c3",
  dangerouslyDisableSandbox: true
})
# → /tmp/claude/codex.X1y2Z3   (RUNDIR)

Bash({
  command: "~/.claude/scripts/codex/codex-wait.sh /tmp/claude/codex.X1y2Z3",
  dangerouslyDisableSandbox: true
})
# exit 0 → stdout IS the agent's response. Any nonzero → call again.

Bash({
  command: "~/.claude/scripts/codex/codex-get-session-id.sh /tmp/claude/codex.X1y2Z3",
  dangerouslyDisableSandbox: true
})
# → 019e7072-675a-7312-b0dc-a040ab91cda9   (UUID session id, for resume)

dangerouslyDisableSandbox: true is required for all three scripts (stryker-incremental.json and the lock dir are sandbox-protected).

For per-script parameter tables, output format, resume/session details, and troubleshooting, see reference.md.

More from this repository

same repository

browsing-bluesky

hughescr/claude-code-config

Browse Bluesky content via API and firehose - search posts, fetch user activity, sample trending topics, read feeds and lists, analyze and categorize accounts. Supports authenticated access for personalized feeds. Use for Bluesky research, user monitoring, trend analysis, feed reading, firehose sampling, account categorization.

2026-05-291

plan-review

hughescr/claude-code-config

Use when explicitly asked to walk through a plan or list of issues one-by-one, with the user deciding each via AskUserQuestion. Triggers only on a request to review/triage a plan interactively — NOT on any casual mention of a feature, fix, or bug.

2026-05-291

review-changes

hughescr/claude-code-config

Use after implementation is complete and lint/tests pass to run a multi-agent review of uncommitted changes. Delegates to multiple perspectives (Codex, code reviewer, code architect, project-steward) checking for bugs, wiring/call-graph, dead code, and long-term project alignment.

2026-05-291

hugo-fundamentals

hughescr/claude-code-config

This skill should be used when the user mentions "hugo basics", "hugo config", "hugo commands", "project structure", "hugo setup", "hugo.toml", "config.toml", "hugo serve", "hugo build", "content directory", "layouts directory", "static directory", "assets directory", "hugo configuration", "module mounts", "hugo environment", ".Site.Author", "author config", "site params", or any general Hugo static site generator questions. Provides foundational Hugo knowledge including project structure, configuration patterns, essential commands, and migration guidance for deprecated features.

2026-02-211

stryker-mutation-testing

hughescr/claude-code-config

This skill should be used when the user mentions "stryker", "mutation testing", "mutant", "mutation score", "survived mutant", "NoCoverage", "stryker disable", "mutation report", "equivalent mutant", "stryker incremental", "stryker cache", or any mutation testing of JavaScript/TypeScript code. Provides comprehensive Stryker mutation testing patterns, disable comment syntax, and strategies for handling survived mutants and NoCoverage results.

2026-02-211

testing-standards

hughescr/claude-code-config

This skill should be used when the user mentions "write tests", "unit test", "fake timers", "mock timers", "test setTimeout", "test setInterval", "flaky tests", "test timing", "test concurrency", "mutation testing quality gate", "test quality", or any testing of JavaScript/TypeScript code. Provides mandatory standards for testing time-dependent code and mutation testing as a secondary quality gate.

2026-02-211

name	codex-cli-reference
description	Reference documentation for invoking Codex through the wrapper scripts. This skill should be used when calling Codex, invoking Codex CLI, delegating tasks to Codex, running Codex in background, or managing Codex sessions. Covers codex-start.sh, codex-wait.sh, codex-get-session-id.sh, query file handling, and session management.

Codex Invocation Reference

Quickstart for invoking OpenAI Codex through the Claude Code wrapper scripts.

⛔ Critical Rules

NEVER use heredocs for file creation — they are blocked by hooks. Use the Write tool.

NEVER invoke codex exec directly — always use the wrapper scripts.

Workflow

Create query file — mktemp /tmp/claude/codex-query.XXXXXX
Write query — Write({ file_path, content }) (NOT heredoc)
Start Codex — codex-start.sh <workdir> <query-file> [session-id] → prints RUNDIR
Wait for completion — codex-wait.sh <rundir>; repeat until exit 0 (any nonzero = call again)
Read the response — it is the stdout of codex-wait.sh (the extracted agent reply). The <rundir>/output file is raw JSONL for debugging only.
Get session ID (for follow-ups) — codex-get-session-id.sh <rundir>

Minimal Session Example

Bash({ command: "mktemp /tmp/claude/codex-query.XXXXXX" })
# → /tmp/claude/codex-query.a1B2c3

Write({ file_path: "/tmp/claude/codex-query.a1B2c3", content: "Analyze the codebase" })

Bash({
  command: "~/.claude/scripts/codex/codex-start.sh /path/to/workspace /tmp/claude/codex-query.a1B2c3",
  dangerouslyDisableSandbox: true
})
# → /tmp/claude/codex.X1y2Z3   (RUNDIR)

Bash({
  command: "~/.claude/scripts/codex/codex-wait.sh /tmp/claude/codex.X1y2Z3",
  dangerouslyDisableSandbox: true
})
# exit 0 → stdout IS the agent's response. Any nonzero → call again.

Bash({
  command: "~/.claude/scripts/codex/codex-get-session-id.sh /tmp/claude/codex.X1y2Z3",
  dangerouslyDisableSandbox: true
})
# → 019e7072-675a-7312-b0dc-a040ab91cda9   (UUID session id, for resume)

dangerouslyDisableSandbox: true is required for all three scripts (stryker-incremental.json and the lock dir are sandbox-protected).

For per-script parameter tables, output format, resume/session details, and troubleshooting, see reference.md.