Agent skill

Collaborating With Codex

by cnfjlhj in cnfjlhj/ai-collab-playbook

A skill your agent uses when you explicitly want a second local or SSH remote Codex CLI session to prototype, debug, or review code, while your current session remains the primary owner of the final…

MITAuto-check passedDevelopment

Install Collaborating With Codex

skills CLI
$ npx skills add cnfjlhj/ai-collab-playbook --skill collaborating-with-codex -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install cnfjlhj/ai-collab-playbook collaborating-with-codex --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/cnfjlhj/ai-collab-playbook.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/full/collaborating-with-codex .claude/skills/collaborating-with-codex && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
collaborating-with-codex
GitHub stars
453
Token cost
~1.4k tokens
SKILL.md length
234 words
Files
4 (incl. scripts)
Skills in repo
17
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when you explicitly want a second local or SSH remote Codex CLI session to prototype, debug, or review code, while your current session remains the primary owner of the final…

  • You explicitly want a second local
  • SKILL.md covers Quick Start, Collaboration Rules, Parameters and Multi-turn Sessions, plus 2 more sections
  • Runs Python scripts from its folder; calls python, codex and ssh
  • SSH remote Codex CLI session to prototype

What it does

Collaborating With Codex is an agent skill from cnfjlhj/ai-collab-playbook. Use when you explicitly want a second local or SSH remote Codex CLI session to prototype, debug, or review code, while your current session remains the primary owner of the final result.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `README.md` and `scripts/codex_bridge.py`).

It sits in Development, covering Code review. The repository describes itself as: Practical AI collaboration playbook for research, writing, reading, and coding: article, prompts, agent rules, and reusable skills. The licence is MIT.

When your agent uses it

  • You explicitly want a second local
  • SSH remote Codex CLI session to prototype
  • While your current session remains the primary owner of the final result

Example prompts

  • “/collaborating-with-codex”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit b3ee0d6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python
    • codex
    • ssh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use ssh, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Collaborating With Codex loads about 1.4k tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 234 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from cnfjlhj/ai-collab-playbook at commit b3ee0d6, republished under its MIT licence (© cnfjlhj). 234 words, ~1,428 tokens.

Download SKILL.mdSave it as .claude/skills/collaborating-with-codex/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
collaborating-with-codex
description
Use when you explicitly want a second local or SSH remote Codex CLI session to prototype, debug, or review code, while your current session remains the primary owner of the final result.

Quick Start

bash
python scripts/codex_bridge.py --cd "/path/to/project" --PROMPT "Your task"

Remote Codex over SSH:

bash
python scripts/codex_bridge.py --ssh "server-alias" --cd "/remote/project" --PROMPT "Your task"

Output: JSON with success, SESSION_ID, agent_messages, and optional error.

Collaboration Rules

  • Keep the current session responsible for scope, synthesis, final edits, and verification.
  • Delegate a bounded task with a concrete output contract such as a diff, diagnosis, or review note.
  • Avoid overlapping write scope between sessions unless the second session is review-only.
  • Start with read-only access; expand the sandbox only when the delegated task requires it.
  • Do not set model or profile overrides unless the user explicitly asked for them.

Parameters

usage: codex_bridge.py [-h] --PROMPT PROMPT --cd CD [--sandbox {read-only,workspace-write,danger-full-access}] [--SESSION_ID SESSION_ID] [--skip-git-repo-check]
                       [--return-all-messages] [--image IMAGE] [--model MODEL] [--yolo] [--profile PROFILE] [--ssh SSH] [--ssh-option SSH_OPTION]
                       [--codex-bin CODEX_BIN]

Codex Bridge

options:
  -h, --help            show this help message and exit
  --PROMPT PROMPT       Instruction for the task to send to codex.
  --cd CD               Set the workspace root for codex before executing the task.
  --sandbox {read-only,workspace-write,danger-full-access}
                        Sandbox policy for model-generated commands. Defaults to `read-only`.
  --SESSION_ID SESSION_ID
                        Resume the specified session of the codex. Defaults to `None`, start a new session.
  --skip-git-repo-check
                        Allow codex running outside a Git repository (useful for one-off directories).
  --return-all-messages
                        Return all messages (e.g. reasoning, tool calls, etc.) from the codex session. Set to `False` by default, only the agent's final reply message is
                        returned.
  --image IMAGE         Attach one or more image files to the initial prompt. Separate multiple paths with commas or repeat the flag.
  --model MODEL         The model to use for the codex session. This parameter is strictly prohibited unless explicitly specified by the user.
  --yolo                Run every command without approvals or sandboxing. Only use when `sandbox` couldn't be applied.
  --profile PROFILE     Configuration profile name to load from `~/.codex/config.toml`. This parameter is strictly prohibited unless explicitly specified by the user.
  --ssh SSH             Run Codex on a remote host via SSH. Value can be an SSH alias or user@host. When set, --cd and --image paths are remote paths.
  --ssh-option SSH_OPTION
                        Extra ssh option, repeatable. Example: --ssh-option=-J --ssh-option=bastion
  --codex-bin CODEX_BIN
                        Codex executable to run locally or on the remote host. Defaults to `codex`. `--remote-codex` is accepted as a backward-compatible alias.

Multi-turn Sessions

Always capture SESSION_ID from the first response for follow-up:

bash
# Initial task
python scripts/codex_bridge.py --cd "/project" --PROMPT "Analyze auth in login.py"

# Continue with SESSION_ID
python scripts/codex_bridge.py --cd "/project" --SESSION_ID "uuid-from-response" --PROMPT "Write unit tests for that"

Remote sessions use the same SESSION_ID, but continue them against the same SSH host:

bash
python scripts/codex_bridge.py --ssh "server-alias" --cd "/remote/project" --SESSION_ID "uuid-from-response" --PROMPT "Now implement it"

SSH Remote Codex

Use --ssh when the repository, runtime, or credentials needed for the task live on a remote server.

Requirements:

  • Local machine can run ssh <host> non-interactively.
  • Remote host has codex installed and available in the remote non-interactive shell PATH, or pass --codex-bin "/absolute/path/to/codex".
  • The remote host should use a POSIX-compatible shell for command quoting.
  • --cd is a remote absolute path when --ssh is set.
  • --image paths are also remote paths when --ssh is set. Upload local images first if Codex on the server needs them.

Examples:

bash
# Use an SSH config alias
python scripts/codex_bridge.py --ssh "gpu-box" --cd "/srv/app" --PROMPT "Review this service for race conditions"

# Use user@host and a remote codex path
python scripts/codex_bridge.py --ssh "ubuntu@example.com" --codex-bin "/home/ubuntu/.local/bin/codex" --cd "/home/ubuntu/app" --PROMPT "Run the failing tests and diagnose"

# Use a jump host
python scripts/codex_bridge.py --ssh "private-box" --ssh-option=-J --ssh-option=bastion --cd "/workspace/repo" --PROMPT "Inspect the deployment scripts"

Do not use --ssh for local repositories. Do not pass --model or --profile unless the user explicitly requested them.

Common Patterns

Prototyping (read-only, request diffs):

bash
python scripts/codex_bridge.py --cd "/project" --PROMPT "Generate unified diff to add logging"

Debug with full trace:

bash
python scripts/codex_bridge.py --cd "/project" --PROMPT "Debug this error" --return-all-messages

Remote debug with write access:

bash
python scripts/codex_bridge.py --ssh "server-alias" --cd "/remote/project" --sandbox workspace-write --PROMPT "Fix the failing integration test and summarize the patch"

© cnfjlhj, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts) in skills/full/collaborating-with-codex of cnfjlhj/ai-collab-playbook.

  • SKILL.md
  • LICENSE
  • README.md
  • scripts/codex_bridge.py

Open the folder on GitHubat commit b3ee0d6

Compare with similar skills

Collaborating With Codex next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Collaborating With Codex compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Collaborating With Codex this skillcnfjlhj/ai-collab-playbook453—~1.4kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT
Backend Code Reviewlangflow-ai/langflow155k—~3.5kAutomated safety check: NotesMIT
Mole Bug Patternstw93/Mole70k—~2kAutomated safety check: PassGPL-3.0
Backend Code Reviewlanggenius/dify158k—~676Automated safety check: PassCustom licence

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Backend Code Review

    langflow-ai/langflow

    Review backend code for quality, security, maintainability, and best practices based on established checklist rules.

    155k GitHub stars~3.5k tokensUpdated today
    DevelopmentAuto-check: notes
  • A catalog of recurring bug shapes in the Mole Mac cleaner, used to review safety-sensitive diffs for deletion safety, unbounded commands, shell traps and weak tests.

    70k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed
  • Backend Code Review

    langgenius/dify

    Reviews backend code under api/ for concrete, reproducible defects, routes to rule packs for architecture, schema, repositories and SQLAlchemy, and ranks findings from P0 to P3.

    158k GitHub stars~676 tokensUpdated today
    DevelopmentAuto-check passed
  • WooCommerce Code Review

    woocommerce/woocommerce

    Reviews WooCommerce code changes against the project's standards, flagging backend PHP architecture, naming, documentation, data integrity and testing violations.

    11k GitHub starsUsed in 3 repos~1.1k tokens
    DevelopmentAuto-check passed

More from cnfjlhj/ai-collab-playbook

All 17 skills in this repo
  • Paper2html

    cnfjlhj/ai-collab-playbook

    A skill your agent uses when turning an academic paper PDF/arXiv/OpenReview page/local LaTeX source into a single-file Chinese HTML deep-reading page, especially when the user wants a Cheat-Sheet…

    453 GitHub stars~2.4k tokensUpdated 25 days ago
    Auto-check passed
  • Xhs Longform Private Publisher

    cnfjlhj/ai-collab-playbook

    This skill should be used when the user wants to publish an existing Markdown article to Xiaohongshu as a private longform post, keep the original wording and structure, insert inline images in…

    453 GitHub stars~1.1k tokensUpdated 25 days ago
    Auto-check passed
  • Paperreview

    cnfjlhj/ai-collab-playbook

    A skill your agent uses when the user explicitly wants to upload a final or near-final PDF to paperreview.ai for an external second opinion.

    453 GitHub stars~668 tokensUpdated 25 days ago
    Auto-check passed
  • Research Lead Sidecar

    cnfjlhj/ai-collab-playbook

    A skill your agent uses when the user wants multi-agent division of labor for research-led work and the lead should stay on the critical path while 1-2 bounded sidecars handle low-coupling tasks.

    453 GitHub stars~842 tokensUpdated 25 days ago
    Auto-check passed
  • Xhs Note Creator

    cnfjlhj/ai-collab-playbook

    A skill your agent uses when the user wants Xiaohongshu note materials such as the note text, cover card, body cards, or publishing-ready assets.

    453 GitHub stars~638 tokensUpdated 25 days ago
    Auto-check: notes
  • Skill Governance Loop

    cnfjlhj/ai-collab-playbook

    A skill your agent uses when the user asks to review a skill, analyze skill quality, update or align a skill version, compare local state against a newer variant, or run a repeatable…

    453 GitHub stars~468 tokensUpdated 25 days ago
    Auto-check passed

Categories

Questions about Collaborating With Codex

What does Collaborating With Codex do?

A skill your agent uses when you explicitly want a second local or SSH remote Codex CLI session to prototype, debug, or review code, while your current session remains the primary owner of the final…. Collaborating With Codex is an agent skill from cnfjlhj/ai-collab-playbook. Use when you explicitly want a second local or SSH remote Codex CLI session to prototype, debug, or review code, while your current session remains the primary owner of the final result.

When should I use Collaborating With Codex?

Collaborating With Codex fits situations like: you explicitly want a second local; SSH remote Codex CLI session to prototype; while your current session remains the primary owner of the final result.

How do I install Collaborating With Codex in Claude Code?

Run `npx skills add cnfjlhj/ai-collab-playbook --skill collaborating-with-codex -a claude-code`. Or copy the skill folder (skills/full/collaborating-with-codex in cnfjlhj/ai-collab-playbook) into .claude/skills/collaborating-with-codex in your project. Claude Code loads it when a task matches its description.

How do I install Collaborating With Codex in Codex?

Run `npx skills add cnfjlhj/ai-collab-playbook --skill collaborating-with-codex -a codex`. Or copy the skill folder (skills/full/collaborating-with-codex in cnfjlhj/ai-collab-playbook) into .agents/skills/collaborating-with-codex in your project. Codex loads it when a task matches its description.

Can I use Collaborating With Codex in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cnfjlhj/ai-collab-playbook --skill collaborating-with-codex -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/collaborating-with-codex, .gemini/skills/collaborating-with-codex, .github/skills/collaborating-with-codex and .opencode/skills/collaborating-with-codex in your project.

What does Collaborating With Codex need to run?

Going by SKILL.md and its folder, Collaborating With Codex needs Python for the scripts in its folder and the command-line tools its instructions call (python, codex and ssh). Our summary lists: Python 3.

Does Collaborating With Codex access the network?

SKILL.md contains no URLs. Its commands use ssh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Collaborating With Codex safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Collaborating With Codex use?

Collaborating With Codex is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Collaborating With Codex use?

About 1.4k tokens (SKILL.md is roughly 5.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Collaborating With Codex?

Skills that share tags, products or a category with Collaborating With Codex: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), Backend Code Review (langflow-ai/langflow, 155k stars) and Mole Bug Patterns (tw93/Mole, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Collaborating With Codex?

cnfjlhj (a GitHub user) maintains it in cnfjlhj/ai-collab-playbook, which has 453 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on September 14, 2026.

Source: cnfjlhj/ai-collab-playbook on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.