codex-bridge
Dispatch coding tasks to the local OpenAI Codex CLI with background execution, status polling, and answerable clarifying questions. Use when OpenClaw should delegate script building, code edits, refactors, or multi-step coding work to Codex from the command line.
Best use case
codex-bridge is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Dispatch coding tasks to the local OpenAI Codex CLI with background execution, status polling, and answerable clarifying questions. Use when OpenClaw should delegate script building, code edits, refactors, or multi-step coding work to Codex from the command line.
Teams using codex-bridge should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/codex-bridge/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How codex-bridge Compares
| Feature / Agent | codex-bridge | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Dispatch coding tasks to the local OpenAI Codex CLI with background execution, status polling, and answerable clarifying questions. Use when OpenClaw should delegate script building, code edits, refactors, or multi-step coding work to Codex from the command line.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
SKILL.md Source
# Codex Bridge Delegate coding tasks from OpenClaw to the local `codex` CLI and manage them asynchronously. This skill provides a file-based bridge so OpenClaw can: - dispatch tasks - poll status and recent output - relay clarifying questions - send answers - collect final results ## When to Use - Build scripts (Python, Bash, etc.) - Implement or refactor code in an existing project - Run larger multi-file coding tasks in the background - Delegate coding work while keeping OpenClaw responsive - Handle tasks that may require clarifying questions mid-run ## When NOT to Use - Quick factual questions or explanations - Small code snippets that OpenClaw can write directly - Non-coding tasks - Tasks that should not invoke a local coding agent/CLI ## Dispatch a Task ```bash ~/.openclaw/skills/codex-bridge/codex-bridge-dispatch.sh \ --task-id <descriptive-name> \ --workdir <project-directory> \ --prompt "<detailed coding task>" ``` ### Prompt Writing Include: - what to build/fix - file paths if known - expected behavior/output - language/framework preferences - constraints (tests, style, no new deps, etc.) Example: ```bash ~/.openclaw/skills/codex-bridge/codex-bridge-dispatch.sh \ --task-id scripts-csv-parser \ --workdir ~/projects/data-tools \ --prompt "Create parse_orders.py. Read orders CSV, keep shipped rows, group by customer_id, and write summary CSV with columns customer_id, order_count, total_amount. Use pandas. Add basic CLI args and error handling." ``` ## Check Status ```bash ~/.openclaw/skills/codex-bridge/codex-bridge-status.sh --task-id <id> ``` Common status commands: ```bash ~/.openclaw/skills/codex-bridge/codex-bridge-status.sh --list ~/.openclaw/skills/codex-bridge/codex-bridge-status.sh --task-id <id> --output ~/.openclaw/skills/codex-bridge/codex-bridge-status.sh --task-id <id> --question ~/.openclaw/skills/codex-bridge/codex-bridge-status.sh --task-id <id> --result ~/.openclaw/skills/codex-bridge/codex-bridge-status.sh --task-id <id> --log ``` ## Answer Clarifying Questions When status is `waiting_for_answer`, read the pending question and send a response: ```bash ~/.openclaw/skills/codex-bridge/codex-bridge-status.sh --task-id <id> --question ~/.openclaw/skills/codex-bridge/codex-bridge-answer.sh --task-id <id> --answer "<answer text>" ``` The bridge resumes the same Codex session after the answer is written. ## Workflow 1. Dispatch task with a clear prompt. 2. Report the task ID. 3. Poll status/output periodically. 4. If status becomes `waiting_for_answer`, read `--question`, relay to user, then write answer with `--answer`. 5. When status is `complete`, read `--result` and summarize outcomes. 6. If status is `error`, inspect `--log` and `--output`. ## Notes and Limits - Uses the local `codex` CLI (`codex exec` and `codex exec resume`). - Clarifying questions are implemented via a lightweight text marker protocol in the prompt wrapper. - Bridge state is stored in `~/.codex-bridge/tasks/<task-id>/`. - Commands run via Codex in the specified `--workdir`. - For unattended runs, the bridge times out after 10 minutes waiting for an answer and resumes with a default/sensible fallback.
Related Skills
cpa-codex-auth-sweep-cliproxy
通过 CLI Proxy Management API 拉取 Codex 认证文件并高并发探活扫描。适用于「扫号」「清死号」「清理 Codex 401」场景；仅在用户明确确认后可删除 401。执行前必须提供 base_url 与 management_key。安全限制：默认仅允许 https://chatgpt.com 作为 probe 主机，非白名单目标需显式危险确认。
deBridge MCP Skill
Enable AI agents to execute non-custodial cross-chain cryptocurrency swaps and transfers via the deBridge protocol.
devops-bridge
Unified developer operations bridge connecting GitHub, CI/CD (GitHub Actions), Slack, Discord, and issue trackers (Linear, Jira, GitHub Issues) into cross-tool automated workflows. Sends context-rich CI failure notifications to Slack with failing test details, tracks PR review lifecycle with escalating reminders, generates daily dev standup summaries, syncs issue status when PRs are merged, detects flaky tests, and monitors repository health. Use this skill for: PR review reminders, CI build alerts, "what happened in my repos", "any failing builds", "who needs a review", dev team standup summary, deploy notifications, repository monitoring, connecting GitHub to Slack, linking PRs to Jira/Linear tickets, code review tracking, merge conflict alerts, or any request to bridge development tools together. If the user mentions GitHub AND Slack (or any two dev tools) together, this skill connects them.
cli-agent-bridge
Public ClawHub text release for a Windows companion skill that bridges local AI CLIs and controlled workspace file operations. This release documents the capability and setup path, but does not include the local PowerShell execution layer.
prestashop_bridge_v1
Secure skill pack for operating a PrestaShop 9 Bridge through a stable, signed, asynchronous API contract.
toybridge
Control any BLE toy that has been reverse-engineered and connected via the ToyBridge server. Calls a local HTTP API to send vibrate/stop commands. Requires the ToyBridge server running on the same machine.
api-bridge
Curated free public APIs for AI agents — geocoding, weather, forex, validation, facts, finance, and test data. Use when an agent needs real-world data without paid API keys.
feishu-bridge
Connect a Feishu (Lark) bot to Clawdbot via WebSocket long-connection. No public server, domain, or ngrok required. Use when setting up Feishu/Lark as a messaging channel, troubleshooting the Feishu bridge, or managing the bridge service (start/stop/logs). Covers bot creation on Feishu Open Platform, credential setup, bridge startup, macOS launchd auto-restart, and group chat behavior tuning.
secretcodex
Generate creative code names and encode/decode secret messages using classic and sophisticated ciphers. Blends nostalgic decoder ring fun with modern cryptographic techniques. Includes Caesar, Vigenère, Polybius, Rail Fence, and hybrid methods. Provides keys for secure message sharing between trusted parties.
cross-disciplinary-bridge-finder
Use when identifying collaboration opportunities across fields, finding experts in complementary disciplines, translating methodologies between scientific domains, or building interdisciplinary research teams. Identifies synergies between scientific disciplines, matches researchers with complementary expertise, and facilitates cross-domain collaborations. Supports interdisciplinary grant applications and innovative research team formation.
quantum-bridge
Transpile quantum circuits between Qiskit (OpenQASM) and OriginIR, run IBC multi-agent consensus, validate OriginIR, and submit circuits to real quantum hardware (Wukong 72Q chip) via the Quantum Bridge API. Use when a user asks to convert quantum circuits, run quantum consensus, submit to quantum hardware, check quantum backends, or work with OriginIR/OpenQASM formats.
codex-cli
Use OpenAI Codex CLI for coding tasks. Triggers: codex, code review, fix CI, refactor code, implement feature, coding agent, gpt-5-codex. Enables Clawdbot to delegate coding work to Codex CLI as a subagent or direct tool.