codex-cli-bridge

Bridge between Claude Code and OpenAI Codex CLI - generates AGENTS.md from CLAUDE.md, provides Codex CLI execution helpers, and enables seamless interoperability between both tools

Install with Tessl CLI

npx tessl i github:alirezarezvani/claude-code-skill-factory --skill codex-cli-bridge

What are skills?

Review — 46%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 11 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

100%

86%

Codex CLI Python Execution Library

Codex CLI execution helpers

Criteria

Without context

With context

Uses codex exec

100%

Analysis uses gpt-5

100%

Edit uses gpt-5-codex

100%

Analysis uses read-only sandbox

100%

Edit uses workspace-write sandbox

100%

Skip git repo check flag

100%

Reasoning effort high

100%

Search flag present

25%

100%

Session resume command

100%

Danger-full-access sandbox mentioned

100%

Result structure returned

100%

Three distinct helper functions

100%

Without context: $0.5107 · 2m 22s · 19 turns · 25 in / 10,264 out tokens

With context: $0.6481 · 2m 18s · 20 turns · 528 in / 8,399 out tokens

88%

15%

Cross-Tool Documentation Bridge

AGENTS.md reference-based generation

Criteria

Without context

With context

Reference-based, no duplication

80%

90%

Project Overview section

100%

Available Skills section

100%

Workflow Patterns section

85%

100%

Command Reference section

100%

Functional skill: script execution shown

100%

Prompt-only skill: prompt reference shown

70%

100%

codex exec in workflow examples

100%

Correct model in examples

62%

File path references present

100%

MCP Integration section

62%

For Codex CLI users note

100%

Without context: $0.1865 · 53s · 8 turns · 13 in / 2,959 out tokens

With context: $1.5395 · 3m 20s · 44 turns · 550 in / 11,638 out tokens

97%

Project Bridge Validator and Orchestrator

Safety mechanism and bridge workflow

Criteria

Without context

With context

codex --version check

100%

which codex path check

100%

CLAUDE.md existence check

100%

Auto-init on missing CLAUDE.md

90%

100%

User notification on auto-init

100%

Step 1: Safety validation

100%

Step 2: Project analysis

100%

Step 3: AGENTS.md generation

100%

Step 4: Write to project root

100%

Validation failure stops workflow

100%

validate-only mode

100%

Status report output

83%

100%

No auto-init option

50%

Without context: $0.3807 · 1m 35s · 19 turns · 25 in / 6,388 out tokens

With context: $0.7131 · 1m 56s · 25 turns · 533 in / 6,774 out tokens

Evaluated: about 13 hours ago
Agent: Claude Code

Table of Contents

Codex CLI Python Execution Library Cross-Tool Documentation Bridge Project Bridge Validator and Orchestrator

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.