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

1.61x

Quality

46%

Does it follow best practices?

Impact

95%

1.61x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./generated-skills/codex-cli-bridge/SKILL.md

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%

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%

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%

Repository: thinmintdev/claude-cooker
Commit: e5df233

Evaluated: 18 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

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.