jia-ethan/codex-keysmith

Versioned Codex instruction deployment with preview, ownership manifests, hook isolation, scenario evaluation, and recovery.

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 49 minutes ago
Added to GitGenius on September 15th, 2026
Created on June 28th, 2026
Open Issues & Pull Requests: 6 (+0)
GitHub issues: Enabled
Number of forks: 715
Total Stargazers: 4,551 (+1)
Total Subscribers: 9 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 7.7 hours
Mean response time: 35.2 hours
90th percentile: 5.9 days
Tracked items: 18

Most active contributors

Sign in to see contributor activity.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 6
New in 7 days: 2
Closed in 7 days: 0
Avg open age: 12 days
Stale 30+ days: 2
Stale 90+ days: 0

Recent activity

Opened in 7 days: 2
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

  • documentation (1)
  • enhancement (1)

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

Codex-keysmith is a command-line tool for versioned instruction deployment to local Codex AI programming environments.

The tool addresses the problem of safely managing custom instructions for Codex by providing a preview-before-apply workflow. It allows developers to stage instruction changes, review them in a dry-run mode, confirm deployment, and later revert changes if needed. The approach works by modifying Codex configuration locally without altering the Codex software itself or accessing account credentials. Instructions take effect in new conversation sessions opened after deployment.

Developers should choose this tool if they work with Codex locally and want to maintain versioned, reversible instruction sets across sessions. It suits projects where instruction consistency matters but experimentation and rollback capability are equally important. The tool is designed for local-first workflows and does not require integration with external systems. The README identifies related tools for other AI environments including Claude Code, Grok Build, and ZCode, each with their own corresponding keysmith variant.

The project maintains active test coverage through continuous integration workflows. Development follows a structured approach to feature implementation, with explicit handling of deployment scenarios and recovery paths built into the core design.