Skip to content
Back to skills

Codex Template Activation

ASecurity

Activate a Hamster-built or otherwise applied John template for Codex in the current project. Use when a merged template plugin already exists, when the user asks to use a John template in Codex, or after template apply has produced a Claude `--plugin-dir` path and Codex needs the same overrides, additions, guidance, and agents.

  • 9 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added August 31, 2026
ai-agentspythonrustgit

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned August 31, 2026

npx -y skills add kitchen-engineer42/joharnessburg --skill codex-template-activation --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Codex Template Activation?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Codex Template Activation
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/kitchen-engineer42-codex-template-activation/badge)](https://www.skillsdirectory.com/skills/kitchen-engineer42-codex-template-activation)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: codex-template-activation
description: Activate a Hamster-built or otherwise applied John template for Codex in the current project. Use when a merged template plugin already exists, when the user asks to use a John template in Codex, or after template apply has produced a Claude `--plugin-dir` path and Codex needs the same overrides, additions, guidance, and agents.
---

# Codex template activation

Keep Claude's `apply.sh` and `claude --plugin-dir` flow unchanged. Activate its
merged result for Codex through project-local state:

```sh
python3 "<john-plugin>/scripts/activate_codex_template.py" \
  --merged-plugin "<applied-plugin-path>" \
  --project-root "<user-project>"
```

Read the JSON response. Report the installed/skipped agent names and reproduce
every instruction exactly. The script materializes the plugin under
`.john-codex/plugins/<template>/`, merges `.agents/plugins/marketplace.json`,
and adds `.john-codex/` to the repository-local Git exclude when possible.

The printed handoff verifies the installed listing, disables vanilla John for
this project, enables the applied listing, reviews and trusts its current hook
definition through `/hooks`, and restarts Codex. Treat all five as required;
installation alone neither enables the correct project state nor trusts hooks.

Do not edit a personal marketplace or global enablement automatically. Explain
that applied John replaces vanilla John for this project session; enabling both
creates duplicate hooks and ambiguous methodology.

Use `--force` only to rebuild a directory carrying John's activation marker.
The script rejects traversal, symlinks, and unmarked destinations, and restores
the prior activation and marketplace if publication fails.

Files in this skill

  • SKILL.md1.7 KB
  • agents/openai.yaml246 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.