pave-init
v2.6.2Native Codex package for PAVE Init: graph design, evidence-backed review, generated workflow plugins, and long-run alignment hooks.
By jinhuang121 GitHub starsUpdated 2 days ago
Directory evidence
- Runtimes
- Codex and Claude Code
- Parsed components
- 2 skill or MCP entries
- Source updated
- Sep 21, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install pave-init for Codex and Claude Code
codex plugin marketplace add IchenDEV/agent-plugin-mkt
codex plugin marketplace upgrade agent-plugin-marketplace
codex plugin add pave-init@agent-plugin-marketplacePaste and run these commands in a terminal with Codex. They add and refresh the PluginsMP catalog, then install this plugin.
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/jinhuang12/paveClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.
Plugin files
├── .codex-plugin/plugin.json├── .claude-plugin/plugin.json├── skills/pave-evolve/SKILL.md└── skills/pave-init/SKILL.md
Included Skills2
Revise a delivered PAVE workflow — pave-init included — from recorded defect and usage evidence: a workflow-updater drafts a successor patch, an update-reviewer judges it, the user approves where the user-only changes moved, and the lead applies it in the append-only revision log. Manual-only: use only when the user explicitly invokes /pave-evolve, or when a PAVE lead routes here from a run paused on a defect in its own graph. Registers no hooks.
Create a PAVE-based Claude Code workflow plugin from a goal the user states. Manual-only: use only when the user explicitly invokes /pave-init. This long campaign clarifies the goal, explores the system, designs and reviews a PAVE graph, and builds and tests the plugin. It registers five disclosed hooks: stop alignment and a stale run-state reminder live in this skill's frontmatter (lead-only); the planning layout warning, the write-for-the-reader reminder, and a goal-restatement prompt (at session resume, after compaction, and at each seat's start) live in the plugin's hooks.json so they also reach subagents. While a run is active, the stop check blocks at most one stop in three; nothing registers silently.
Plugin manifests2
{
"name": "pave-init",
"version": "2.6.2",
"description": "Native Codex package for PAVE Init: graph design, evidence-backed review, generated workflow plugins, and long-run alignment hooks.",
"skills": "./codex/skills/",
"hooks": "./codex/hooks/hooks.json"
}{
"name": "pave-init",
"version": "2.6.2",
"description": "PAVE Init as a Claude Code plugin: the pave-init skill plus its dispatched agent roles registered as agent types.",
"author": {
"name": "jinhuang12"
}
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[pave-init on Agent Plugins Marketplace](https://pluginsmp.com/plugins/pave-init)