ai-infra
v0.1.1Scarred universal rules on every session, /init that generates a verified AGENTS.md + permissions + worktree script, /lesson that turns incidents into review traps and then into guards, an adversarial pr-reviewer, a codebase scout.
By Ray Sears0 GitHub starsUpdated 2 weeks ago
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 6 skill or MCP entries
- Source updated
- Sep 7, 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 ai-infra for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install ai-infra@agent-plugin-marketplacePaste and run these commands in a terminal with Claude Code. 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/raysears/ai-infraClone 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
├── .claude-plugin/plugin.json├── skills/grill-me/SKILL.md├── skills/grilling/SKILL.md├── skills/handover/SKILL.md├── skills/init/SKILL.md├── skills/lesson/SKILL.md└── skills/writing-for-agents/SKILL.md
Included Skills6
A relentless interview to sharpen a plan or design.
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Write .claude/state/HANDOFF.md so a fresh session can continue this work.
Detect this project and generate AGENTS.md, .claude/settings.json and scripts/new_worktree.sh, every command verified by running it.
File an incident into AGENTS.md as a dated, costed surprise; promote or delete the oldest when the cap of 7 is hit.
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
Plugin manifests1
{
"$schema": "https://anthropic.com/claude-code/plugin.schema.json",
"name": "ai-infra",
"version": "0.1.1",
"description": "Scarred universal rules on every session, /init that generates a verified AGENTS.md + permissions + worktree script, /lesson that turns incidents into review traps and then into guards, an adversarial pr-reviewer, a codebase scout.",
"author": {
"name": "Ray Sears",
"url": "https://github.com/raysears"
}
}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.
[ai-infra on Agent Plugins Marketplace](https://pluginsmp.com/plugins/ai-infra)