stackwich
v3.0.0Delivery discipline for AI coding agents. Writes the five-layer Stackwich policy (Prompt / Context / Harness / Loop / Graph) into CLAUDE.md and scaffolds advisor, executor and verifier subagents.
By Abhirup BanerjeeLicense: MIT1 GitHub starsUpdated last week
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 1 skill or MCP entry
- Source updated
- Sep 15, 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 stackwich for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install stackwich@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/ovhirup/stackwichClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/stackwich/.
Plugin files
├── .claude-plugin/plugin.json└── skills/stackwich/SKILL.md
Included Skills1
Installs the Stackwich architecture — meta-prompt delegation, a plan/execute/verify/review sandwich, loop-by-default for recurring work, and fork-based context engineering — into any Claude Code setup. Writes the operating policy into CLAUDE.md and optionally scaffolds three companion subagents (advisor/executor/verifier). Use this whenever the user wants to adopt, install, bootstrap, upgrade, or re-apply this delegation architecture on a new machine, project, or someone else's setup — and also when they ask more loosely for help making their Claude Code setup more disciplined, setting up planner/executor/reviewer subagents, adding a review gate before risky changes, enforcing cheap-model tiering, or fixing agents that make sloppy or out-of-scope edits.
Plugin manifests1
{
"name": "stackwich",
"version": "3.0.0",
"description": "Delivery discipline for AI coding agents. Writes the five-layer Stackwich policy (Prompt / Context / Harness / Loop / Graph) into CLAUDE.md and scaffolds advisor, executor and verifier subagents.",
"author": {
"name": "Abhirup Banerjee"
},
"homepage": "https://github.com/ovhirup/stackwich",
"repository": "https://github.com/ovhirup/stackwich",
"license": "MIT",
"keywords": [
"workflow",
"subagents",
"code-review",
"delegation",
"verification"
]
}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.
[stackwich on Agent Plugins Marketplace](https://pluginsmp.com/plugins/stackwich)