amir
v1.1.0Amir project plugin — project-selected components (harness, cloud/security/network groups, dev tools)
By Amir0 GitHub starsUpdated 2 weeks ago
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 10 skill or MCP entries
- Source updated
- Oct 4, 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 amir for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install amir@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/amirdeadline/amir_marketplaceClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/amir_project/.
Plugin files
├── .claude-plugin/plugin.json├── skills/btw/SKILL.md├── skills/design/SKILL.md├── skills/handoff/SKILL.md├── skills/plan/SKILL.md├── skills/rollback/SKILL.md├── skills/troubleshoot/SKILL.md└── .mcp.json
Included Skills6
Temporary read-only side question; not saved to amir state.
Produce technical architecture and design document `.ai/design.md` driven by the architect agent from approved `project.md`, question inventory, and `.ai/project-goal.md`. The architect leads; the human approves.
Generate a structured pause handoff from template so a fresh orchestrator instance can resume without relying on chat history.
Produce a phased implementation plan, run context-engineering quality review, obtain human approval, and populate `.ai/state/tasks.json`.
Revert project codebase to a prior checkpoint safely. Prefer git revert; allow `git reset --hard` only with explicit typed human confirmation.
Interactive human-controlled troubleshooting (amir marketplace). Read-only diagnostics without approval; state-changing fixes require plan and approval. Slash: /amir:troubleshoot {problem}.
MCP servers4
- command
- uvx
- args
- [email protected] https://aws-mcp.us-east-1.api.aws/mcp --metadata AWS_REGION=${env:AWS_REGION}
- command
- npx
- args
- -y @azure/mcp@latest server start
- command
- npx
- args
- -y mcp-remote ${env:ELASTIC_KIBANA_URL}/api/agent_builder/mcp --header Authorization:${env:ELASTIC_AUTH_HEADER}
- command
- python
- args
- ${CLAUDE_PLUGIN_ROOT}/scripts/litellm/litellm_mcp.py
MCP configuration uses runtime-provided plugin path placeholders such as ${PLUGIN_ROOT} or ${CLAUDE_PLUGIN_ROOT}. Review the manifest for the runtime-specific expansion rules.
Plugin manifests1
{
"name": "amir",
"version": "1.1.0",
"description": "Amir project plugin — project-selected components (harness, cloud/security/network groups, dev tools)",
"author": {
"name": "Amir",
"email": "[email protected]"
},
"keywords": [
"multi-agent",
"harness",
"cloud",
"security",
"network",
"project-scoped"
],
"mcpServers": {
"aws-mcp": {
"command": "uvx",
"args": [
"[email protected]",
"https://aws-mcp.us-east-1.api.aws/mcp",
"--metadata",
"AWS_REGION=${env:AWS_REGION}"
]
},
"azure-mcp": {
"command": "npx",
"args": [
"-y",
"@azure/mcp@latest",
"server",
"start"
]
},
"litellm": {
"command": "python",
"args": [
"${CLAUDE_PLUGIN_ROOT}/scripts/litellm/litellm_mcp.py"
]
},
"elastic-agent-builder": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"${env:ELASTIC_KIBANA_URL}/api/agent_builder/mcp",
"--header",
"Authorization:${env:ELASTIC_AUTH_HEADER}"
]
}
}
}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.
[amir on Agent Plugins Marketplace](https://pluginsmp.com/plugins/amir)