AndrewAltimit/template-repo
Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability on sleeper agents, and agent integration via CLI wrappers
ARCHETYPE
MCP Hoarder
Six or more MCP servers wired in. Every tool, always in context.
Copy this rig
# review before running: this installs third-party code $ claude mcp add code-quality -- docker compose -f ./docker-compose.yml --profile services run --rm -T mcp-code-quality mcp-code-quality --mode stdio $ claude mcp add blender -- docker compose -f ./docker-compose.yml --profile services run --rm -T mcp-blender mcp-blender --mode stdio $ claude mcp add content-creation -- docker compose -f ./docker-compose.yml --profile services run --rm -T mcp-content-creation mcp-content-creation --mode stdio $ claude mcp add opencode -- docker compose -f ./docker-compose.yml --profile services run --rm -T mcp-opencode mcp-opencode --mode stdio $ claude mcp add crush -- docker compose -f ./docker-compose.yml --profile services run --rm -T mcp-crush mcp-crush --mode stdio $ claude mcp add github-board -e BOARD_PROJECT_NUMBER=YOUR_BOARD_PROJECT_NUMBER -e GITHUB_PROJECTS_<redacted> -e GITHUB_REPOSITORY=YOUR_GITHUB_REPOSITORY -e GITHUB_<redacted> -- docker compose -f ./docker-compose.yml --profile services run --rm -T mcp-github-board mcp-github-board --mode stdio $ claude mcp add agentcore-memory -- docker compose -f ./docker-compose.yml --env-file ./.env --profile memory run --rm -T mcp-agentcore-memory mcp-agentcore-memory --mode stdio $ claude mcp add reaction-search -- docker compose -f ./docker-compose.yml --profile services run --rm -T mcp-reaction-search --mode stdio $ claude mcp add sprite-sheet -- docker compose -f ./docker-compose.yml --profile services run --rm -T mcp-sprite-sheet mcp-sprite-sheet --mode stdio --output /output $ npx degit AndrewAltimit/template-repo/.claude ./rig-template-repo # inspect, then merge into .claude/
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add code-quality -- docker compose -f ./docker-compose.yml --profile services run --rm -T mcp-code-quality mcp-code-quality --mode stdio $ claude mcp add blender -- docker compose -f ./docker-compose.yml --profile services run --rm -T mcp-blender mcp-blender --mode stdio $ claude mcp add content-creation -- docker compose -f ./docker-compose.yml --profile services run --rm -T mcp-content-creation mcp-content-creation --mode stdio $ claude mcp add opencode -- docker compose -f ./docker-compose.yml --profile services run --rm -T mcp-opencode mcp-opencode --mode stdio $ claude mcp add crush -- docker compose -f ./docker-compose.yml --profile services run --rm -T mcp-crush mcp-crush --mode stdio $ claude mcp add github-board -e BOARD_PROJECT_NUMBER=YOUR_BOARD_PROJECT_NUMBER -e GITHUB_PROJECTS_<redacted> -e GITHUB_REPOSITORY=YOUR_GITHUB_REPOSITORY -e GITHUB_<redacted> -- docker compose -f ./docker-compose.yml --profile services run --rm -T mcp-github-board mcp-github-board --mode stdio $ claude mcp add agentcore-memory -- docker compose -f ./docker-compose.yml --env-file ./.env --profile memory run --rm -T mcp-agentcore-memory mcp-agentcore-memory --mode stdio $ claude mcp add reaction-search -- docker compose -f ./docker-compose.yml --profile services run --rm -T mcp-reaction-search --mode stdio $ claude mcp add sprite-sheet -- docker compose -f ./docker-compose.yml --profile services run --rm -T mcp-sprite-sheet mcp-sprite-sheet --mode stdio --output /output
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} MCP servers (9)
| server | source | est. tokens |
|---|---|---|
| ./docker-compose.yml · "code-quality" | docker | 2.5k |
| ./docker-compose.yml · "blender" | docker | 2.5k |
| ./docker-compose.yml · "content-creation" | docker | 2.5k |
| ./docker-compose.yml · "opencode" | docker | 2.5k |
| ./docker-compose.yml · "crush" | docker | 2.5k |
| ./docker-compose.yml · "github-board" env: BOARD_PROJECT_NUMBER, GITHUB_PROJECTS_TOKEN, GITHUB_REPOSITORY, GITHUB_TOKEN | docker | 2.5k |
| ./.env · "agentcore-memory" | docker | 2.5k |
| ./docker-compose.yml · "reaction-search" | docker | 2.5k |
| /output · "sprite-sheet" | docker | 2.5k |
Similar rigs
affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
MCP Hoarder 58.4k tok ·
anthropics/knowledge-work-plugins
Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork
MCP Hoarder 118.2k tok ·
superset-sh/superset
Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.
MCP Hoarder 28.8k tok ·
awslabs/mcp
Open source MCP Servers for AWS
MCP Hoarder 19.1k tok ·