jainsahabtusharjain/ai-agent-harness
AI agent harness — Claude Code + Hermes Agent configs, skills, memories, session transcripts, and LiteLLM gateway setup
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 io.github.upstash-context7 -e CONTEXT7_<redacted> -- npx @upstash/context7-mcp@1.0.31 $ claude mcp add --transport http io.github.github-github-mcp-server https://api.githubcopilot.com/mcp/ $ claude mcp add oraios-serena -- uvx --from git+https://github.com/oraios/serena serena start-mcp-server serena@latest --context ide-assistant $ claude mcp add obsidian -e PATH=YOUR_PATH -- /opt/homebrew/bin/npx -y @bitbonsai/mcpvault '~/Documents/Obsidian Vault' $ claude mcp add --transport http exa-ecc https://mcp.exa.ai/mcp $ claude mcp add sequential-thinking-ecc -- npx -y @modelcontextprotocol/server-sequential-thinking@2025.12.18 $ claude mcp add playwright -- npx @playwright/mcp@latest
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 io.github.upstash-context7 -e CONTEXT7_<redacted> -- npx @upstash/context7-mcp@1.0.31 $ claude mcp add --transport http io.github.github-github-mcp-server https://api.githubcopilot.com/mcp/ $ claude mcp add oraios-serena -- uvx --from git+https://github.com/oraios/serena serena start-mcp-server serena@latest --context ide-assistant $ claude mcp add obsidian -e PATH=YOUR_PATH -- /opt/homebrew/bin/npx -y @bitbonsai/mcpvault '~/Documents/Obsidian Vault' $ claude mcp add --transport http exa-ecc https://mcp.exa.ai/mcp $ claude mcp add sequential-thinking-ecc -- npx -y @modelcontextprotocol/server-sequential-thinking@2025.12.18 $ claude mcp add playwright -- npx @playwright/mcp@latest
$ npx degit jainsahabtusharjain/ai-agent-harness/claude-code/skills/aws-gpu .claude/skills/aws-gpu $ npx degit jainsahabtusharjain/ai-agent-harness/claude-code/skills/caveman .claude/skills/caveman $ npx degit jainsahabtusharjain/ai-agent-harness/claude-code/skills/dynamodb .claude/skills/dynamodb $ npx degit jainsahabtusharjain/ai-agent-harness/claude-code/skills/find-docs .claude/skills/find-docs $ npx degit jainsahabtusharjain/ai-agent-harness/claude-code/skills/git-commit .claude/skills/git-commit $ npx degit jainsahabtusharjain/ai-agent-harness/claude-code/skills/graphify .claude/skills/graphify $ npx degit jainsahabtusharjain/ai-agent-harness/claude-code/skills/grilling .claude/skills/grilling $ npx degit jainsahabtusharjain/ai-agent-harness/hermes/skills/computer-use .claude/skills/computer-use $ npx degit jainsahabtusharjain/ai-agent-harness/hermes/skills/dogfood .claude/skills/dogfood $ npx degit jainsahabtusharjain/ai-agent-harness/hermes/skills/llm-gateway-proxy .claude/skills/llm-gateway-proxy $ npx degit jainsahabtusharjain/ai-agent-harness/hermes/skills/yuanbao .claude/skills/yuanbao
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 (8)
| server | source | est. tokens |
|---|---|---|
| Context7 · "io.github.upstash/context7" env: CONTEXT7_API_KEY | npm | 1.2k |
| GitHub MCP · "io.github.github/github-mcp-server" | remote · remote | 18.0k |
| Serena · "oraios/serena" | git | 8.0k |
| @bitbonsai/mcpvault · "obsidian" env: PATH | npm | 2.5k |
| Exa · "exa-ecc" | remote · remote | 1.5k |
| memory-ecc | local / custom | 2.5k |
| Sequential Thinking · "sequential-thinking-ecc" | npm | 900 |
| Playwright MCP · "playwright" | npm | 7.5k |
Skills (11)
Similar rigs
imMamdouhaboammar/agent-kernel
Local governance, memory, failure lessons, and architecture guardrails for Claude Code, Codex, Cursor, Gemini CLI, and other AI coding agents.
MCP Hoarder 34.4k tok ·
cassler/awesome-claude-code-setup
Give Claude the super powers it deserves with this power user collection of bash scripts and slash commands
Pragmatist 31.8k tok ·
ifitsmanu/claude-template
The best Claude Code setup template. 14 commands, 5 agents, 6 MCP servers, auto-formatting hooks. Based on Boris Cherny's workflow.
Fort Knox 17.2k tok ·
affaan-m/agentshield
AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️
MCP Hoarder 60.2k tok ·