omerakben/agent-context-center
One offline, committed HTML dashboard that maps a repo's AI context — CLAUDE.md, AGENTS.md, Cursor rules, MCP servers, skills, agents, hooks, commands, docs, and TODOs. Markdown stays the source of truth; the dashboard is the human map.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ claude mcp add postgres -e PGHOST=YOUR_PGHOST -e PG<redacted> -- npx -y @modelcontextprotocol/server-postgres $ claude mcp add filesystem -- npx -y @modelcontextprotocol/server-filesystem ./data $ npx degit omerakben/agent-context-center/examples/mcp-and-skills/.claude ./rig-agent-context-center # 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 postgres -e PGHOST=YOUR_PGHOST -e PG<redacted> -- npx -y @modelcontextprotocol/server-postgres $ claude mcp add filesystem -- npx -y @modelcontextprotocol/server-filesystem ./data
$ npx degit omerakben/agent-context-center/examples/mcp-and-skills/.claude/skills/seed-db .claude/skills/seed-db $ npx degit omerakben/agent-context-center/skills/agent-context-center .claude/skills/agent-context-center
$ curl -fsSL --create-dirs -o .claude/agents/migration-reviewer.md https://raw.githubusercontent.com/omerakben/agent-context-center/main/examples/claude-codex-cursor/.claude/agents/migration-reviewer.md 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 (2)
| server | source | est. tokens |
|---|---|---|
| Postgres env: PGHOST, PGPASSWORD | npm | 600 |
| Filesystem | npm | 4.2k |
Skills (2)
Subagents (1)
| migration-reviewer | Reviews a database migration for safety before it ships — locks, backfills, reversibility. |
Hooks (1)
| event | matcher | runs |
|---|---|---|
| PostToolUse | Edit | npm run lint --silent |
Slash commands (1)
/dashboard
Cursor rules (1)
style
Similar rigs
holt-web-ai/n8n-nodes-claudecode
—
Pragmatist 27.1k tok ·
felixhennequin-gif/claude-code-config-template
Production-ready AI config template for Claude Code. CLAUDE.md, agents, skills, hooks, routines, and commands — based on analysis of 55+ open-source repos (Supabase, Bitwarden, Vercel, Cloudflare, OpenAI).
Orchestrator 24.5k tok ·
KosMaster87/Link-Shortener-Render
Built with Node.js and PostgreSQL, I applied analytical problem-solving to implement secure URL shortening, click tracking, and dashboard insights.
Pragmatist 6.4k tok ·
floating-astronaut/vibe-coding-kit
Replace your dev team: an operating system for a coordinated Claude Code, Codex and Kimi AI coding team. Docs-first lanes, zero-drift handoffs. MIT.
Pragmatist 22.8k tok ·