agentrigs
+ submit rig
~ / rigs / gabrielrojasc / configuration

gabrielrojasc/configuration

dotfiles

↗ GitHub ★ 1 no license updated 23d ago personal setup Claude CodeCodex
share on X
ARCHETYPE
MCP Hoarder
Six or more MCP servers wired in. Every tool, always in context.
CONTEXT TAX · EVERY TURN
~16.0k tokens
Context hog · median rig: 2.3k · breakdown
GUARDRAILS
2/5
No YOLO mode · Sandbox or ask-first rules · details

Copy this rig

# review before running: this installs third-party code
$ claude mcp add --transport http grafana https://mcp.grafana.com/mcp
$ claude mcp add --transport http zf-grafana-prod https://mcp.nixhoodwink.com/grafana/mcp
$ claude mcp add --transport http zf-grafana-stag https://mcp-stag.nixhoodwink.com/grafana/mcp
$ claude mcp add --transport http zf-grafana-qa https://mcp-qa.nixhoodwink.com/grafana/mcp
$ npx degit gabrielrojasc/configuration/base/home/.claude ./rig-configuration  # 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 --transport http grafana https://mcp.grafana.com/mcp
$ claude mcp add --transport http zf-grafana-prod https://mcp.nixhoodwink.com/grafana/mcp
$ claude mcp add --transport http zf-grafana-stag https://mcp-stag.nixhoodwink.com/grafana/mcp
$ claude mcp add --transport http zf-grafana-qa https://mcp-qa.nixhoodwink.com/grafana/mcp
$ curl -fsSL --create-dirs -o .claude/agents/consequential.md https://raw.githubusercontent.<redacted>.claude/agents/consequential.md
$ curl -fsSL --create-dirs -o .claude/agents/proven.md https://raw.githubusercontent.<redacted>.claude/agents/proven.md
$ curl -fsSL --create-dirs -o .claude/agents/unproven.md https://raw.githubusercontent.<redacted>.claude/agents/unproven.md
$ curl -fsSL --create-dirs -o .claude/agents/unruly.md https://raw.githubusercontent.<redacted>.claude/agents/unruly.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 (6)

serversourceest. tokens
node_repl local / custom 2.5k
computer-use local / custom 2.5k
mcp.grafana.com · "grafana" remote · remote 2.5k
mcp.nixhoodwink.com · "zf-grafana-prod" remote · remote 2.5k
mcp-stag.nixhoodwink.com · "zf-grafana-stag" remote · remote 2.5k
mcp-qa.nixhoodwink.com · "zf-grafana-qa" remote · remote 2.5k

Subagents (4)

consequential
model: claude-opus-5-5
Use for unresolved design, diagnosis, or correctness decisions whose errors would be costly or hard to detect, including changes, and reviews of changes, to authentication, authorization, tenant isola
proven
model: claude-opus-5-5
Use when an existing independent check, such as a test, command output, diff, or cited source for a lookup, alone proves the result, and the environment is ready and the approach established.
unproven
model: claude-opus-5-5
Use for routine work that checks cannot alone prove, such as implementation and repair of reproduced issues with partial acceptance checks, and review of changes that alter no behavior, such as typos
unruly
model: claude-opus-5-5
Use when the main challenge is adapting dependent terminal steps to observed tool or environment behavior, such as recovering from failures or configuring interacting tools without a known sequence, a

Plugins (1)

nomad@zerofox-claude-plugins

Permissions

deny (0)
—
ask (0)
—
allow (1)
Bash(codex exec:*)

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.
★ 275k project Claude CodeCodexCursor 7 mcp 96 skills 68 agents 4d ago
MCP Hoarder 58.4k tok ·
anthropics/knowledge-work-plugins
Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork
★ 26.2k collection Claude CodeCodex 32 mcp 144 skills 3d ago
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.
★ 14.9k project Claude CodeCodex 6 mcp 50 skills 1 agents 3d ago
MCP Hoarder 28.8k tok ·
awslabs/mcp
Open source MCP Servers for AWS
★ 9,748 project Codex 6 mcp 7 skills 6d ago
MCP Hoarder 19.1k tok ·
copied ✓