agentrigs
+ submit rig
~ / rigs / HartBrook / staghorn

HartBrook/staghorn

Sync Claude Code configs and skills from GitHub — for teams, communities, or across your personal projects. Run evals to verify your guidelines actually work.

↗ GitHub ★ 9 MIT updated 4mo ago project Claude Code
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~196 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
1/5
No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit HartBrook/staghorn/.claude ./rig-staghorn  # 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.

$ npx degit HartBrook/staghorn/internal/starter/skills/code-review .claude/skills/code-review
$ npx degit <redacted>-audit .claude/skills/security-audit
$ npx degit HartBrook/staghorn/internal/starter/skills/test-gen .claude/skills/test-gen
$ npx degit <redacted> .claude/skills/verify

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 *)"
    ]
  }
}

Skills (4)

code-reviewsecurity-audittest-genverify

Permissions

deny (0)
—
ask (0)
—
allow (1)
Bash(/tmp/stag-new commands code-review:*)

Similar rigs

pravindurgani/claude-code-multipane-iterm2
Stop your AI agent from reviewing its own code — 4-pane iTerm2 setup with role-locked Claude Code sessions. Step-by-step guide included.
★ 3 project Claude Code 3 skills 18d ago
Minimalist 1.0k tok ·
kimon1230/claude_extensions
Custom hooks, skills, and rules for Claude Code: adds automatic Python formatting, context persistence across sessions, parallel subagent workflows, and a status line.
★ 4 project Claude Code 5 skills 4mo ago
Pragmatist 1.7k tok ·
zenbu-labs/terminal-browser
A browser inside your terminal
★ 3,734 project Claude CodeCodex 1 skills 2d ago
Minimalist 815 tok ·
cosmtrek/mindwalk
A visualization tool that replays coding-agent sessions on a 3D map of your codebase.
★ 1,364 project Claude CodeCodex 1 skills 2mo ago
Minimalist 1.1k tok ·
copied ✓