agentrigs
+ submit rig
~ / rigs / wbern / agent-instructions

wbern/agent-instructions

Claude Instructions Repository

↗ GitHub ★ 167 MIT updated 4mo ago project Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~2.0k tokens
Featherweight · median rig: 2.2k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit wbern/agent-instructions/.claude ./rig-agent-instructions  # 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 wbern/agent-instructions/.claude/skills/tdd .claude/skills/tdd

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,413 rigs:

{
  "permissions": {
    "deny": [
      "Read(~/.ssh/**)",
      "Read(**/.env)",
      "Bash(rm -rf *)",
      "Read(./.env)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /*)",
      "Read(~/.aws/**)",
      "Bash(rm -rf:*)",
      "Read(.env)",
      "Bash(git push --force*)",
      "Read(**/*.key)",
      "Read(./.env.*)",
      "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(wget *)",
      "Bash(npm publish:*)",
      "Bash(gh pr merge *)",
      "Bash(chown *)",
      "Bash(docker *)"
    ]
  }
}

Skills (1)

tdd

Slash commands (32)

/add-command/beepboop/busycommit/code-review/commit-hook-checklist/commit/contribute-a-command/create-adr/create-issues/cycle/gap/gastown-setup/green/issue/kata/polish/pr-ask/pr-ship/pr-show/pr/red/refactor/research/simplify/spike/summarize/tdd-review/tdd/upgrade-deps/worktree-add/worktree-cleanup/worktree-setup

Similar rigs

leviFrosty/dotfiles
My MacOS specific dotfiles & configs.
★ 34 setup Claude Code 2 skills 13d ago
YOLO Cowboy 132 tok ·
wesammustafa/Claude-Code-Everything-You-Need-to-Know
A practical Claude Code guide with clear mental models and copy-paste examples — setup, prompt engineering, slash commands, skills, hooks, subagents, agent teams, and MCP servers. Beginner path to power-user depth. Featured in Awesome Claud
★ 3,096 project Claude CodeCodex 3 skills 5d ago
Minimalist 2.4k tok ·
AsobaCloud/claude-code-sdlc
Claude Code SDLC enforcement template — hooks, scripts, and settings for disciplined AI-assisted development
★ 0 project Claude Code 1 skills 3 agents 13 hooks 6mo ago
YOLO Cowboy 3.1k tok ·
danjdewhurst/dotclaude
Global Claude Code config, synced between machines by one script: CLAUDE.md, writing rules, vendored skills and the bash environment commands run in, symlinked into ~/.claude and wherever Codex and other agents look
★ 6 setup Claude Code 6 skills 15d ago
Pragmatist 398 tok ·
copied ✓