agentrigs
+ submit rig
~ / rigs / chaosteil / dotfiles

chaosteil/dotfiles

Stores my various config files, like my vimrc.

↗ GitHub ★ 38 MIT updated 1d ago personal setup Claude CodeCodex Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~1.1k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit chaosteil/dotfiles/agents ./rig-dotfiles/agents

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 chaosteil/dotfiles/agents/skills/jujutsu-stacks .claude/skills/jujutsu-stacks
$ npx degit chaosteil/dotfiles/agents/skills/jujutsu-workspaces .claude/skills/jujutsu-workspaces
$ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.<redacted>.md
$ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>-stacks/SKILL.md
$ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.<redacted>-workspaces/SKILL.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 *)"
    ]
  }
}

Skills (2)

jujutsu-stacksjujutsu-workspaces

Subagents (3)

implementer
model: opus
Implements an approved plan word for word in a jj repository. Use after the user approves a plan, or when the user gives an exact specification. Not for research, review, or design.
jujutsu-stacks**REQUIRED** - Activate when work in a Jujutsu (jj) repo spans MORE THAN ONE commit: you build a stack, you amend or reorder or split or drop a commit in a range, you fix an earlier commit, or you rev
jujutsu-workspaces**REQUIRED** - Activate when work in a Jujutsu (jj) repo is split across PARALLEL agents or isolated working directories: a workflow that fans out subagents onto separate features, an agent that must

Similar rigs

nobodyiscertain/claude-config
Commands, Agents & Configs for Claude Code
★ 3 setup Claude CodeCodex 2 agents 11mo ago
Pragmatist 3.0k tok ·
Saba-Var/claude-ward
A read-only tripwire that watches Claude Code's local config and reports suspicious changes.
★ 2 project Claude CodeCodex 2 agents 3mo ago
Pragmatist 1.8k tok ·
0xT4sty/claude-code-dotfiles
—
★ 0 setup Claude Code 3 agents 5mo ago
Pragmatist 979 tok ·
Pushedskydiver/CC-Checker-Web-Extension
WCAG accessibility colour contrast checker web extension
★ 9 project Claude CodeCodex 4 agents 2d ago
Pragmatist 3.9k tok ·
copied ✓