deathbeam/dotfiles
My awesome dotfiles :rocket:
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit deathbeam/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 deathbeam/dotfiles/agents/.agents/skills/codebase-design .claude/skills/codebase-design $ npx degit deathbeam/dotfiles/agents/.agents/skills/diagnosing-bugs .claude/skills/diagnosing-bugs $ npx degit deathbeam/dotfiles/agents/.agents/skills/execute-plan .claude/skills/execute-plan $ npx degit deathbeam/dotfiles/agents/.agents/skills/find-skills .claude/skills/find-skills $ npx degit deathbeam/dotfiles/agents/.agents/skills/ponytail-audit .claude/skills/ponytail-audit $ npx degit deathbeam/dotfiles/agents/.agents/skills/ponytail-debt .claude/skills/ponytail-debt $ npx degit deathbeam/dotfiles/agents/.agents/skills/ponytail-review .claude/skills/ponytail-review $ npx degit deathbeam/dotfiles/agents/.agents/skills/ponytail .claude/skills/ponytail $ npx degit deathbeam/dotfiles/agents/.agents/skills/prepare-plan .claude/skills/prepare-plan $ npx degit deathbeam/dotfiles/agents/.agents/skills/technical-writing .claude/skills/technical-writing $ npx degit deathbeam/dotfiles/agents/.agents/skills/unslop .claude/skills/unslop $ npx degit deathbeam/dotfiles/agents/.agents/skills/writing-for-agents .claude/skills/writing-for-agents
$ curl -fsSL --create-dirs -o .claude/agents/DEEPENING.md https://raw.githubusercontent.com/deathbeam/dotfiles/master/agents/.agents/skills/codebase-design/DEEPENING.md $ curl -fsSL --create-dirs -o .claude/agents/DESIGN-IT-TWICE.md https://raw.githubusercontent.com/deathbeam/dotfiles/master/agents/.agents/skills/codebase-design/DESIGN-IT-TWICE.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/deathbeam/dotfiles/master/agents/.agents/skills/codebase-design/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/deathbeam/dotfiles/master/agents/.agents/skills/diagnosing-bugs/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/deathbeam/dotfiles/master/agents/.agents/skills/execute-plan/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/deathbeam/dotfiles/master/agents/.agents/skills/find-skills/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/deathbeam/dotfiles/master/agents/.agents/skills/ponytail-audit/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/deathbeam/dotfiles/master/agents/.agents/skills/ponytail-debt/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/deathbeam/dotfiles/master/agents/.agents/skills/ponytail-review/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/deathbeam/dotfiles/master/agents/.agents/skills/ponytail/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/deathbeam/dotfiles/master/agents/.agents/skills/prepare-plan/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/deathbeam/dotfiles/master/agents/.agents/skills/technical-writing/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/deathbeam/dotfiles/master/agents/.agents/skills/unslop/SKILL.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL-MECHANICS.md https://raw.githubusercontent.com/deathbeam/dotfiles/master/agents/.agents/skills/writing-for-agents/SKILL-MECHANICS.md $ curl -fsSL --create-dirs -o .claude/agents/SKILL.md https://raw.githubusercontent.com/deathbeam/dotfiles/master/agents/.agents/skills/writing-for-agents/SKILL.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(~/.aws/**)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(.env)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/.env.*)",
"Read(**/*.key)",
"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(npm publish:*)",
"Bash(wget *)",
"Bash(git rebase *)",
"Bash(gh pr merge *)",
"Bash(git commit *)"
]
}
} Skills (12)
codebase-designdiagnosing-bugsexecute-planfind-skillsponytail-auditponytail-debtponytail-reviewponytailprepare-plantechnical-writingunslopwriting-for-agents
Subagents (15)
| DEEPENING | — |
| DESIGN-IT-TWICE | — |
| codebase-design | Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-n |
| diagnosing-bugs | Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow. |
| execute-plan | Implement or resume tasks from a .plans/<name>.md file, verifying each task before marking it done. |
| find-skills | Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This sk |
| ponytail-audit | > |
| ponytail-debt | > |
| ponytail-review | > |
| ponytail | > |
| prepare-plan | Create or revise a .plans/<name>.md implementation plan before coding; use when work needs a detailed, executable task breakdown. |
| technical-writing | Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use when writing or reviewing docs, RFCs, readmes, PR descriptio |
| unslop | Cut AI tells from any writing. Use when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages. |
| SKILL-MECHANICS | — |
| writing-for-agents | Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md. |
Similar rigs
DietrichGebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Pragmatist 1.6k tok ·
saqie803/ponytail
Ship production-ready code with one line of AI-generated output, built for 20 agents and zero ceremony.
Pragmatist 714 tok ·
Starefossen/dotfiles
:feet: All of my configuration files for all the things
Skill Collector 4.8k tok ·
contextmux/contextmux
Turn a ticket into a reviewed pull request, under gates that stop work which drifted out of scope or weakened tests. Compiles one source of coding rules to CLAUDE.md, AGENTS.md, .cursor/rules and copilot-instructions.
Pragmatist 10.1k tok ·