~ / rigs / agent-rig / rig

agent-rig/rig

Copy-in kit of config-driven agent skills, agents, and CI templates — native to Claude Code and adaptable to any AGENTS.md-reading agent.

↗ GitHub ★ 3 MIT updated 28d ago project Claude Code
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~1.4k 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 agent-rig/rig/agents ./rig-rig/agents
$ npx degit agent-rig/rig/skills ./rig-rig/skills

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 agent-rig/rig/skills/rig-debug .claude/skills/rig-debug
$ npx degit agent-rig/rig/skills/rig-doctor .claude/skills/rig-doctor
$ npx degit agent-rig/rig/skills/rig-epic .claude/skills/rig-epic
$ npx degit agent-rig/rig/skills/rig-issue .claude/skills/rig-issue
$ npx degit agent-rig/rig/skills/rig-onboard .claude/skills/rig-onboard
$ npx degit agent-rig/rig/skills/rig-plan .claude/skills/rig-plan
$ npx degit agent-rig/rig/skills/rig-proof .claude/skills/rig-proof
$ npx degit agent-rig/rig/skills/rig-review .claude/skills/rig-review
$ npx degit agent-rig/rig/skills/rig-spike .claude/skills/rig-spike
$ npx degit agent-rig/rig/skills/rig-sprint .claude/skills/rig-sprint
$ npx degit agent-rig/rig/skills/rig-task .claude/skills/rig-task
$ npx degit agent-rig/rig/skills/rig-tidy .claude/skills/rig-tidy
$ npx degit agent-rig/rig/skills/rig-worktree .claude/skills/rig-worktree
$ curl -fsSL --create-dirs -o .claude/agents/rig-architect.md https://raw.githubusercontent.com/agent-rig/rig/main/agents/rig-architect.md
$ curl -fsSL --create-dirs -o .claude/agents/rig-coder.md https://raw.githubusercontent.com/agent-rig/rig/main/agents/rig-coder.md
$ curl -fsSL --create-dirs -o .claude/agents/rig-debugger.md https://raw.githubusercontent.com/agent-rig/rig/main/agents/rig-debugger.md
$ curl -fsSL --create-dirs -o .claude/agents/rig-qa.md https://raw.githubusercontent.com/agent-rig/rig/main/agents/rig-qa.md
$ curl -fsSL --create-dirs -o .claude/agents/rig-reviewer.md https://raw.githubusercontent.com/agent-rig/rig/main/agents/rig-reviewer.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 (13)

Subagents (5)

rig-architect
model: opus
Tech lead agent for planning, architecture decisions, and ticket creation. Use when breaking down a feature, designing a solution, evaluating tradeoffs, or creating implementation tickets. Invoke befo
rig-coder
model: sonnet
Implementation agent for writing production code from tickets or specs. Use when a plan exists and it's time to write code. Reads the ticket, explores the affected files, and implements the change.
rig-debugger
model: sonnet
Systematic root-cause debugger. Use when investigating a failing test, a production bug, a flaky behavior, or any "this doesn't work and I don't know why" situation. Walks Phase 1 → 4 (root-cause → pa
rig-qa
model: sonnet
Test writing agent. Use to write or extend unit tests for new or changed code. Give it the file or function to test and it will produce the test cases.
rig-reviewer
model: opus
Code review agent. Use after implementation to check correctness, security, and adherence to project conventions before merging. Provide the diff, PR, or list of changed files.

Similar rigs

copied ✓