agentrigs
+ submit rig
~ / rigs / dimokol / agent-workbench

dimokol/agent-workbench

Claude Code plugins for running several coding agents at once: git guardrails, a machine-pressure gate, agent-to-agent chat, PR review and QA loops. Pick only the parts you want.

↗ GitHub ★ 1 no license updated 1d ago project Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~3.2k tokens
Moderate · 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 dimokol/agent-workbench/skills ./rig-agent-workbench/skills
$ npx degit dimokol/agent-workbench/hooks ./rig-agent-workbench/hooks

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 dimokol/agent-workbench/skills/babysit-prs .claude/skills/babysit-prs
$ npx degit dimokol/agent-workbench/skills/create-pr .claude/skills/create-pr
$ npx degit dimokol/agent-workbench/skills/e2e-harness-patterns .claude/skills/e2e-harness-patterns
$ npx degit dimokol/agent-workbench/skills/setup-audit .claude/skills/setup-audit
$ npx degit dimokol/agent-workbench/skills/task-sync .claude/skills/task-sync
$ npx degit dimokol/agent-workbench/skills/verify-before-building .claude/skills/verify-before-building
$ npx degit dimokol/agent-workbench/skills/worktree-hygiene .claude/skills/worktree-hygiene
$ npx degit dimokol/agent-workbench/skills/worktree-qa-queue .claude/skills/worktree-qa-queue

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 *)"
    ]
  }
}

MCP servers (1)

serversourceest. tokens
agent-chat
env: AGENT_CHAT_DIR
 local / custom 2.5k

Skills (8)

babysit-prscreate-pre2e-harness-patternssetup-audittask-syncverify-before-buildingworktree-hygieneworktree-qa-queue

Similar rigs

ReflexioAI/claude-smart
Turns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode.
★ 781 project Codex 3 skills 8d ago
Minimalist 327 tok ·
MaksymStoianov/skills
Public Agent Skills collection by Maksym Stoianov – Claude Code, Gemini CLI, Cursor, and npx skills compatible.
★ 3 collection Claude CodeCodex 3 skills 1 agents 17d ago
Pragmatist 3.3k tok ·
ozturkoglu/fable-skills
Four Claude Code skills for reliable agentic coding: verify-before-flag guardrails, model-tier routing, setup auditing, and a verification-chain for trustworthy multi-step findings.
★ 0 collection Claude Code 4 skills 3mo ago
Minimalist 47 tok ·
tigercosmos/terminal
A macOS-native terminal workspace designed for AI-driven development
★ 7 project Claude CodeCodexCursor 6 skills 1 hooks 2d ago
Pragmatist 1.1k tok ·
copied ✓