dimokol/agent-dojo
Plugins, skills and habits that help you do professional-grade work with coding agents. From my daily workflows as a web and game developer: git guardrails, a machine-pressure gate, agent-to-agent chat, review and verify loops for Claude Co
stack: JavaScript
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
up to ~3.0k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Moderate · median rig: 2.3k · breakdown
Copy this rig
$ git clone --depth 1 https://github.com/dimokol/agent-dojo 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-dojo/plugins/integration-branch-qa/skills/integration-branch-qa .claude/skills/integration-branch-qa $ npx degit dimokol/agent-dojo/plugins/pr-review-loop/skills/pr-review-loop .claude/skills/pr-review-loop $ npx degit dimokol/agent-dojo/plugins/setup-audit/skills/setup-audit .claude/skills/setup-audit $ npx degit dimokol/agent-dojo/plugins/storage-reclaim/skills/disk-map .claude/skills/disk-map $ npx degit dimokol/agent-dojo/plugins/storage-reclaim/skills/storage-reclaim .claude/skills/storage-reclaim $ npx degit dimokol/agent-dojo/plugins/verify-before-building/skills/verify-before-building .claude/skills/verify-before-building $ npx degit dimokol/agent-dojo/plugins/worktree-hygiene/skills/worktree-hygiene .claude/skills/worktree-hygiene
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| agent-chat | local / custom | 2.5k |
Skills (7)
Similar rigs
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.
Pragmatist 3.0k tok · · Q0
yqrashawn/yqdotfiles
dotfiles
Minimalist 817 tok · · Q0
sandudorogan/pr-loop
PR Loop: a macOS app that reviews and fixes your GitHub PRs with Claude Code and Codex
Pragmatist 6.8k tok · · Q3
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.
Minimalist 47 tok · · Q0