agentrigs
+ submit rig
~ / rigs / SandeepTakasi / drydock

SandeepTakasi/drydock

Plan-first parallel execution for Claude Code: rigorous plan documents, wave-based subagent execution with disjoint file ownership, plan-conformance verification gates, and a reconcile loop. Nothing sails until it leaves the dock.

↗ GitHub ★ 0 mit updated 23d ago project Claude Code Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~5.7k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/SandeepTakasi/drydock

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 SandeepTakasi/drydock/drydock/skills/check .claude/skills/check
$ npx degit SandeepTakasi/drydock/drydock/skills/init .claude/skills/init
$ npx degit SandeepTakasi/drydock/drydock/skills/planwright .claude/skills/planwright
$ npx degit SandeepTakasi/drydock/drydock/skills/reconcile .claude/skills/reconcile
$ npx degit SandeepTakasi/drydock/drydock/skills/replan .claude/skills/replan
$ npx degit SandeepTakasi/drydock/drydock/skills/seatrial .claude/skills/seatrial
$ npx degit SandeepTakasi/drydock/drydock/skills/wavecheck .claude/skills/wavecheck

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 (7)

checkinitplanwrightreconcilereplanseatrialwavecheck

Similar rigs

warrendeanlangeveldt/code-kit
Keeps AI coding agents inside your project's rules: lanes, layer rules, protected paths and proof before finish, enforced by Claude Code hooks and in CI
★ 0 project Claude CodeCodex 8 skills 2d ago
Pragmatist 1.2k tok ·
bentleypark/claude-code-mobile-spine
Claude Code plugin marketplace bundling mobile-spine — scaffolds a meta-repo coordinating 4 subagents (api/pm/android/ios) for mobile teams whose Android, iOS, and Backend live in 3 separate repos.
★ 1 project Claude Code 1 skills 3mo ago
Minimalist 84 tok ·
yongkyung-oh/agent-bootstrap
A minimal workflow bootstrap for AI coding agents — three markdown files that solve context loss between sessions. No framework, no dependencies.
★ 0 project Claude CodeCodex 1 skills 8mo ago
Minimalist 1.7k tok ·
oter/bruh
Claude Code plugin for coordinating work across sessions and machines: coordinator, clankers, clerks, workflows
★ 0 project Claude Code 2 mcp 2 skills today
Pragmatist 5.2k tok ·
copied ✓