agentrigs
+ submit rig
~ / rigs / luisabwk / kraken

luisabwk/kraken

🦑 Release the Kraken! A 3-layer architecture template for reliable AI agents in Cursor IDE. Tame the chaos, ship with confidence.

↗ GitHub ★ 1 no license updated 7mo ago project Claude CodeCodexCursor
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~7.5k tokens
Heavy · median rig: 2.3k · breakdown
GUARDRAILS
3/5
Blocks destructive commands · Pre-tool screening hook · No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit luisabwk/kraken/.claude ./rig-kraken  # inspect, then merge into .claude/

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 luisabwk/kraken/.cursor/skills/ab-testing-framework .claude/skills/ab-testing-framework
$ npx degit luisabwk/kraken/.cursor/skills/ai-evals-builder .claude/skills/ai-evals-builder
$ npx degit luisabwk/kraken/.cursor/skills/code-simplifier .claude/skills/code-simplifier
$ npx degit luisabwk/kraken/.cursor/skills/continuous-discovery .claude/skills/continuous-discovery
$ npx degit luisabwk/kraken/.cursor/skills/dhm-strategy-framework .claude/skills/dhm-strategy-framework
$ npx degit luisabwk/kraken/.cursor/skills/documentation-standards .claude/skills/documentation-standards
$ npx degit luisabwk/kraken/.cursor/skills/dynamic-context .claude/skills/dynamic-context
$ npx degit luisabwk/kraken/.cursor/skills/execution .claude/skills/execution
$ npx degit luisabwk/kraken/.cursor/skills/lno-task-prioritization .claude/skills/lno-task-prioritization
$ npx degit luisabwk/kraken/.cursor/skills/mcp-modes .claude/skills/mcp-modes
$ npx degit luisabwk/kraken/.cursor/skills/memory-awareness .claude/skills/memory-awareness
$ npx degit luisabwk/kraken/.cursor/skills/opportunity-solution-tree .claude/skills/opportunity-solution-tree
$ npx degit luisabwk/kraken/.cursor/skills/plan .claude/skills/plan
$ npx degit luisabwk/kraken/.cursor/skills/prd-writer .claude/skills/prd-writer
$ npx degit luisabwk/kraken/.cursor/skills/pre-mortem-facilitator .claude/skills/pre-mortem-facilitator
$ npx degit luisabwk/kraken/.cursor/skills/product-led-growth-playbook .claude/skills/product-led-growth-playbook
$ npx degit luisabwk/kraken/.cursor/skills/stack .claude/skills/stack
$ npx degit luisabwk/kraken/.cursor/skills/systematic-debugging .claude/skills/systematic-debugging
$ npx degit luisabwk/kraken/.cursor/skills/task .claude/skills/task
$ npx degit luisabwk/kraken/.cursor/skills/test-driven-development .claude/skills/test-driven-development
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/luisabwk/kraken/main/.claude/agents/code-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/code-simplifier.md https://raw.githubusercontent.com/luisabwk/kraken/main/.claude/agents/code-simplifier.md
$ curl -fsSL --create-dirs -o .claude/agents/debugger.md https://raw.githubusercontent.com/luisabwk/kraken/main/.claude/agents/debugger.md
$ curl -fsSL --create-dirs -o .claude/agents/prd-creator.md https://raw.githubusercontent.com/luisabwk/kraken/main/.claude/agents/prd-creator.md
$ curl -fsSL --create-dirs -o .claude/agents/tdd-coach.md https://raw.githubusercontent.com/luisabwk/kraken/main/.claude/agents/tdd-coach.md

Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.

{
  "permissions": {
    "deny": [
      "Bash(rm -rf /)",
      "Bash(rm -rf ~)",
      "Bash(rm -rf /*)",
      "Bash(dd if=*)",
      "Bash(mkfs.*)",
      "Bash(chmod 777 *)",
      "Bash(chown -R * /)",
      "Bash(> /dev/*)",
      "Bash(git push --force *)",
      "Bash(git push -f *)"
    ]
  },
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "CMD=\"$CLAUDE_TOOL_INPUT_COMMAND\"; if echo \"$CMD\" | grep -qE '(rm\\s+-rf\\s+[/~]|dd\\s+if=|mkfs\\.|>\\s*/dev/|chmod\\s+777)'; then echo 'BLOCKED: Dangerous command detected' >&2; exit 2; fi"
          }
        ]
      }
    ]
  }
}

Skills (20)

ab-testing-frameworkai-evals-buildercode-simplifiercontinuous-discoverydhm-strategy-frameworkdocumentation-standardsdynamic-contextexecutionlno-task-prioritizationmcp-modesmemory-awarenessopportunity-solution-treeplanprd-writerpre-mortem-facilitatorproduct-led-growth-playbookstacksystematic-debuggingtasktest-driven-development

Subagents (5)

code-reviewerConfidence-based code review specialist. Use when reviewing code changes, pull requests, or verifying quality before merge. Applies scoring threshold of 80+ to avoid noise.
code-simplifierPost-implementation code cleanup specialist. Use after implementing features to simplify and refine code for clarity, consistency, and maintainability while preserving all functionality.
debuggerSystematic debugging specialist. Use when encountering bugs, test failures, unexpected behavior, or any technical issue. Follows a 4-phase root cause analysis process before proposing fixes.
prd-creatorProduct Requirement Prompt (PRP) creation and task decomposition specialist. Use when defining requirements for features, creating PRDs/PRPs, or breaking requirements into executable technical tasks w
tdd-coachTest-driven development specialist. Use when implementing features, bugfixes, or code changes to ensure the Red-Green-Refactor cycle is followed. Write tests first, watch them fail, then implement.

Hooks (2)

eventmatcherruns
PostToolUseWrite|EditFILE="$CLAUDE_TOOL_INPUT_FILE_PATH"; if [ -n "$FILE" ]; then LINES=$(wc -l < "$FILE" 2>/dev/null || echo 0); if [ "$LINES" -gt 500 ]; then echo "WARNING: File $FILE has $LINES lines (>500). Consider splitting."; fi; fi
PreToolUseBashCMD="$CLAUDE_TOOL_INPUT_COMMAND"; if echo "$CMD" | grep -qE '(rm\s+-rf\s+[/~]|dd\s+if=|mkfs\.|>\s*/dev/|chmod\s+777)'; then echo 'BLOCKED: Dangerous command detected' >&2; exit 2; fi

Slash commands (10)

/boot/clean/code-review/commit/context/execute/mcp/prp-new/prp-review/run

Cursor rules (11)

code-simplifier/RULEdocumentation-standards/RULEdynamic-context/RULE · alwaysexecution/RULEmcp-modes/RULEplan/RULE · alwaysprd/RULEstack/RULEsystematic-debugging/RULEtask/RULEtest-driven-development/RULE

Permissions

deny (10)
Bash(rm -rf /)
Bash(rm -rf ~)
Bash(rm -rf /*)
Bash(dd if=*)
Bash(mkfs.*)
Bash(chmod 777 *)
Bash(chown -R * /)
Bash(> /dev/*)
Bash(git push --force *)
Bash(git push -f *)
ask (0)
—
allow (35)
Bash(npm run *)
Bash(npm test *)
Bash(npm install *)
Bash(npx *)
Bash(git status)
Bash(git diff *)
Bash(git log *)
Bash(git add *)
Bash(git commit *)
Bash(git branch *)
Bash(git checkout *)
Bash(git pull *)
Bash(git stash *)
Bash(ls *)
Bash(find *)
Bash(grep *)
Bash(rg *)
Bash(head *)
Bash(tail *)
Bash(wc *)
Bash(du *)
Bash(cat *)
Bash(mkdir *)
Bash(touch *)
Bash(cp *)
Bash(mv *)
Bash(python3 *)
Bash(pip install *)
Bash(pip freeze *)
Bash(ruff *)
Bash(echo *)
Read
Edit
Write
Grep

Similar rigs

minhtuluc/Claude-Code-Configs
—
★ 1 setup Claude Code 17 skills 10 agents 26d ago
Orchestrator 2.2k tok ·
IvanKuzyshyn/dotfiles
Dotfiles optimized for speed, coffee, and questionable life choices. 😜
★ 5 setup Claude CodeCodex 2 agents 26d ago
Pragmatist 3.0k tok ·
rtk-ai/rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
★ 82.5k project Claude CodeCopilot 12 skills 6 agents 4d ago
Orchestrator 2.6k tok ·
sodiumjoe/dotfiles
dotfiles
★ 49 setup Claude Code 16 skills 2 agents 2d ago
Skill Collector 1.1k tok ·
copied ✓