agentrigs
+ submit rig
~ / rigs / onurpolat05 / ALBA

onurpolat05/ALBA

Turn Claude Code into a personal AI agent with persistent memory. Interactive setup, 9 skills, 8 hooks, role-agnostic. Verified against v2.1.220.

↗ GitHub ★ 22 MIT updated 2mo ago project Claude Code
share on X
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
CONTEXT TAX · EVERY TURN
~3.9k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
5/5
Blocks destructive commands · Protects secrets · Pre-tool screening hook · No YOLO mode · Sandbox or ask-first rules · details

Copy this rig

# review before running: this installs third-party code
$ npx degit onurpolat05/ALBA/examples/content-creator/.claude ./rig-alba  # 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 onurpolat05/ALBA/.claude/skills/create-skill .claude/skills/create-skill
$ npx degit onurpolat05/ALBA/.claude/skills/end .claude/skills/end
$ npx degit onurpolat05/ALBA/.claude/skills/extend .claude/skills/extend
$ npx degit onurpolat05/ALBA/.claude/skills/reflect .claude/skills/reflect
$ npx degit onurpolat05/ALBA/.claude/skills/research .claude/skills/research
$ npx degit onurpolat05/ALBA/.claude/skills/setup .claude/skills/setup
$ npx degit onurpolat05/ALBA/.claude/skills/start .claude/skills/start
$ npx degit onurpolat05/ALBA/.claude/skills/status .claude/skills/status
$ npx degit onurpolat05/ALBA/.claude/skills/weekly-review .claude/skills/weekly-review
$ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/onurpolat05/ALBA/main/examples/content-creator/.claude/agents/planner.md
$ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/onurpolat05/ALBA/main/examples/developer/.claude/agents/planner.md
$ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/onurpolat05/ALBA/main/examples/founder/.claude/agents/planner.md
$ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/onurpolat05/ALBA/main/examples/project-manager/.claude/agents/planner.md
$ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/onurpolat05/ALBA/main/examples/researcher/.claude/agents/planner.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(sudo:*)",
      "Read(.env)",
      "Edit(.env)",
      "Read(**/.aws/credentials*)",
      "Read(**/.ssh/id_*)",
      "Bash(sudo:*)",
      "Read(.env)",
      "Edit(.env)",
      "Read(**/.aws/credentials*)",
      "Read(**/.ssh/id_*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push --force:*)",
      "Bash(npm publish:*)",
      "Edit(**/*.env)",
      "Bash(git push:*)",
      "Bash(git push --force:*)",
      "Bash(npm publish:*)",
      "Edit(**/*.env)"
    ]
  },
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "bash ${CLAUDE_PROJECT_DIR}/.claude/hooks/bash-validator.sh"
          },
          {
            "type": "command",
            "command": "bash ${CLAUDE_PROJECT_DIR}/.claude/hooks/bash-validator.sh"
          }
        ]
      }
    ]
  }
}

Skills (9)

create-skillendextendreflectresearchsetupstartstatusweekly-review

Subagents (5)

plannerBreaks a complex goal into ordered, estimated steps with dependencies and risks. Use when a task needs 3+ steps, when sequencing or effort is unclear, or when the user says "plan this", "break this do
plannerBreaks a complex goal into ordered, estimated steps with dependencies and risks. Use when a task needs 3+ steps, when sequencing or effort is unclear, or when the user says "plan this", "break this do
plannerBreaks a complex goal into ordered, estimated steps with dependencies and risks. Use when a task needs 3+ steps, when sequencing or effort is unclear, or when the user says "plan this", "break this do
plannerBreaks a complex goal into ordered, estimated steps with dependencies and risks. Use when a task needs 3+ steps, when sequencing or effort is unclear, or when the user says "plan this", "break this do
plannerBreaks a complex goal into ordered, estimated steps with dependencies and risks. Use when a task needs 3+ steps, when sequencing or effort is unclear, or when the user says "plan this", "break this do

Hooks (18)

eventmatcherruns
SessionStart*bash ${CLAUDE_PROJECT_DIR}/.claude/hooks/session-start.sh
UserPromptSubmit*bash ${CLAUDE_PROJECT_DIR}/.claude/hooks/agent-suggest.sh
PreToolUseBashbash ${CLAUDE_PROJECT_DIR}/.claude/hooks/bash-validator.sh
PostToolUseBashbash ${CLAUDE_PROJECT_DIR}/.claude/hooks/error-logger.sh
PostToolUseFailure*bash ${CLAUDE_PROJECT_DIR}/.claude/hooks/error-logger.sh
Stop*bash ${CLAUDE_PROJECT_DIR}/.claude/hooks/memory-check.sh
SessionEnd*bash ${CLAUDE_PROJECT_DIR}/.claude/hooks/session-end.sh
PreCompact*bash ${CLAUDE_PROJECT_DIR}/.claude/hooks/pre-compact.sh
PostCompact*bash ${CLAUDE_PROJECT_DIR}/.claude/hooks/post-compact.sh
SessionStart*bash ${CLAUDE_PROJECT_DIR}/.claude/hooks/session-start.sh
UserPromptSubmit*bash ${CLAUDE_PROJECT_DIR}/.claude/hooks/agent-suggest.sh
PreToolUseBashbash ${CLAUDE_PROJECT_DIR}/.claude/hooks/bash-validator.sh
PostToolUseBashbash ${CLAUDE_PROJECT_DIR}/.claude/hooks/error-logger.sh
PostToolUseFailure*bash ${CLAUDE_PROJECT_DIR}/.claude/hooks/error-logger.sh
Stop*bash ${CLAUDE_PROJECT_DIR}/.claude/hooks/memory-check.sh
SessionEnd*bash ${CLAUDE_PROJECT_DIR}/.claude/hooks/session-end.sh
PreCompact*bash ${CLAUDE_PROJECT_DIR}/.claude/hooks/pre-compact.sh
PostCompact*bash ${CLAUDE_PROJECT_DIR}/.claude/hooks/post-compact.sh

Permissions

deny (10)
Bash(sudo:*)
Read(.env)
Edit(.env)
Read(**/.aws/credentials*)
Read(**/.ssh/id_*)
Bash(sudo:*)
Read(.env)
Edit(.env)
Read(**/.aws/credentials*)
Read(**/.ssh/id_*)
ask (8)
Bash(git push:*)
Bash(git push --force:*)
Bash(npm publish:*)
Edit(**/*.env)
Bash(git push:*)
Bash(git push --force:*)
Bash(npm publish:*)
Edit(**/*.env)
allow (24)
Bash(git status:*)
Bash(git diff:*)
Bash(git log:*)
Bash(git branch:*)
Bash(ls:*)
Bash(cat:*)
Bash(head:*)
Bash(tail:*)
Bash(wc:*)
Read(memory/**)
Read(.claude/**)
Edit(memory/**)
Bash(git status:*)
Bash(git diff:*)
Bash(git log:*)
Bash(git branch:*)
Bash(ls:*)
Bash(cat:*)
Bash(head:*)
Bash(tail:*)
Bash(wc:*)
Read(memory/**)
Read(.claude/**)
Edit(memory/**)

Similar rigs

hashgraph-online/hol-guard
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
★ 784 project Codex 3 skills 3d ago
Minimalist 397 tok ·
greenpolo/cc-multi-cli-plugin
Claude Code plugin: delegate to Codex, Gemini, Cursor, GitHub Copilot, and Qwen CLIs via their native protocols (ACP, ASP). Use /gemini:research, /cursor:debug, /codex:execute, /copilot:review and more — Claude can also auto-dispatch.
★ 92 collection Claude CodeCodex 5 skills 23d ago
Pragmatist 2.2k tok ·
orwa-mahmoud/nightshift
Accountable long-running coding shifts for Cursor, Codex, and Claude Code. Safe autonomy, recovery, persistent state, and reviewable results a clear view of what’s done, in progress, parked, or blocked—without scrolling a marathon chat.
★ 76 project Codex 15 skills today
Skill Collector 756 tok ·
sendbird/cc-plugin-codex
An open-source plugin that runs inside Codex and lets you use Claude Code and Claude models for review, rescue, and tracked background workflows.
★ 217 project Claude CodeCodex 7 skills 11d ago
Pragmatist 620 tok ·
copied ✓