chacosoldier/compabob
A customizable Claude Code setup for knowledge workers: agents, safety hooks, skills, memory, and an Obsidian knowledge base. Clone, run setup, make it yours.
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
GUARDRAILS
4/5
Blocks destructive commands · 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 chacosoldier/compabob/.claude ./rig-compabob # 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 chacosoldier/compabob/.claude/skills/add-agent .claude/skills/add-agent $ npx degit chacosoldier/compabob/.claude/skills/build-list .claude/skills/build-list $ npx degit chacosoldier/compabob/.claude/skills/chart-tufte .claude/skills/chart-tufte $ npx degit chacosoldier/compabob/.claude/skills/council .claude/skills/council $ npx degit chacosoldier/compabob/.claude/skills/document-export .claude/skills/document-export $ npx degit chacosoldier/compabob/.claude/skills/handover .claude/skills/handover $ npx degit chacosoldier/compabob/.claude/skills/index-memory .claude/skills/index-memory $ npx degit chacosoldier/compabob/.claude/skills/log-decision .claude/skills/log-decision $ npx degit chacosoldier/compabob/.claude/skills/mcp-debug .claude/skills/mcp-debug $ npx degit chacosoldier/compabob/.claude/skills/meeting-prep .claude/skills/meeting-prep $ npx degit chacosoldier/compabob/.claude/skills/memory-debt .claude/skills/memory-debt $ npx degit chacosoldier/compabob/.claude/skills/merge-contacts .claude/skills/merge-contacts $ npx degit chacosoldier/compabob/.claude/skills/morning-brief .claude/skills/morning-brief $ npx degit chacosoldier/compabob/.claude/skills/post-call .claude/skills/post-call $ npx degit chacosoldier/compabob/.claude/skills/reflect .claude/skills/reflect $ npx degit chacosoldier/compabob/.claude/skills/system-audit .claude/skills/system-audit $ npx degit chacosoldier/compabob/.claude/skills/tasks .claude/skills/tasks $ npx degit chacosoldier/compabob/.claude/skills/visual-explainer .claude/skills/visual-explainer $ npx degit chacosoldier/compabob/.claude/skills/weekly-review .claude/skills/weekly-review
$ curl -fsSL --create-dirs -o .claude/agents/_orchestrator-reference.md https://raw.githubusercontent.com/chacosoldier/compabob/main/.claude/agents/_orchestrator-reference.md $ curl -fsSL --create-dirs -o .claude/agents/analyst.md https://raw.githubusercontent.com/chacosoldier/compabob/main/.claude/agents/analyst.md $ curl -fsSL --create-dirs -o .claude/agents/comms-meetings.md https://raw.githubusercontent.com/chacosoldier/compabob/main/.claude/agents/comms-meetings.md $ curl -fsSL --create-dirs -o .claude/agents/crm-relationships.md https://raw.githubusercontent.com/chacosoldier/compabob/main/.claude/agents/crm-relationships.md $ curl -fsSL --create-dirs -o .claude/agents/daily-copilot.md https://raw.githubusercontent.com/chacosoldier/compabob/main/.claude/agents/daily-copilot.md $ curl -fsSL --create-dirs -o .claude/agents/error-handling.md https://raw.githubusercontent.com/chacosoldier/compabob/main/.claude/agents/error-handling.md $ curl -fsSL --create-dirs -o .claude/agents/first-principles.md https://raw.githubusercontent.com/chacosoldier/compabob/main/.claude/agents/first-principles.md $ curl -fsSL --create-dirs -o .claude/agents/principal-engineer.md https://raw.githubusercontent.com/chacosoldier/compabob/main/.claude/agents/principal-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/second-brain.md https://raw.githubusercontent.com/chacosoldier/compabob/main/.claude/agents/second-brain.md $ curl -fsSL --create-dirs -o .claude/agents/strategy-advisor.md https://raw.githubusercontent.com/chacosoldier/compabob/main/.claude/agents/strategy-advisor.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"ask": [
"Bash"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "python3 \"$CLAUDE_PROJECT_DIR/hooks/hook-block-dangerous.py\""
},
{
"type": "command",
"command": "python3 \"$CLAUDE_PROJECT_DIR/hooks/hook-comms-guard.py\""
}
]
},
{
"matcher": "Read",
"hooks": [
{
"type": "command",
"command": "python3 \"$CLAUDE_PROJECT_DIR/hooks/hook-protect-secrets.py\""
}
]
},
{
"matcher": "ExitPlanMode",
"hooks": [
{
"type": "command",
"command": "python3 \"$CLAUDE_PROJECT_DIR/hooks/hook-plan-premortem.py\""
}
]
}
]
}
} Skills (19)
add-agentbuild-listchart-tuftecouncildocument-exporthandoverindex-memorylog-decisionmcp-debugmeeting-prepmemory-debtmerge-contactsmorning-briefpost-callreflectsystem-audittasksvisual-explainerweekly-review
Subagents (10)
| _orchestrator-reference | — |
| analyst model: inherit | Metrics, KPIs, and data-backed analysis. Use for pipeline and revenue figures, dashboards, forecasts, trend and cohort analysis, variance investigation, and any question that needs numbers decomposed |
| comms-meetings model: inherit | Email triage, meeting preparation, daily and weekly briefings, communication drafting, and follow-up tracking. Use for "what's in my inbox", "prep me for my meeting with X", "draft a reply to Y", "wha |
| crm-relationships model: inherit | Contacts, pipeline, and relationship tracking. Use for looking up a person or account, recording an interaction, tracking deal or opportunity stages, deduplication, and "who do I know at X" or "what's |
| daily-copilot model: inherit | The everyday work partner. Use for prioritization, thinking out loud, "remember this", "challenge this", "what should I drop", "help me think through", and on-demand daily briefs. The default agent fo |
| error-handling | — |
| first-principles model: inherit | Rigorous abstract reasoning. Use to reason a problem from scratch, decompose a concept to its fundamentals, calibrate a prediction, run scenario analysis under deep uncertainty, or synthesize opposing |
| principal-engineer model: inherit | Senior engineering voice for technical decisions. Use to design a system, review code or architecture, choose between technologies, assess technical debt, or do a security review. Reasons against mode |
| second-brain model: inherit | Knowledge base management. Use for taking notes, creating and retrieving meeting records, research synthesis, finding what was discussed with a person or on a topic, and keeping the vault healthy (wik |
| strategy-advisor model: inherit | Strategic sparring partner. Use when bringing a plan, idea, or decision for critique, or for pre-mortems, steelmans, second-order analysis, and "should I do X". Challenges assumptions and surfaces wha |
Hooks (8)
| event | matcher | runs |
|---|---|---|
| SessionStart | startup|resume|clear|compact|fork | bash "$CLAUDE_PROJECT_DIR/hooks/hook-session-start.sh" |
| UserPromptSubmit | * | bash "$CLAUDE_PROJECT_DIR/hooks/hook-inject-now.sh" |
| PreToolUse | Bash | python3 "$CLAUDE_PROJECT_DIR/hooks/hook-block-dangerous.py" |
| PreToolUse | Bash | python3 "$CLAUDE_PROJECT_DIR/hooks/hook-comms-guard.py" |
| PreToolUse | Read | python3 "$CLAUDE_PROJECT_DIR/hooks/hook-protect-secrets.py" |
| PreToolUse | ExitPlanMode | python3 "$CLAUDE_PROJECT_DIR/hooks/hook-plan-premortem.py" |
| Stop | * | python3 "$CLAUDE_PROJECT_DIR/hooks/hook-style-gate.py" |
| PostToolUse | Bash|Read|WebFetch|WebSearch|mcp__.* | python3 "$CLAUDE_PROJECT_DIR/hooks/prompt-injection-defender/post-tool-defender.py" |
Permissions
deny (0)
—
ask (1)
Bash
allow (5)
Read
Glob
Grep
WebSearch
WebFetch
Similar rigs
davidianstyle/openbrain-claude-starter
Portable template for a personal AI Chief of Staff built on an Obsidian LYT vault and Claude Code. One-script setup wires multi-account Gmail, Calendar, Drive, Slack, Asana, and Fathom MCPs, plus 21 Chief of Staff skills.
Skill Collector 9.5k tok ·
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.
Fort Knox 3.9k tok ·
sohaibdevv/Claude-Starter-Kit
A pre-built configuration that gives Claude Code persistent memory, security guardrails, and structured workflows. Clone, run setup.sh, and your next session picks up where the last one left off.
Pragmatist 435 tok ·
paulophl94/cadence-os
An AI-powered operating system, built on Cursor. 14 document templates, 6 multi-perspective reviewers, 7 workflow skills, and a complete personal planning system. Fork it, configure your product context, start shipping better documents in 1
Skill Collector 6.8k tok ·