Skip to main content

/sentinel

Source: ~/.claude/skills/sentinel/SKILL.md

/sentinel — System Audit Team

Description

Spawns a 5-agent audit team (BA, Architect, Developer, Tester, Validator) that performs a comprehensive system audit and delivers a consolidated report with prioritized action items.

Invocation

/sentinel [target]
  • No target = full system audit
  • Target examples: "tools", "hooks", "offline", "Drop project", "daemons"

Team Composition

Role Agent File Focus
BA sentinel-ba.md Business value, gaps, redundancy, ROI
Architect sentinel-architect.md Architecture, integrations, offline/online parity
Developer sentinel-developer.md Code quality, dead code, tech debt, bugs
Tester sentinel-tester.md Functional testing, daemon health, data integrity
Validator sentinel-validator.md Cross-reference, consolidate, final action plan

Execution Flow

Phase 1: Parallel Audit (4 agents)

Spawn BA, Architect, Developer, and Tester as parallel Task agents (sonnet model). Each agent receives:

  1. Their role-specific prompt from ~/.claude/agents/sentinel-{role}.md
  2. The audit target/scope
  3. Key system paths to investigate
Task(subagent_type="general-purpose", model="sonnet", name="sentinel-ba")
Task(subagent_type="general-purpose", model="sonnet", name="sentinel-architect")
Task(subagent_type="general-purpose", model="sonnet", name="sentinel-developer")
Task(subagent_type="general-purpose", model="sonnet", name="sentinel-tester")

Phase 2: Validation (1 agent)

After all 4 complete, spawn Validator with ALL 4 reports as input.

Task(subagent_type="general-purpose", model="sonnet", name="sentinel-validator")

Phase 3: Delivery

  • Save final report to ~/system/reports/sentinel-audit-{date}.md
  • Post summary to HiveMind
  • Present findings to user

Agent Constraints

  • Model: sonnet (NEVER opus for agents)
  • All agents: READ-ONLY. No file modifications.
  • Tester: Only runs safe, non-destructive commands
  • Each agent produces structured markdown report

Key System Paths for Agents

~/.claude/hooks/          — Hook scripts (Python/Bash)
~/.claude/skills/         — Skill definitions
~/.claude/agents/         — Agent definitions
~/.claude/mcp.json        — MCP server config
~/.claude/settings.json   — Claude settings + permissions
~/system/tools/           — All system tools
~/system/tools/manifest.md — Tool registry
~/system/rules/           — Business & dev rules
~/system/agents/hivemind/ — Knowledge base
~/system/db/              — SQLite databases
~/system/config/          — Configuration files
~/system/context/         — Context documents
~/system/specs/           — Specifications
~/system/boot.sh          — Boot sequence
~/Library/LaunchAgents/   — Daemon definitions

Reuse

This skill is designed to be called repeatedly. Each run produces a dated report. Compare reports over time to track system health trajectory.

Back to top