Skip to main content

/sentinel

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

name: sentinel version: 2.0 description: > Run full system audit using 5-agent team (BA, Architect, Developer, Tester, Validator). Use when: "audit the system", "run sentinel", "system health check", "/sentinel", "review infrastructure", "find issues", "what's broken". argument-hint: "[target] — e.g. 'tools', 'hooks', 'Drop project', 'daemons', or empty for full audit" level: 4 company: ALAI

/sentinel — System Audit Team

Purpose

5-agent parallel audit that delivers a consolidated report with prioritized action items. BA + Architect + Developer + Tester run in parallel → Validator consolidates.

Variables

Variable Type Description Default
target string Audit scope full system
model string Agent model sonnet
depth string shallow | deep deep

Team

Role Agent 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

Workflow

Phase 1: Pre-flight

  • Read audit target/scope from $ARGUMENTS
  • if no target → set target = "full system"
  • if target = "quick" → set depth = shallow (skip code quality, focus on daemons + health)

Phase 2: Parallel Audit (4 agents simultaneously)

Spawn 4 sub-agents in parallel using CONTEXT ISOLATION PATTERN:

For each agent, use ~/system/tools/dispatch-isolated.sh or inject isolation preamble:

  1. Load ~/system/prompts/SUBAGENT_ISOLATION.md template
  2. Instruct agent: "Write FULL audit to /tmp/{task_id}-{role}-deliverables.md"
  3. Request: "Return ONLY 100-word summary + deliverable path + memory_candidates"
  4. Role-specific prompt from ~/.claude/agents/sentinel-{role}.md
  5. Audit target + key paths: ~/system/, ~/.claude/, ~/system/databases/
[Parallel with isolation]:
  Task(sentinel-ba)        → /tmp/sentinel-ba-deliverables.md + summary
  Task(sentinel-architect) → /tmp/sentinel-arch-deliverables.md + summary
  Task(sentinel-developer) → /tmp/sentinel-dev-deliverables.md + summary
  Task(sentinel-tester)    → /tmp/sentinel-test-deliverables.md + summary

Token savings: Each agent returns ~150 tokens (summary) instead of 200K+ (full report).

Phase 3: Validation (after all 4 complete)

Collect summaries from 4 agents. If critical issues flagged OR deep audit requested:

  • Read full deliverable files via Read tool
  • Extract relevant sections only (not entire 200K+ report)

Spawn Validator with summaries + selective excerpts:

Task(sentinel-validator, input=[
  ba_summary + critical_excerpts,
  arch_summary + critical_excerpts,
  dev_summary + critical_excerpts,
  test_summary + critical_excerpts
])
  → consolidated final report at /tmp/sentinel-final-deliverables.md

Validator also uses isolation pattern — returns summary + deliverable path.

Phase 4: Output

  • Print final report from Validator
  • if critical issues found → create MC tasks via delegate_task
  • if minor issues → list as recommendations

Report Format

SENTINEL AUDIT REPORT
Target: [scope]
Date: [timestamp]
Model: [sonnet|opus]

CRITICAL (fix immediately):
  [numbered list]

HIGH (fix this week):
  [numbered list]

MEDIUM (backlog):
  [numbered list]

MC Tasks Created: [list of task IDs]
Next Audit: [recommended interval]

$ARGUMENTS

Back to top