Ops Sentinel — Development agent for Claude Code
Interprets the back office's own run ledger, flagging failing or missed jobs, repeated failures, cost spikes and approvals about to expire.
How to install Ops Sentinel
Installs to ~/.claude/agents/altanziya-agentic-backoffice-ops-sentinel.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/altanziya/agentic-backoffice/HEAD/.claude/agents/ops-sentinel.md -o ~/.claude/agents/altanziya-agentic-backoffice-ops-sentinel.md Restart Claude Code, or start a new session, for it to be picked up.
What Ops Sentinel does
name: ops-sentinel description: Interprets the back office's own run ledger, flagging failing or missed jobs, repeated failures, cost spikes and approvals about to expire. Use for "is the back office healthy" and incident triage. tools: Read, Grep, Glob, Write, Edit, mcp__backoffice__ops_status, mcp__backoffice__list_actions, mcp__backoffice__propose_action model: haiku effort: low skills: source-discipline, report-format, propose-action, ops-check backoffice: writes: - workspace/repor
Alternatives in Development
- Fg Finance Orchestrator — Finance Guru Master Portfolio Orchestrator (Cassandra Holt) 317 ★
- Sentinel Apex Guardian 89 ★
- Openclaw Debugger — Use when an OpenClaw instance has a problem the health sentinel couldn't fix — gateway failures, config drift 75 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Smith Replicator
Spawns and tears down watcher clones under load. Invoke when sentinel subscription volume crosses a threshold,
Simplify Reuse Reviewer
Read-only reuse lens of the HIGH simplify pass: missed local helpers, duplicated logic, repeated literals/conf
Etrnl Investigator
Use this agent when an ETRNL execution run is blocked by a failing command, ambiguous root cause, or repeated
Treasurer
Efficiency auditor (Sonnet) that checks whether agents drifted - repeated failing approaches, work nobody aske
Personal Archivist
Local-only archivist for Guillaume's personal documents (~/Documents). Use to locate a document, answer 'where
Deployment Verifier
Validates deployments via health checks, smoke tests, and monitoring verification. Use after deploying to veri
Related Skills
Analyze Sessions
Audit recent AI coding sessions to find repeated mistakes, speed losses, and missed Nimbalyst tool usage — the
Claude Code Discipline Skills
Seven Claude Code skills that stop an LLM agent asserting what it has not measured. Each born from a dated pro
Flake Audit
Detect intermittently-failing tests from recent CI history (or repeated local runs); dedupe against tracked fl