Skip to content
Get packs

Hermes Sidecar Observability

Check health, diagnose failed tasks, trace sessions, and update a Hermes sidecar for LifeOS

Source Download skill
Repository
danielmiessler/LifeOS
Stars
19,682
Licence
MIT
Files
6 files

What it does

This skill lets an AI agent inspect a Hermes sidecar, which is a separate background assistant install that LifeOS uses for messaging and scheduled tasks. Once installed, the agent can answer whether the sidecar is healthy, explain why tasks or cron jobs failed, and trace exactly what happened inside a single session by reading the sidecar's own logs and databases. It is designed to diagnose without changing anything, and only the Update intent is allowed to modify the sidecar.

Great for

  • Developers running a Hermes sidecar alongside LifeOS who need to debug failed iMessage or chat tasks
  • Operators who want to confirm the LifeOS soul (persona file) is actually loading in sidecar sessions
  • People checking whether their Hermes install is up to date and healthy after an upgrade

Skip it if

  • Users without a Hermes sidecar installed, since the skill reports 'absent' and has nothing to observe
  • Anyone wanting general messaging or LifeOS service management, which the skill explicitly excludes; the reason is that those are handled by other skills
  • Situations needing live fixes without review, because the skill is built to diagnose and route fixes through policy tools rather than edit config directly

Try asking

  • “Why did my Hermes iMessage task fail this morning?”
  • “Is the Hermes sidecar healthy and running LifeOS?”
  • “Trace what happened to the message I sent to Hermes yesterday”
  • “Is Hermes up to date, and check it after the upgrade”
Step-by-step guide: how to use Hermes Sidecar ObservabilityInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 6 original files, the MIT licence and an attribution note.

    Hermes.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip Hermes.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip Hermes.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Start with a status check so the agent confirms the sidecar and soul state before deeper triage
  • Give the trace intent a specific task, time, or channel so it can pick the right session, since blocked-guard records are matched by time window only
  • Read the reported owner of any failure (Policy.ts, soul files, approval allowlist, or upstream Hermes) before making changes yourself

What's inside

  • Intents/Status.md
  • Intents/Trace.md
  • Intents/Triage.md
  • Intents/Update.md
  • Setup.md
  • SKILL.md

Redistributed unmodified from danielmiessler/LifeOS under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.