gtapps/hermit-health
plugins/claude-code-hermit/skills/hermit-health/SKILL.md
Show alert state, proposal queue depth, routine engagement, and channel availability. Activates on messages like 'health check', 'how's the hermit', 'is anything broken', 'hermit health', 'system health', 'anything wrong', 'hermit status', 'are routines running'.
$ install --global
skillsauthnpx skillsauth add gtapps/claude-code-hermit hermit-healthInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 29, 2026, 4:09 AM139.1s1 file scanned
SKILL.md
- name:
- hermit-health
- description:
- Show alert state, proposal queue depth, routine engagement, and channel availability. Activates on messages like 'health check', 'how's the hermit', 'is anything broken', 'hermit health', 'system health', 'anything wrong', 'hermit status', 'are routines running'.
Hermit Health
Synthesize a compact infrastructure snapshot: active alerts, proposal queue, routine engagement, and whether channels are ready for outbound sends.
Step 0 — Channel reply
If this skill was invoked from a channel-arrived message (the inbound prompt contains a <channel source="..."> tag), reply via that channel's reply tool. Otherwise emit to conversation.
Scope
Read the following (gracefully skip any file that doesn't exist):
.claude-code-hermit/state/alert-state.json—activearray andsuppressedarray; each entry hastype,timestamp,message..claude-code-hermit/state/runtime.json—last_activity,session_id..claude-code-hermit/state/reflection-state.json—last_reflectiontimestamp andcounters.judge_suppress_by_codemap..claude-code-hermit/config.json—routinesarray (id, schedule, enabled);channelsobject (each channel'sdm_channel_id)..claude-code-hermit/proposals/PROP-*.md— glob; count bystatusfrontmatter field.
Analysis
Alerts: Count entries in alert-state.json → active. For each, compute age from timestamp. Show oldest. If none: "No active alerts."
Proposal queue: Count proposals with status: proposed (pending operator review) and status: accepted (in flight, not yet resolved). If both zero: "Queue empty."
Routine engagement: From config.json.routines, list each routine with enabled: true and its schedule. For the reflect routine, use reflection-state.json → last_reflection to show when it last ran; also check counters.judge_suppress_by_code — if any code has a non-zero count, append a compact suppress-mix suffix on the same bullet: suppress mix — no-evidence:N, covered-by-memory:N, no-sessions:N (omit codes with count 0; omit the suffix entirely when all counts are 0 or the map is absent). For other routines, report schedule and enabled state — per-routine last-run tracking is not yet available.
Channel availability: From config.json.channels, for each configured channel, check whether dm_channel_id is set. Report "ready" or "not yet paired (no dm_channel_id — send a message first)".
Output
Reply in ≤1500 chars. Use exactly this section structure:
### Alerts
- N active (oldest: [type] Xd ago) [or "No active alerts"]
(or: Alerts — alert-state.json not found (hermit not yet initialized).)
### Proposal queue
- N proposed (pending review), N accepted (in flight)
(or: Queue empty.)
### Routine engagement
- [id]: enabled, schedule [cron], [last run or "no run data"] [suppress mix suffix if applicable]
- [id]: disabled
(or: Routine engagement — config.json not found.)
### Channel availability
- [channel]: ready (dm_channel_id set) [or "not yet paired"]
(or: No channels configured — run /claude-code-hermit:channel-setup.)
Omit sections that have no data rather than showing a heading with an empty body. Keep each bullet to one line.
Related Skills
gtapps/cost-reflect
development
VerifiedTrustedCommunity
Use when the user asks about cost structure or composition: which token types cost the most, how cache reads compare to output costs, which sessions are draining budget, or what cold starts add up to. This is the 'why is my bill high' skill. It audits where spend goes across token categories (cache_read, cache_write, output, input) and per-session attribution. Invoke for questions like 'cost breakdown', 'which sessions are expensive', 'what's driving spend', or 'cold start costs'. Not for week-over-week trend lines (use hermit-evolution) or simple total-spend summaries.
59SKILL.mdUpdated Jun 6, 2026
gtapps/ha-presence-report
tools
VerifiedTrustedCommunity
Presence history & tracker-health report — current home/away state, reliability, recent arrival/departure transitions, and activity patterns for person/device_tracker entities. Use when the operator asks about presence history or when a presence-dependent automation (locks, alarm, vacuum, climate) misbehaves.
59SKILL.mdUpdated Jun 4, 2026
gtapps/ha-evening-brief
development
VerifiedTrustedCommunity
Evening house brief — end-of-day security check, device status, and energy snapshot. Runs as a daily routine at 22:30 or on demand.
59SKILL.mdUpdated Jun 4, 2026
gtapps/ha-automation-explorer
tools
VerifiedTrustedCommunity
Browse and explain the hermit's Home Assistant automations — list by topic, filter by keyword with plain-language YAML explanations, or sort by last-fired. Read-only. Use when the operator asks "what automations do I have / what does this one do / which haven't fired."
59SKILL.mdUpdated Jun 4, 2026