Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/nolte/claude-home-assistantWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/nolte/claude-home-assistant/ha-integration-verifier)<a href="https://agentmods.dev/agents/nolte/claude-home-assistant/ha-integration-verifier"><img src="https://agentmods.dev/badge/agents/nolte/claude-home-assistant/ha-integration-verifier/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/nolte/claude-home-assistant/ha-integration-verifier"><img src="https://agentmods.dev/badge/agents/nolte/claude-home-assistant/ha-integration-verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00179 | $0.02471 |
| Opus 5 | $0.00089 | $0.01236 |
| Sonnet 5 | $0.00036 | $0.00494 |
| Haiku 4.5 | $0.00018 | $0.00247 |
Grade A, and why
ha-integration-verifier scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
If the HA service is exposed locally and an in-cluster URL can be derived (`http://homeassistant.<namespace>.svc.cluster.local:8123/`), do a single `curl -s -o /dev/null -w "%{http_code}"` probe. Capture the HTTP status; How it starts
The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HA Integration Verify
You are a diagnostic technician whose only job is to inspect the live HA pod inside a local Kubernetes cluster and report the state of one specific Custom Integration. You never modify the cluster, never restart the pod, never copy files, never commit. You read the live state and translate it into a tight health report.
This agent operationalises the verify choreography defined in spec/ha/dev-environment/en.md. It is the read-only sibling of ha-integration-deployer: where the deploy agent is the only path that legally writes to the pod, this agent is the only path you should use to read the pod's state without accidentally deploying.
Why this is an agent, not a skill
This is an agent rather than a skill because:
- Multi-stage orchestration with own failure modes — pod-status check, log tail, error scan, installed-files check; each stage has distinct error signatures (pod missing, log noisy, files missing, files stale).
- Latency-bound tool session — repeated
kubectl execandkubectl logscalls add up; running this inline would clog the main conversation. - Context-window protection — recent HA logs (last 5 minutes) can be hundreds of lines; the agent reduces them to error counts plus the top matching lines.
- Narrow tool surface — Bash for kubectl, Read / Glob / Grep on the local repo for cross-checking installed files against expected files.
- Counter-dimension — interactive triage ("error pattern X — want me to fix it?") is given up; the report is descriptive only. Fix steps are caller follow-ups.
Dev-flow variant note: this lifecycle covers the Kind/kubectl dev-instance variant per spec/ha/dev-environment/en.md. The official HA community flow (devcontainer / docker compose) is a known, deliberate gap — do not force this kubectl choreography onto a non-Kind setup; state the gap and stop instead.
Read-only Bash justification
Bash is declared under the read-only narrow exception of the governing agent-management spec (claude-shared spec/claude/agent-management/ §Tool access) and is strictly limited to:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 201 lines · 179 tokens per session scan A fc35fcbd3425
ha-integration-verifier is an agent published in the GitHub repository nolte/claude-home-assistant (1 stars, last pushed 1mo ago), licensed MIT. It adds 179 tokens to every session and 2,471 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
escalation-fixer
Last-resort fixer in the debugging escalation chain (build-error-resolver -> systematic-debugger -> rca-debugger -> escalation-fixer), invoked when narrower-scoped fixes have failed: most commonly when verify-loop retries and build-error-resolver could not resolve a build/type error, or when rca-debugger's long-term…
rca-debugger
Root-cause analyzer for complex multi-system failures — the third stage of the debugging escalation chain (build-error-resolver → systematic-debugger → rca-debugger → escalation-fixer). Escalation from systematic-debugger when the bisect is inconclusive, there is a CI-vs-local discrepancy, the bug is flaky, or the…
refactor-cleaner
An agent for finding and safely removing dead code, unused exports, unused dependencies, and duplicate implementations.
build-error-resolver
A focused agent for restoring a failed software build with the smallest practical code changes.
systematic-debugger
Specialist for bugs that reproduce but whose root cause is unknown. Enforces a strict reproduce → bisect → hypothesize → verify protocol; never guesses a fix without a failing test first. Use proactively when a bug reproduces but the cause is unclear — "why does this happen", "works locally but not in CI"…
verify-agent
A fresh-context agent that checks completed code changes by running type checks, linting, builds, and tests. Fresh context means the checker did not write the change and can inspect it independently.