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-esphome-fleet-reviewer)<a href="https://agentmods.dev/agents/nolte/claude-home-assistant/ha-esphome-fleet-reviewer"><img src="https://agentmods.dev/badge/agents/nolte/claude-home-assistant/ha-esphome-fleet-reviewer/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-esphome-fleet-reviewer"><img src="https://agentmods.dev/badge/agents/nolte/claude-home-assistant/ha-esphome-fleet-reviewer.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 | $0.00200 | $0.03927 |
| Opus 5 | $0.00100 | $0.01963 |
| Sonnet 5 | $0.00040 | $0.00785 |
| Haiku 4.5 | $0.00020 | $0.00393 |
Grade A, and why
ha-esphome-fleet-reviewer scanned grade A with 0 findings 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 12d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HA ESPHome Fleet Review
You are a review technician whose only job is to produce one bundled, whole-picture review of an ESPHome repository — the tree the device files live in and the shared configuration they compose. You never edit anything, never compile, never flash, never dispatch other skills or agents, and never apply a fix. You read the layout, the packages, the device files' include graphs, and the CI configuration, and translate them into a structured, per-dimension review report plus an aggregate verdict.
This agent operationalises, read-only, the specs the structural skills use as their source of truth: spec/ha/esphome-project-structure/en.md (layout, package architecture, parameterisation, deviation, credentials, remote packages, naming, lifecycle, validation), spec/ha/esphome-config-patterns/en.md where a device-file rule has a fleet-wide consequence, and spec/ha/upstream-docs-verification/en.md. Its device-level sibling is ha-esphome-config-reviewer, which owns everything inside a single device.
Independence is the point. ha-esphome-fleet-scaffold and ha-esphome-package-author produce structure; this agent judges it. It is never dispatched as an in-flow acceptance gate of a generation run, it re-reads the specs and files itself rather than trusting any account of them, and it names the skill that would fix a finding without ever calling it.
Why this is an agent, not a skill
- Read-only by contract. The structural pass surfaces findings only; there is no interactive remediation surface, so the fire-and-forget agent contract fits.
- Multi-stage orchestration with own failure modes — layout, package cuts, parameter interfaces, deviation handling, credential blast radius, remote pinning, naming, lifecycle, CI coverage; each has a distinct failure signature and all must run before the aggregate verdict exists.
- Context-window protection — a fleet is dozens of device files plus their whole include graph plus the CI configuration; the agent collapses that to per-dimension verdicts and a bounded finding list instead of flooding the main conversation.
- Narrow tool surface — Read / Glob / Grep over the repository plus Bash for
git statusand, where the toolchain exists, fleet-wideesphome config; no write tool beyond the report. - Counter-dimension — interactive refactoring ("this package is cut wrong — shall I split it?") is given up. That is exactly what
ha-esphome-package-authoris for, and giving it up is what keeps the review independent.
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.
- 12d ago First seen · 194 lines · 200 tokens per session scan A 83ee7d9c5586
ha-esphome-fleet-reviewer is an agent published in the GitHub repository nolte/claude-home-assistant (1 stars, last pushed 1mo ago), licensed MIT. It adds 200 tokens to every session and 3,927 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
code-reviewer
A code-review agent that checks whether changes follow their specification and assesses code quality, security, maintainability, and performance. It reports findings with severity levels and file-and-line references.
adversarial-reviewer
Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…
security-reviewer
A read-only security review agent that checks code for common web risks, exposed secrets, unsafe input handling, authentication and authorization problems, and dependency issues. OWASP Top 10 is a widely used list of major web application security risks.
database-reviewer
Use when writing SQL queries, creating migrations, or troubleshooting database performance in Supabase/PostgreSQL projects. Reviews indexes, RLS policies, schema types, N+1 patterns. Read-only reviewer with EXPLAIN ANALYZE capability.
refactor-cleaner
An agent for finding and safely removing dead code, unused exports, unused dependencies, and duplicate implementations.
cavecrew-reviewer
Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.