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.
npx skills add semperi/restaurant-marketing-skills --skill google-review-replygit clone --depth 1 https://github.com/semperi/restaurant-marketing-skillsWrote 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/skills/semperi/restaurant-marketing-skills/google-review-reply)<a href="https://agentmods.dev/skills/semperi/restaurant-marketing-skills/google-review-reply"><img src="https://agentmods.dev/badge/skills/semperi/restaurant-marketing-skills/google-review-reply/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/skills/semperi/restaurant-marketing-skills/google-review-reply"><img src="https://agentmods.dev/badge/skills/semperi/restaurant-marketing-skills/google-review-reply.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 | $0.00079 | $0.02179 |
| Opus 5 | $0.00039 | $0.01090 |
| Sonnet 5 | $0.00016 | $0.00436 |
| Haiku 4.5 | $0.00008 | $0.00218 |
Grade A, and why
google-review-reply 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Review Reply
You get a reply you can paste into Google — two to four sentences, in the restaurant's voice, that names the actual thing the guest said. No corporate filler, no promises the owner did not make, and nothing that breaks Google's review rules and risks the listing.
What to paste
| What | Where to find it | If you don't have it |
|---|---|---|
| The review text | Google Business Profile → Reviews, or the email Google sent | Nothing to reply to — paste the review first |
| The star rating | Shown beside the review | Infer nothing; write for the words, not the stars |
| The reviewer's first name | Shown above the review | Write the reply without a name; never invent one |
| The restaurant name | You know it | Ask the owner once, then reuse it |
| How the restaurant talks | The restaurant-voice.md file if one exists, or the owner's own words |
Use plain, warm, unfussy English and say you did |
| A contact route for follow-up | An email or phone the owner is happy to publish | Leave the invitation out — never invent a channel |
Everything in that table is the whole truth available to you — see Never do this below.
Quick start
Owner: "2 star review came in, burger was cold and the wait was 40 minutes"
→ Read the review. Name the two specific complaints: cold food, 40-minute wait.
→ Draft 2-4 sentences: acknowledge both by name, apologise for the experience,
invite direct contact only if the owner gave a contact route.
→ Show the exact text. No remedy offered — flag that it may want one.
→ Owner approves → owner pastes it into Google. You do not post it.
Workflow
Step 1 — Read the review properly
Separate what the guest stated from what they felt. "The burger was cold" is a stated fact about their visit. "Worst place in town" is a feeling. You acknowledge both, but you only ever repeat the stated specifics.
Then classify it, because the shape of the reply changes:
- Positive — thank them, name what they named, invite them back. If they told other people to come, thank them for that specifically. A guest recommending the restaurant to strangers is the most valuable thing in the review and the easiest one to walk straight past.
- Negative with specifics — name each complaint, apologise for the reported experience, invite contact if a route exists.
- Mixed — acknowledge both sides. Never quietly drop the criticism because the review was mostly kind, and never drop the praise because it was mostly harsh. If the guest listed several suggestions, acknowledge each one — without promising to act on any.
- Vague or extreme, no detail — answer calmly, do not echo the language, invite contact.
- Wrong restaurant — if the guest describes food or a cuisine this restaurant does not serve, say plainly what it does serve and suggest they may have the wrong place. Add no other claim.
- Public refund demand — reply to the experience. Keep the refund out of it entirely; that is the owner's decision to make privately.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 169 lines · 79 tokens per session scan A 7992819c134d
google-review-reply is a skill published in the GitHub repository semperi/restaurant-marketing-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 2,179 once invoked, about $0.0004 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 skills, from other repositories
restaurant-local-seo
Local SEO audit — "best [cuisine] near me" targeting, Google Business Profile optimization, NAP consistency, citation building, restaurant schema markup.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
google-ads-audit
Google Ads account audit and business context setup. Use for account-health audits and business-context setup. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should I fix in my ads", or when the user is new to NotFair and hasn't run…
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.