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 DaizeDong/buy-me-a-car --skill inbox-triagegit clone --depth 1 https://github.com/DaizeDong/buy-me-a-carWrote 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/daizedong/buy-me-a-car/inbox-triage)<a href="https://agentmods.dev/skills/daizedong/buy-me-a-car/inbox-triage"><img src="https://agentmods.dev/badge/skills/daizedong/buy-me-a-car/inbox-triage/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/daizedong/buy-me-a-car/inbox-triage"><img src="https://agentmods.dev/badge/skills/daizedong/buy-me-a-car/inbox-triage.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 | $0.00115 | $0.02309 |
| Opus 5 | $0.00057 | $0.01154 |
| Sonnet 5 | $0.00023 | $0.00462 |
| Haiku 4.5 | $0.00012 | $0.00231 |
Grade A, and why
inbox-triage 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dealer Inbox Triage
Caveat: this skill is one author's playbook + 5-scenario stress test. Verify state fees / CPO terms / EV credits / dealer practices against current sources before quoting numbers to a dealer or making financial decisions. Not tax, legal, or financial advice.
Narrow-trigger skill: classify Gmail dealer mail into 4 actionable buckets and route each
to its next step. Defers drafting to ../dealer-reply-drafter/SKILL.md and cron setup
details to ../orchestrator/references/cron_monitoring.md.
When to invoke
User says any of: "check my dealer inbox", "triage these emails", "is this real or autoresponder", "看下邮箱", "dealer 回复了吗", "spam folder check", "what came in overnight", "did anyone reply".
The 4 buckets
Every dealer-domain email lands in exactly ONE bucket. Decide in order:
1. Real reply, buyer-specific human response
Signals: human prose, references buyer-supplied details (the buyer's name, the
specific VIN/stock number the buyer asked about, an OTD figure, an availability
confirmation, a counter-offer number). Sender is a named salesperson, not a generic
sales@, info@, or noreply@ alias.
Spanish / bilingual dealer mail: a reply written in Spanish or mixed Spanish+English is still a bucket-1 real reply, NOT spam, many US dealers staff bilingual reps and will answer in the buyer's apparent language or their own. Language is never a spam signal; judge by the bucket-1 content signals above (human prose, buyer-specific numbers, named sender). When handing off:
- Translate the substance for the buyer: surface the actionable content in English, meaning OTD/price figures, VIN/stock confirmation, availability, any counter-offer or condition the rep stated. Give the buyer the meaning, not a word-for-word gloss.
- Outbound counter stays in English: the draft handed to
../dealer-reply-drafter/SKILL.mdis composed in English regardless of the inbound language (per the buyer's drafting preference). Do not mirror Spanish in the reply unless the buyer explicitly asks.
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 · 192 lines · 115 tokens per session scan A 5d38f3734646
inbox-triage is a skill published in the GitHub repository DaizeDong/buy-me-a-car (5 stars, last pushed 8d ago), licensed MIT. It adds 115 tokens to every session and 2,309 once invoked, about $0.0006 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
service-desk
Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…
collaboration-platform-administration
Administers the email, chat, meeting and file-sharing platform the organization runs on — tenant and domain configuration, mail authentication and routing, phishing and spam controls, shared mailboxes and distribution groups, external sharing and guest access, permission sprawl in file storage, and retention and legal…
onboarding-and-offboarding
Designs the joining and leaving experience — first-day readiness, ramp to productivity, knowledge capture, and clean exits. Use this to design or fix onboarding, shorten time to productivity, structure a leaver process, capture knowledge before someone leaves, or coordinate the access and asset steps around a joiner…
glyph
Render an answer as ASCII art plus semantic emojis inline, right now, with no setup questions. Use for a fast visual take on status, comparisons, trade-offs, architecture, or any ad-hoc 'show me X visually' ask. For a full multi-artifact plan playground, use visualize-plan instead.
join-meeting
AgentCall (agentcall.dev) — Join a video meeting (Google Meet, Teams, Zoom) as an AI bot with voice and visual presence. Supports audio-only mode with voice intelligence (barge-in, interruptions), text-to-speech mode, and webpage modes for custom UI. Use when asked to join a call, attend a meeting, or participate in a…
day-close
A day-ending protocol that reviews and records the required closing steps for the workday in IWE.