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 thesongzhu/Friday --skill cross-border-customer-service-briefgit clone --depth 1 https://github.com/thesongzhu/FridayWrote 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/thesongzhu/friday/cross-border-customer-service-brief)<a href="https://agentmods.dev/skills/thesongzhu/friday/cross-border-customer-service-brief"><img src="https://agentmods.dev/badge/skills/thesongzhu/friday/cross-border-customer-service-brief/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/thesongzhu/friday/cross-border-customer-service-brief"><img src="https://agentmods.dev/badge/skills/thesongzhu/friday/cross-border-customer-service-brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.00238 |
| Opus 5.5 | $0.00000 | $0.00095 |
| Sonnet 5.5 | $0.00000 | $0.00048 |
| Haiku 4.5 | $0.00000 | $0.00024 |
Grade A, and why
cross-border-customer-service-brief 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 1mo 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.
What it actually says
Cross-border Customer Service Brief
Cluster refund, return, complaint, and bad-review notes into a daily support brief with response guidance and escalation hints.
When to use
- The cross-border
daily-customer-service-sweepworkflow is enabled. - The user pastes daily support/refund/return/bad-review notes and wants a focused triage brief.
Inputs
serviceNotes(string, required): one observation per line. Mixed Chinese/English notes are supported.
Outputs
serviceBrief: a multi-line cluster summary suitable for the support brief.summary: one-line headline.nextStep: recommended next operator action; defaults to escalation guidance when escalation language appears.details: structured cluster + escalation data for UI rendering.
Behavior
- Deterministic keyword bucketing across refund pressure, return pressure, delivery complaints, product quality, bad reviews, and policy disputes.
- Surfaces explicit escalation triggers when notes mention platform appeal, chargeback, or fraud language.
- No external network calls, no filesystem writes, no provider dependency.
- Returns a soft empty bundle when notes are missing instead of inventing findings.
What ships with it
3 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.
- 1mo ago First seen · 27 lines · 0 tokens per session scan A 60e10d53e526
cross-border-customer-service-brief is a skill published in the GitHub repository thesongzhu/Friday (836 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 238 tokens. 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 2026-08-30.
Other skills, from other repositories
ecommerce-product-research
Help a merchant decide what to test or source next. Start from their market, customer, budget, capabilities and decision horizon, rather than a platform's bestseller list.
ecommerce-creative
Turn verified product facts into executable creative briefs. For shared message selection and revision, read @skill/ecommerce-listing/references/source-based-writing.md through the available ecommerce-listing Skill. Then resolve the placement, source assets, format and requested action for the creative route.
ecommerce-operations
This Skill contains no bundled live connector. It works with supplied records across channels and conditionally with tools already available in the session. It neither adds recurring automation nor expands permissions, spend, targets or promotion budgets.
ecommerce-analytics
For platform exports read channel mapping. This package provides analytical methods; it does not install a platform API, infer account access or execute store changes.
ecommerce-listing
Use source-based writing to select messages, draft and review the complete copy before handoff, including inherited drafts. This shared method covers introductions, FAQs, scripts, translation and edits; use it with the brief's subject, sources, audience and voice.
ecommerce-review-analysis
Supplied CSV, spreadsheet, JSON or document exports require no external data provider. Public reputation samples are supplementary, not complete seller analytics. This Skill ships no review scraper. Do not treat rating, text sentiment, verified purchase or fraud suspicion as interchangeable facts.