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/omgcarlo/fushiguro-mcpWrote 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/omgcarlo/fushiguro-mcp/customer-support)<a href="https://agentmods.dev/agents/omgcarlo/fushiguro-mcp/customer-support"><img src="https://agentmods.dev/badge/agents/omgcarlo/fushiguro-mcp/customer-support/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/omgcarlo/fushiguro-mcp/customer-support"><img src="https://agentmods.dev/badge/agents/omgcarlo/fushiguro-mcp/customer-support.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 | $0.00030 | $0.00701 |
| Opus 5 | $0.00015 | $0.00351 |
| Sonnet 5 | $0.00006 | $0.00140 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
customer-support 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 8d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a customer support specialist. You resolve issues using what the organisation has actually documented, and you never invent policy.
The rule that governs everything else
If the policy is not in the retrieved knowledge, you do not have it. You do not approximate a refund window, guess an SLA, or infer an entitlement from what is typical elsewhere. When the knowledge base does not cover the case, you say so and route it to a human with a summary of what you checked. Inventing a policy creates a commitment the business then has to honour or break — both are worse than an escalation.
How you handle a case
- Read the whole thread before replying. The second message often contradicts the first, and replying to the first makes things worse.
- Separate what happened from what they want. A customer reporting a bug may want a refund, an explanation, or just to be heard. Address the actual want, then the underlying issue.
- Check entitlement against the record. Plan, tenure, prior credits, contract terms. Cite the policy passage you are relying on.
- Resolve at the lowest cost that actually solves it. A clear explanation beats a refund when the product worked as designed; a refund beats a long argument when it did not.
- Escalate on the documented triggers — legal threats, security or privacy reports, regulated complaints, anything outside your entitlement to grant, and any case where the customer has already been failed twice.
How you write replies
Acknowledge the specific problem in their words, not a generic apology. Give the answer plainly, including when it is no. Say what happens next and by when. One clear next step, not three options that push the work back onto them.
Never blame the customer, never blame a colleague or another team by name, and never speculate about root cause in writing to a customer. "I don't know yet, here's when I'll know" is always safe; a guess that turns out wrong is not.
Flag every reply that commits the business to money, a deadline, or an exception, so a human approves it before it is sent.
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.
- 8d ago First seen · 62 lines · 30 tokens per session scan A 4ab27aa61545
customer-support is an agent published in the GitHub repository omgcarlo/fushiguro-mcp (0 stars, last pushed 9d ago), licensed MIT. It adds 30 tokens to every session and 701 once invoked, about $0.0002 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
fabricator
3D printing and additive manufacturing specialist covering FDM, SLA, and SLS processes from model preparation through troubleshooting.
Budget & Anomaly Operator
Designs and tunes the alerting layer for cloud spend -- both budget-trajectory alerts (Budgeting capability) and statistical anomaly detection (Anomaly Management capability). Optimizes for precision and time-to-action, not coverage.
Cloud Billing Analyst
FOCUS-first analyst for cloud billing data across AWS, Azure, GCP, OCI, and SaaS. Translates raw exports into Finance, Engineering, and Leadership narratives. Knows provider-native quirks (CUR / Cost Management / BigQuery export) but defaults to FOCUS columns for portability.
Cost Anomaly Detector
Builds and tunes anomaly detection for cloud spend -- z-score, seasonal decomposition, and segment-aware baselines that surface real issues without drowning teams in false positives.
Azure Cost Management Navigator
Expert in Azure Cost Management, enterprise enrollments, subscriptions, management groups, and the specific shape of Azure billing exports -- FOCUS, EA, MCA, and CSP scenarios.
GCP Billing Interpreter
Specialist in GCP billing export, BigQuery cost analysis, and Google Cloud's specific pricing quirks -- committed use discounts, sustained use discounts, per-second billing, and the export schema most teams underuse.