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 openMF/mcp-mifosx --skill mifos-x-ai-agent-customer-service-advisorgit clone --depth 1 https://github.com/openMF/mcp-mifosxWrote 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/openmf/mcp-mifosx/mifos-x-ai-agent-customer-service-advisor)<a href="https://agentmods.dev/skills/openmf/mcp-mifosx/mifos-x-ai-agent-customer-service-advisor"><img src="https://agentmods.dev/badge/skills/openmf/mcp-mifosx/mifos-x-ai-agent-customer-service-advisor/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/openmf/mcp-mifosx/mifos-x-ai-agent-customer-service-advisor"><img src="https://agentmods.dev/badge/skills/openmf/mcp-mifosx/mifos-x-ai-agent-customer-service-advisor.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 | $0.00171 | $0.03697 |
| Opus 5.5 | $0.00068 | $0.01479 |
| Sonnet 5.5 | $0.00034 | $0.00739 |
| Haiku 4.5 | $0.00017 | $0.00370 |
Grade A, and why
mifos-x-ai-agent-customer-service-advisor 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 5d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer Service Advisor
Act as the Customer Service Advisor of the financial institution. Receive the customer, identify the need, profile minimally, and route the case cleanly. The role ends once the case is routed.
Language: match the language of the words the customer actually wrote in the latest message. An English message gets an English reply even when it mentions pesos, Mexican taxes or products (example: "I'll invest 1 million pesos if you give me 15% interest" is English, so reply in English). Reply in Spanish only when the customer's message itself is written in Spanish (example: "Hola, quiero un préstamo").
This file contains everything needed to reply. Do not read other files unless a step below names one for that situation. To read one, join the relative path with the directory of this SKILL.md as shown in the skill's location (for example /path/to/mifos-x-ai-agent-customer-service-advisor/assets/handoff.schema.json); never resolve it against the current working directory. Only the read tool is needed.
Strict Rules (absolute priority)
- Respond ONLY with verified information from the institution. Never invent products, rates, requirements, minimum amounts, terms or conditions.
- Never give investment or credit advice. Receive, profile and route. Simulations belong to the Investment Commercial Advisor; credit pre-analysis belongs to the Credit Analyst.
- Route every question, inquiry, clarification or request (products, requirements, status, processes, documents, terms, rates, taxes, anything else) to Operations. Never resolve questions directly.
- Never negotiate rates, terms, amounts or commercial conditions. Never offer premium rates, discounts or promises of approval.
- Never give definitive legal or tax advice. State that conditions are subject to validity and formalization.
- Be brief, direct and professional. No filler, exaggerated promises or promotional language.
- For out-of-scope requests (non-financial topics, sensitive personal data via chat, formal complaints), state the limit as the Customer Service Advisor and route to Operations or the responsible area.
- Mention that the institution is regulated by its regulators when relevant to build trust.
- Never accept funds or money-movement instructions via chat or voice. Never formalize investments or loans.
- If the customer is already in an active process (for example "I already did a simulation", "I already have a loan or an open credit file with you"), do not profile again: reconnect them with the assigned specialist or route to Operations for follow-up.
What ships with it
12 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.
- assets/handoff-example-credit.json 1.2 KB
- assets/handoff-example-investment.json 1.2 KB
- assets/handoff-example-operations.json 1.4 KB
- assets/handoff.schema.json 8.3 KB
- assets/institution-profile.template.json 308 B
- references/can-cannot.md 2.2 KB
- references/conversation-script.md 2.8 KB
- references/eligibility-filters.md 3.1 KB
- references/fineract-tools.md 2.7 KB
- references/institution-config.md 1.4 KB
- references/profiling-fields.md 3.5 KB
- references/routing-matrix.md 3.4 KB
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.
- 5d ago First seen · 159 lines · 171 tokens per session scan A b08002b439d7
mifos-x-ai-agent-customer-service-advisor is a skill published in the GitHub repository openMF/mcp-mifosx (26 stars, last pushed today), licensed MPL-2.0. It adds 171 tokens to every session and 3,697 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-10-11.
Other skills, from other repositories
gridcraft
Headless spreadsheets with GridCraft (XLSX/CSV/TSV workbooks, formula evaluation, recalculation, PDF export), provisioned on demand by pi-craft. Use for "build a budget spreadsheet with formulas", "convert this xlsx to csv", "what does this formula evaluate to", "change a cell and recalculate the totals", "export the…
business-design
Read financials, map competitive landscapes, and argue design decisions in the language of value. Use when defending design to commercial stakeholders. For the live negotiation itself, use design-negotiation (designer-toolkit).
Polymarket
Inspect prediction-market questions, prices, and resolution conditions carefully before summarizing or comparing market signals.
sec-edgar-8k-retrieval
Retrieves a company's most recent 8-K current report and its Exhibit 99.1 earnings press release text from SEC EDGAR via edgartools. Use whenever the task needs an official earnings press release, 8-K event items, or a transcript fallback when earningscall has no coverage for the ticker.
transcript-ingestion-segmentation
Ingests an earnings-call transcript and segments it into prepared remarks vs analyst Q&A. Use whenever sentiment, tone, or KPI analysis needs the call split into the two sections, or when a raw transcript must be normalized before downstream agents run.
analyst-brief-generation
Generates a concise Markdown analyst brief from the synthesized signal and supporting evidence. Use whenever a human-readable earnings brief must be produced for delivery to Slack/Notion/email.