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-agentgit 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-agent)<a href="https://agentmods.dev/skills/openmf/mcp-mifosx/mifos-agent"><img src="https://agentmods.dev/badge/skills/openmf/mcp-mifosx/mifos-agent/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-agent"><img src="https://agentmods.dev/badge/skills/openmf/mcp-mifosx/mifos-agent.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 | $0.00103 | $0.01748 |
| Opus 5.5 | $0.00041 | $0.00699 |
| Sonnet 5.5 | $0.00021 | $0.00350 |
| Haiku 4.5 | $0.00010 | $0.00175 |
Grade A, and why
fineract-agent-skill 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 6d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apache Fineract Agent Skill
Provides 55+ tools across 9 domains for full-lifecycle banking operations against an Apache Fineract instance.
Prerequisites
- Verify the environment file exists at
agent-skill/mifos-agent/.env. If missing, copyagent-skill/mifos-agent/.env.exampleand populate the credentials. Seereferences/environment-config.mdfor variable descriptions. - Verify the Python package is installed:
pip install -e agent-skill/mifos-agent/.[dev]. If import errors occur, re-run this command.
Step 1: Initialize the Client
- Import and instantiate the Fineract client:
from fineract_skill import FineractClient client = FineractClient() - Verify connectivity by calling
client.ping(). If the result contains"status": "error", inspect the error message and check the.envconfiguration.
Step 2: Discover Available Tools
- Import the tool registry:
from fineract_skill import list_tools, get_tool - To list all tools:
list_tools(). To filter by domain:list_tools(domain="loans"). - Supported domains:
clients,loans,savings,groups,accounting,staff,products,charges,reports. - For the full tool catalog with parameter schemas, read
references/tool-catalog.md.
Step 3: Execute a Tool
- Look up the tool by name:
tool = get_tool("search_clients"). - Call the handler, passing the
clientas the first argument followed by the required parameters:result = tool.handler(client, name_query="John") - All tools return a standardised envelope:
- Success:
{"ok": True, "data": {...}} - Failure:
{"ok": False, "error": "..."}
- Success:
- If
result["ok"]isFalse, read theerrorfield. Common causes: invalid IDs, missing required fields, or authentication failures.
Step 4: Export Schemas for Agent Frameworks
- For OpenAI function-calling format:
from fineract_skill.tools import get_openai_tools schemas = get_openai_tools() - For MCP-compatible format:
from fineract_skill.tools import get_mcp_tools schemas = get_mcp_tools() - For the static JSON schema template, read
assets/tool-schema-template.json.
What ships with it
22 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.
- .env.example 965 B
- assets/tool-schema-template.json 996 B
- fineract_skill/__init__.py 635 B runs code
- fineract_skill/client.py 7.6 KB runs code
- fineract_skill/domains/__init__.py 75 B runs code
- fineract_skill/domains/accounting.py 2.6 KB runs code
- fineract_skill/domains/charges.py 3.5 KB runs code
- fineract_skill/domains/clients.py 11 KB runs code
- fineract_skill/domains/groups.py 4.7 KB runs code
- fineract_skill/domains/loans.py 15 KB runs code
- fineract_skill/domains/products.py 1.6 KB runs code
- fineract_skill/domains/reports.py 3.7 KB runs code
- fineract_skill/domains/savings.py 7.9 KB runs code
- fineract_skill/domains/staff.py 1.9 KB runs code
- fineract_skill/helpers.py 1.6 KB runs code
- fineract_skill/tools.py 32 KB runs code
- pyproject.toml 928 B
- README.md 16 KB
- references/checklist.md 2.2 KB
- references/environment-config.md 1.3 KB
- references/tool-catalog.md 8.4 KB
- scripts/validate-skill.py 8.5 KB runs code
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.
- 6d ago First seen · 116 lines · 103 tokens per session scan A 930236876bcd
fineract-agent-skill is a skill published in the GitHub repository openMF/mcp-mifosx (26 stars, last pushed today), licensed MPL-2.0. It adds 103 tokens to every session and 1,748 once invoked, about $0.0004 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 2026-10-10.
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).
kandev-approvals
Clear the CEO approval queue when hire requests, budget grants, or other sensitive Office mutations are waiting for approve or reject decisions.
kandev-team-admin
Manage the Office roster when delegating work, hiring agents, changing budgets or concurrency, retiring agents, or checking spend before approvals.
api-design
Design REST API contracts that are consistent, evolvable, and easy to consume.
banco-inter-api
Use esta skill para implementar, revisar, depurar, testar, migrar ou explicar integrações com a plataforma de desenvolvedores do Banco Inter Empresas, incluindo OAuth 2.0 + mTLS, Banking, Pix, Pix Automático, Cobrança Boleto com Pix V3, Webhooks, Sandbox, SDKs, CNAB, Crédito Empresas e Crédito Imobiliário.