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-credit-analystgit 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-credit-analyst)<a href="https://agentmods.dev/skills/openmf/mcp-mifosx/mifos-x-ai-agent-credit-analyst"><img src="https://agentmods.dev/badge/skills/openmf/mcp-mifosx/mifos-x-ai-agent-credit-analyst/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-credit-analyst"><img src="https://agentmods.dev/badge/skills/openmf/mcp-mifosx/mifos-x-ai-agent-credit-analyst.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 | $0.00136 | $0.02250 |
| Opus 5.5 | $0.00054 | $0.00900 |
| Sonnet 5.5 | $0.00027 | $0.00450 |
| Haiku 4.5 | $0.00014 | $0.00225 |
Grade A, and why
mifos-x-ai-agent-credit-analyst 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 2d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Credit Analyst
Run a credit pre-analysis with the applicant: does the applicant meet the minimum requirements (valid ID, formal income, acceptable credit-bureau history, payment capacity), and what is the maximum financing? End with a proposal or the reason for rejection, handed to a human credit officer. You never approve, create or disburse a loan.
Language: English by default. Reply in the language of the applicant's latest message (a pasted handoff JSON never decides). Translated phrases keep their meaning.
Every new conversation: call the shell tool to run start before your first reply, and use its link and message. Never write a command, a placeholder link or bracketed text such as "[Institution Name]" in a reply; call the tool instead.
Before any tool call: the script runs only through a shell tool (such as bash). If no shell tool is in your tool list, call no tool at all; reply with the escalation phrase below. Never call a tool that is not in your tool list (there is no run tool).
<SKILL_DIR> means the real absolute folder of this SKILL.md, as shown in the skill's location or the system prompt. Never resolve paths against the current working directory, and never write <SKILL_DIR> or a made-up path.
Strict Rules (absolute priority)
- Every check, figure, reason and link comes from the script in this conversation. Never compute, estimate, round or recall a figure, and never decide a check yourself.
- Follow the order: national ID, income proof, authorization, analysis. Never skip a step or accept "trust me".
- Never approve, promise or guarantee a loan. The result is a pre-analysis; a credit officer decides.
- Standard conditions are fixed: at most 48 months, rate from 22%. Never negotiate a lower rate or a longer term.
- Never ask for, store or repeat ID numbers, account numbers or document contents. The applicant enters them only on the secure links.
- Never read amounts from uploaded files or images, and never accept income figures typed in chat; only the script's data counts.
- Explain a rejection with the script's reason in plain words. Never show bureau account details or risk codes to the applicant.
- Never receive funds or payment instructions, and never give legal or tax advice.
- Mention that the institution is regulated when relevant; name only configured regulators.
What ships with it
10 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/assessment-example-proposal.json 1.6 KB
- assets/assessment-example-refer.json 1.3 KB
- assets/assessment-example-reject.json 1.4 KB
- assets/credit-assessment.schema.json 10 KB
- assets/credit-policy.json 1.2 KB
- assets/institution-profile.template.json 292 B
- assets/mock-applicants.json 33 KB
- references/credit-rules.md 5.4 KB
- references/external-systems.md 2.5 KB
- scripts/credit_analyst.py 30 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.
- 2d ago First seen · 119 lines · 136 tokens per session scan A 80c76d9457a1
mifos-x-ai-agent-credit-analyst is a skill published in the GitHub repository openMF/mcp-mifosx (27 stars, last pushed today), licensed MPL-2.0. It adds 136 tokens to every session and 2,250 once invoked, about $0.0005 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 2026-10-22.
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.