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 ActiveInferenceInstitute/GEO-INFER --skill geo-infer-insurancegit clone --depth 1 https://github.com/ActiveInferenceInstitute/GEO-INFERWrote 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/activeinferenceinstitute/geo-infer/geo-infer-insurance)<a href="https://agentmods.dev/skills/activeinferenceinstitute/geo-infer/geo-infer-insurance"><img src="https://agentmods.dev/badge/skills/activeinferenceinstitute/geo-infer/geo-infer-insurance/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/activeinferenceinstitute/geo-infer/geo-infer-insurance"><img src="https://agentmods.dev/badge/skills/activeinferenceinstitute/geo-infer/geo-infer-insurance.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 | $0.00050 | $0.00832 |
| Opus 5 | $0.00025 | $0.00416 |
| Sonnet 5 | $0.00010 | $0.00166 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
geo-infer-insurance 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 today.
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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
48 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.
- AGENTS.md 1.3 KB
- outputs/risk_engine.log 20 KB
- pyproject.toml 2.1 KB
- README.md 903 B
- requirements.txt 372 B
- setup.py 146 B runs code
- src/geo_infer_insurance/__init__.py 2.4 KB runs code
- src/geo_infer_insurance/underwriting/__init__.py 7.5 KB runs code
- src/geo_infer_insurance/underwriting/AGENTS.md 1.2 KB
- src/geo_infer_insurance/underwriting/core/__init__.py 76 B runs code
- src/geo_infer_insurance/underwriting/core/AGENTS.md 1.4 KB
- src/geo_infer_insurance/underwriting/core/claims_processing.py 36 KB runs code
- src/geo_infer_insurance/underwriting/core/policy_management.py 31 KB runs code
- src/geo_infer_insurance/underwriting/core/portfolio_management.py 7.4 KB runs code
- src/geo_infer_insurance/underwriting/core/pricing_engine.py 27 KB runs code
- src/geo_infer_insurance/underwriting/core/README.md 1.8 KB
- src/geo_infer_insurance/underwriting/core/risk_assessment.py 28 KB runs code
- src/geo_infer_insurance/underwriting/core/underwriting_decisions.py 17 KB runs code
- src/geo_infer_insurance/underwriting/core/underwriting_engine.py 26 KB runs code
- src/geo_infer_insurance/underwriting/core/underwriting_rules.py 29 KB runs code
- src/geo_infer_insurance/underwriting/models/__init__.py 933 B runs code
- src/geo_infer_insurance/underwriting/models/AGENTS.md 1.3 KB
- src/geo_infer_insurance/underwriting/models/claim_models.py 12 KB runs code
- src/geo_infer_insurance/underwriting/models/policy_models.py 12 KB runs code
- src/geo_infer_insurance/underwriting/models/README.md 1.6 KB
- src/geo_infer_insurance/underwriting/models/risk_models.py 7.4 KB runs code
- src/geo_infer_insurance/underwriting/models/underwriting_models.py 11 KB runs code
- src/geo_infer_insurance/underwriting/README.md 1.2 KB
- src/geo_infer_insurance/underwriting/utils/__init__.py 83 B runs code
- src/geo_infer_insurance/underwriting/utils/AGENTS.md 1.3 KB
- src/geo_infer_insurance/underwriting/utils/compliance.py 22 KB runs code
- src/geo_infer_insurance/underwriting/utils/data_integration.py 20 KB runs code
- src/geo_infer_insurance/underwriting/utils/README.md 1.8 KB
- src/geo_infer_insurance/underwriting/utils/reporting.py 27 KB runs code
- src/geo_infer_insurance/underwriting/utils/validation.py 21 KB runs code
- tests/conftest.py 60 B runs code
- tests/integration/test_integration.py 4.2 KB runs code
- tests/README.md 1.7 KB
- tests/unit/test_compliance_engine.py 8.6 KB runs code
- tests/unit/test_identifier_generation.py 1.3 KB runs code
- tests/unit/test_models.py 10 KB runs code
- tests/unit/test_package_safety.py 1.9 KB runs code
- tests/unit/test_policy_lifecycle.py 8.7 KB runs code
- tests/unit/test_portfolio_management.py 2.2 KB runs code
- tests/unit/test_pricing_and_claims.py 4.2 KB runs code
- tests/unit/test_silent_fabrication_fixes.py 5.3 KB runs code
- tests/unit/test_underwriting_decisions.py 8.9 KB runs code
- tests/unit/test_underwriting_rules.py 14 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.
- today Changed 22fdbdc10620
- 5d ago First seen · 100 lines · 50 tokens per session scan A 8650054ff703
geo-infer-insurance is a skill published in the GitHub repository ActiveInferenceInstitute/GEO-INFER (15 stars, last pushed today), with no licence file. It adds 50 tokens to every session and 832 once invoked, about $0.0003 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 2026-09-07.
Other skills, from other repositories
wealth-structure
A framework for thinking about wealth through ownership, responsibility, leverage, and avoiding risks that could end your progress.
finance-review
A review guide for financial calculations in a trading-assistant codebase. It requires decimal.js, a library for decimal arithmetic, instead of ordinary JavaScript number operations for money and prices.
tdx-quant-docs
A reference guide for TdxQuant, a Python framework built around the Tongda Xin financial terminal for collecting Chinese market and financial data. It helps users find the relevant documentation for its tqcenter APIs and trading strategies.
plaid
Plaid banking API expert for financial data integration. Covers Plaid Link, Auth (account/routing numbers), Transactions, Identity verification, Balance checking, and webhooks. Build fintech apps with bank connections, ACH transfers, and transaction history. Triggers on Plaid, banking API, Plaid Link, bank connection…
capability-circle
A framework for deciding which companies and industries an investor understands well enough to judge their future cash flow.
concentrated-investing
An investing framework about putting a larger share of money into a small number of companies you understand well. It distinguishes concentrated investing from broad diversification used for general wealth management.