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 PolicyEngine/policyengine-claude --skill policyengine-usgit clone --depth 1 https://github.com/PolicyEngine/policyengine-claudeWrote 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/policyengine/policyengine-claude/policyengine-us)<a href="https://agentmods.dev/skills/policyengine/policyengine-claude/policyengine-us"><img src="https://agentmods.dev/badge/skills/policyengine/policyengine-claude/policyengine-us/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/policyengine/policyengine-claude/policyengine-us"><img src="https://agentmods.dev/badge/skills/policyengine/policyengine-claude/policyengine-us.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 87 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00251 | $0.03789 |
| Opus 5.5 | $0.00100 | $0.01516 |
| Sonnet 5.5 | $0.00050 | $0.00758 |
| Haiku 4.5 | $0.00025 | $0.00379 |
Grade A, and why
policyengine-us 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 — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PolicyEngine US domain knowledge
This skill is the US-specific layer for analysts using the policyengine package. It assumes
you already know the shared mechanics — pe.us.calculate_household, population Simulation,
reform dicts, datasets — from the policyengine skill; read that first for anything not
US-specific. For building new US variables or parameters, use policyengine-model-development.
For Medicaid / ACA / CHIP / Medicare, use policyengine-healthcare.
Verified against policyengine 4.21.0 / policyengine-us 1.764.6 (2026-07). Re-verify law-year values before reporting — the model updates continuously.
The six entities, and which program lives on which
US taxes and benefits are administered by different units, so the model has six entities. A program's variable is defined on exactly one of them, and reading it from the wrong entity is the most common US mistake.
| Entity | Plural key | What it groups |
|---|---|---|
person |
people |
individuals |
marital_unit |
marital_units |
a married couple (or a single person) |
family |
families |
a nuclear family (Census-style) |
tax_unit |
tax_units |
a tax-filing unit (a 1040) |
spm_unit |
spm_units |
a Supplemental Poverty Measure resource-sharing unit |
household |
households |
everyone at a physical address |
Which entity a program attaches to (verified — entity and definition period both matter):
| Program / measure | Variable | Entity | Period |
|---|---|---|---|
| Federal income tax | income_tax |
tax_unit | year |
| EITC | eitc |
tax_unit | year |
| Child Tax Credit | ctc |
tax_unit | year |
| State income tax (aggregate) | state_income_tax |
tax_unit | year |
| SNAP | snap |
spm_unit | month |
| TANF | tanf |
spm_unit | year |
| SSI | ssi |
person | month |
| Net income | household_net_income |
household | year |
| Total benefits | household_benefits |
household | year |
| Total taxes | household_tax |
household | year |
| In poverty (SPM) | in_poverty |
spm_unit | year |
| Person in poverty | person_in_poverty |
person | year |
| Is a child | is_child |
person | year |
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 Changed 57945e5ed60f
- 1mo ago First seen · 286 lines · 251 tokens per session scan A e98269603f49
policyengine-us is a skill published in the GitHub repository PolicyEngine/policyengine-claude (32 stars, last pushed 2d ago), licensed MIT. It adds 251 tokens to every session and 3,789 once invoked, about $0.0010 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 2026-08-30.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research through opencli: the user's home timeline, tweet search, trending topics, bookmarks, a user's recent tweets, threads, articles, profiles, followers and following, and notifications. Use this skill whenever the user wants to know what people are saying on Twitter/X or fintwit about…
energy-procurement
Codified expertise for electricity and gas procurement, tariff optimization, demand charge management, renewable PPA evaluation, and multi-facility energy cost management. Informed by energy procurement managers with 15+ years experience at large commercial and industrial consumers. Includes market structure analysis…
airdrop-hunting-guide
Guide to finding and qualifying for crypto airdrops — eligibility criteria, farming strategies, on-chain activity requirements, Sybil detection avoidance, and tracking tools. Use when helping users understand airdrops, check eligibility, or plan participation strategies.
china-portfolio-monitoring
A monitoring framework for tracking the financial results, operating measures, strategic milestones, and risks of companies held by China-focused private-equity funds. It uses measures such as revenue growth, margins, debt, cash flow, and return on equity.