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 agentmods add skills/policyengine/policyengine-claude/policyengine-usnpx skills add PolicyEngine/policyengine-claude --skill policyengine-usgit clone --depth 1 https://github.com/PolicyEngine/policyengine-claudeWhat 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 | $0.00251 | $0.03753 |
| Opus 5 | $0.00125 | $0.01877 |
| Sonnet 5 | $0.00050 | $0.00751 |
| Haiku 4.5 | $0.00025 | $0.00375 |
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 First seen · 286 lines · 251 tokens per session scan A e98269603f49
policyengine-us is a skill published in the GitHub repository PolicyEngine/policyengine-claude (31 stars, last pushed 8d ago), licensed MIT. It adds 251 tokens to every session and 3,753 once invoked, about $0.0013 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 2026-08-30.
Other skills, from other repositories
monte-carlo
Use when the user wants Monte Carlo simulation of a PlanExe model — sampling from bounds to produce output distributions (mean/std/percentiles), threshold pass probabilities, and Pearson-correlation sensitivity rankings — given an extract-parameters-from-full JSON, a generate-bounds JSON, a generate-calculations…
fin-paper-figure
Generate academic-quality figures (>=300 DPI) for economics and finance papers.
de-portfolio-opt
差分进化（DE）组合优化。用户说「DE组合优化」「差分进化权重」「/de-portfolio-opt」时使用。长仅权重最大化样本夏普；纯 Python。默认 createweb。.
hht-timing
改进 HHT 择时（相位代理）。用户说「HHT」「希尔伯特」「EMD择时」「/hht-timing」时使用。无 EMD 库时用包络/相位近似并 meta.degraded。默认 createweb。.
quant-experiment-runtime
Quant research experiment executor: discover an offline source database under the workdir's code-repo, build a panel, run a Research Artifact's entry point to compute research-object values, and evaluate IC/ICIR/RANKIC/coverage metrics. Runtime = Experiment Executor; it runs a Research Artifact via a Python-native…
fin-paper-writing
经济金融论文写作编排器。根据PAPEROUTLINE.md和REFINEDDESIGN.md，编排调用fin-paper-draft（正文写作）、fin-paper-figure（图表生成）、fin-review-loop（review循环），管理版本并确保章节间的一致性。.