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-canadanpx skills add PolicyEngine/policyengine-claude --skill policyengine-canadagit 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-canada)<a href="https://agentmods.dev/skills/policyengine/policyengine-claude/policyengine-canada"><img src="https://agentmods.dev/badge/skills/policyengine/policyengine-claude/policyengine-canada.svg" alt="Measured on agentmods" 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 | $0.00214 | $0.01747 |
| Opus 5 | $0.00107 | $0.00873 |
| Sonnet 5 | $0.00043 | $0.00349 |
| Haiku 4.5 | $0.00021 | $0.00175 |
Grade A, and why
policyengine-canada 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 4d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PolicyEngine Canada domain knowledge
Canada is the exception to the standard PolicyEngine stack. Read this before writing any Canadian analysis — the entry points and the limits are different from the US/UK.
Verified against policyengine-canada 0.99.0 (2026-07), installed standalone. Do not hardcode
benefit amounts; look them up live (below), because provincial and federal parameters re-index
every year.
Two hard constraints
1. pe.ca does not exist. The policyengine wrapper ships US and UK only; there is no pe.ca.
Use the policyengine_canada package directly.
import policyengine as pe
assert not hasattr(pe, "ca") # Canada is not in the policyengine wrapper
2. Canada is household-only — there is no representative microdata. The package ships a small synthetic template, not a survey-weighted population sample. So you cannot run population microsimulation, and you cannot produce national program costs, revenue estimates, caseloads, or poverty rates for Canada. If asked "what would this cost nationally" or "how many families benefit," say that population estimates are not available for Canada and offer a household example. What you can do: compute taxes/benefits for a specific family, compare baseline vs. reform for that family, sweep it across an income range, and compare provinces.
One household calculation
Install the package on its own (it is not in the shared analysis venv), then build a situation
and use policyengine_canada.Simulation. Values below verified against 0.99.0.
uv pip install policyengine-canada
from policyengine_canada import Simulation
sim = Simulation(situation={
"people": {
"parent1": {"age": {"2026": 35}, "employment_income": {"2026": 45_000}},
"parent2": {"age": {"2026": 33}, "employment_income": {"2026": 20_000}},
# full_custody defaults to False, which HALVES the CCB (see gotcha below):
"child1": {"age": {"2026": 4}, "full_custody": {"2026": True}},
"child2": {"age": {"2026": 9}, "full_custody": {"2026": True}},
},
"households": {"household": {
"members": ["parent1", "parent2", "child1", "child2"],
"province_code": {"2026": "ONT"}, # note: "ONT" for Ontario, "QC" for Quebec
}},
})
assert round(float(sim.calculate("child_benefit", 2026)[0]), 2) == 11_030.75 # federal CCB
assert float(sim.calculate("adjusted_family_net_income", 2026)[0]) == 65_000 # AFNI
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.
- 4d ago First seen · 128 lines · 214 tokens per session scan A 1cfce3ec9345
policyengine-canada is a skill published in the GitHub repository PolicyEngine/policyengine-claude (32 stars, last pushed yesterday), licensed MIT. It adds 214 tokens to every session and 1,747 once invoked, about $0.0011 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
convex-add
Add a capability to the CURRENT Convex app — consults the served Convex capability catalog for always-current procedures (billing, crons, auth, agent, search, …); falls back to built-in hosting or @convex-dev component search. TRIGGER when the user runs /add, or asks to add hosting/publishing or any backend capability…
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
multi-expert-analyzer
针对通用问题进行多领域专家联合分析, 综合稿产生前必经 fact-checker 与 red-team 两道独立校验。适用场景: 用户提出跨领域或不确定领域的复杂问题, 需要从多个专家角度分别搜证并相互校验后综合成文, 例如该不该买房、该不该跳槽、是否进入某个赛道等。触发关键词: 多角度分析、专家分析、综合分析、多视角、跨领域分析、从不同角度看、深度分析。问题只属于单一明确领域时, 优先使用该领域的专门 skill, 例如纯财务用 finance-core-analysis、纯技术用 software-architect。输出 (全部 markdown 保存到当前项目 markdown/ 目录): (1) 每位专家的中间分析稿…