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-apinpx skills add PolicyEngine/policyengine-claude --skill policyengine-apigit 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 | $0.00168 | $0.01400 |
| Opus 5 | $0.00084 | $0.00700 |
| Sonnet 5 | $0.00034 | $0.00280 |
| Haiku 4.5 | $0.00017 | $0.00140 |
Grade A, and why
policyengine-api 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PolicyEngine APIs
Two APIs coexist: v1 (PolicyEngine/policyengine-api, Flask) is production today, and
v2 (PolicyEngine/policyengine-api-v2, FastAPI microservices) is in alpha.
Pick the right client first. If you are computing policy impacts from Python, use the
policyengine package (pe.us.calculate_household, Simulation, economic_impact_analysis)
— see the policyengine skill. It pins a certified model + data bundle and is reproducible.
Reach for REST only for apps and external integrations (JS frontends, third parties) that
need HTTP.
v1 API — production (https://api.policyengine.org)
Flask (policyengine_api, Python 3.10/3.11). Country id (us, uk, ca, …) is the first
path segment. Verified route surface (policyengine_api/routes/, api.py):
| Route | Method | Purpose |
|---|---|---|
/{country}/metadata |
GET | variables, parameters, entities |
/{country}/calculate |
POST | stateless household calc (household JSON in, values out) |
/{country}/calculate-full |
POST | stateless full household calc |
/{country}/household |
POST | create a stored household |
/{country}/household/{id} |
GET/PUT | fetch/update a stored household |
/{country}/household/{id}/policy/{policyId} |
GET | household calc under a stored policy |
/{country}/policy · /{country}/policy/{id} |
POST · GET | store / fetch a reform policy |
/{country}/economy/{policyId}/over/{baselinePolicyId} |
GET | society-wide reform impact |
/{country}/simulation, /{country}/report |
POST/GET/PATCH | stored simulations / report output |
/specification |
GET | OpenAPI spec (also /liveness-check, /readiness-check) |
The economy endpoint is asynchronous — poll it. The same GET is re-issued until the job finishes; the response is a status envelope, not the result on the first call:
{ "status": "computing" | "ok" | "error",
"queue_position": 3, "average_time": 42.0,
"result": { /* deciles, poverty, budget… once status == "ok" */ },
"policyengine_bundle": { "model_version": "…", "data_version": "…" } }
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 · 101 lines · 168 tokens per session scan A 0d7fe51c3ecc
policyengine-api is a skill published in the GitHub repository PolicyEngine/policyengine-claude (31 stars, last pushed 7d ago), licensed MIT. It adds 168 tokens to every session and 1,400 once invoked, about $0.0008 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…