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-appnpx skills add PolicyEngine/policyengine-claude --skill policyengine-appgit 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 | $0.00174 | $0.01993 |
| Opus 5 | $0.00087 | $0.00996 |
| Sonnet 5 | $0.00035 | $0.00399 |
| Haiku 4.5 | $0.00017 | $0.00199 |
Grade C, and why
policyengine-app scanned grade C with 2 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- When `bun install` fails, try at most 2 fixes, then ask. Never `rm -rf node_modules`, Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **`curl` is NOT verification.** An SPA (and a streamed Next page) returns a 200 HTML shell How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PolicyEngine app v2
PolicyEngine/policyengine-app-v2 is the frontend served at policyengine.org. It is
mid-migration: a Next.js 15 App Router host lives in website/ and is the live apex,
while a legacy Vite SPA in app/ still owns the calculator surface and is being ported
page by page. Verify the current stack from package.json files before trusting any summary
— this repo moves fast.
Monorepo layout
Bun workspaces + Turbo (packageManager: [email protected], root turbo.json). Workspaces:
packages/*, app, website, calculator-app.
| Path | What | Bundler |
|---|---|---|
website/ |
@policyengine/website — Next.js 15 App Router host (live apex, marketing/research/tools) |
Next 15 + Turbopack |
app/ |
policyengine-app-v2 — legacy Vite SPA (calculator: policies, households, reports, simulations) |
Vite 6 |
calculator-app/ |
standalone calculator workspace | Vite |
packages/ |
shared workspace packages | — |
Root scripts run through Turbo: bun run build → turbo run build; bun run dev runs the
Next host (scripts/dev-server-next.mjs); bun run dev:legacy runs the Vite app.
Tech stack (verified from package.json)
There is no third-party component framework — UI is built from radix-ui primitives plus local components. Do not add one.
website/:next^15.3.3,radix-ui^1.4.3,@tabler/icons-react,tailwindcssv4 (@tailwindcss/postcss),class-variance-authority,react19,react-plotly.js(maps),framer-motion,fuse.js,react-markdown.app/:vite6,react-router-dom7,@tanstack/react-query,@reduxjs/toolkit+react-redux,recharts^3.7.0,@tabler/icons-react,tailwindcssv4 (@tailwindcss/vite), Storybook.- Both pin
@policyengine/ui-kit^0.4.0. See the policyengine-design skill for its API.
useDisclosure / useMediaQuery / useViewportSize in app/src/hooks/ are local
reimplementations — not a dependency.
App Router page pattern (website/)
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 · 140 lines · 174 tokens per session scan C efcd2fc6d374
policyengine-app is a skill published in the GitHub repository PolicyEngine/policyengine-claude (31 stars, last pushed 8d ago), licensed MIT. It adds 174 tokens to every session and 1,993 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…