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-research-lookupgit 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-research-lookup)<a href="https://agentmods.dev/skills/policyengine/policyengine-claude/policyengine-research-lookup"><img src="https://agentmods.dev/badge/skills/policyengine/policyengine-claude/policyengine-research-lookup.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00088 | $0.00932 |
| Opus 5 | $0.00044 | $0.00466 |
| Sonnet 5 | $0.00018 | $0.00186 |
| Haiku 4.5 | $0.00009 | $0.00093 |
Grade A, and why
policyengine-research-lookup 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 8d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PolicyEngine research lookup
Find existing PolicyEngine articles to cite as evidence or to model tone against. PolicyEngine has published ~185 articles — US and UK policy analyses, model/methodology notes, and org announcements. Paths below are verified against the policyengine-app-v2 mirror.
Where posts live
In policyengine-app-v2:
- Article bodies (plain markdown, some Jupyter
.ipynb):app/src/data/posts/articles/<filename> - Post index (title, description, date, tags, authors, image):
app/src/data/posts/posts.json - Author records (slug → name/bio):
app/src/data/posts/authors.json
Article files are plain markdown — metadata is not in per-file YAML frontmatter. Each post's
title, date, tags, and authors live in posts.json, keyed to the article's filename; the
authors field holds slugs that resolve in authors.json. A posts.json entry:
{
"title": "How we used Claude Code to apply for the Public Benefit Innovation Fund",
"description": "Treating writing as software development...",
"date": "2025-08-28",
"tags": ["us", "org", "ai", "featured"],
"authors": ["max-ghenis"],
"filename": "policyengine-atlas-pbif-grant.md",
"image": "policyengine-atlas-demo.png"
}
A post's public URL is policyengine.org/<country>/research/<filename-without-extension>.
Lookup recipes
POSTS=~/PolicyEngine/policyengine-app-v2/app/src/data/posts
# Full-text search article bodies for a topic
grep -rli "child tax credit" "$POSTS/articles/" | head
# Search titles/descriptions in the index
python3 -c 'import json;[print(p["date"],p["filename"]) for p in json.load(open("'"$POSTS"'/posts.json")) if "eitc" in (p["title"]+p.get("description","")).lower()]'
# Filter by tag (e.g. everything tagged "featured" or "uk")
python3 -c 'import json;[print(p["date"],p["title"]) for p in json.load(open("'"$POSTS"'/posts.json")) if "featured" in p.get("tags",[])]'
# Most recent posts
python3 -c 'import json;[print(p["date"],p["title"]) for p in sorted(json.load(open("'"$POSTS"'/posts.json")),key=lambda p:p["date"],reverse=True)[:10]]'
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.
- 8d ago First seen · 82 lines · 88 tokens per session scan A 6c88910b4d58
policyengine-research-lookup is a skill published in the GitHub repository PolicyEngine/policyengine-claude (32 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 932 once invoked, about $0.0004 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…