Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/PolicyEngine/policyengine-claudenpx agentmods add skills/policyengine/policyengine-claude/policyengine-prior-scoresWrote 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-prior-scores)<a href="https://agentmods.dev/skills/policyengine/policyengine-claude/policyengine-prior-scores"><img src="https://agentmods.dev/badge/skills/policyengine/policyengine-claude/policyengine-prior-scores/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/policyengine/policyengine-claude/policyengine-prior-scores"><img src="https://agentmods.dev/badge/skills/policyengine/policyengine-claude/policyengine-prior-scores.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00217 | $0.02367 |
| Opus 5 | $0.00109 | $0.01184 |
| Sonnet 5 | $0.00043 | $0.00473 |
| Haiku 4.5 | $0.00022 | $0.00237 |
Grade A, and why
policyengine-prior-scores 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PolicyEngine prior scores
Finding a prior score to anchor a new analysis has two parts: a curated anchor list of
notable PE reforms (below, with URLs) and the real infrastructure in this repo that
enumerates presets, external scorekeepers, and local archived runs. Earlier versions of this
skill described a data/prior-scores.json file with get_priors_by_program() query functions —
those never existed. The sections below point only at things that are actually on disk or live.
When to use
/analyze-policyStage 3 (find prior scores) and Stage 5 (compare the microsim to them).- The
/prior-scorescommand (external-benchmark research without running the microsim). - The
prior-scores-finderagent's Tier-1 lookup. - Writing a research post and citing PE's prior work on a similar reform.
Real infrastructure in this repo
Presets — named reform-dicts with published scores
presets/reforms/*.yaml and presets/baselines/*.yaml are callable-by-name reform/baseline
dicts. A preset may carry a published_scores block recording what external sources scored that
exact shape — which is what makes external corroboration turn-key.
python3 scripts/presets.py list # all presets
python3 scripts/presets.py list --category reform --country us
python3 scripts/presets.py show arpa-ctc-restoration # prints the reform_dict + published_scores
from scripts.presets import load_preset
preset = load_preset("arpa-ctc-restoration")
preset["reform_dict"] # ready to pass as a reform
preset["published_scores"] # [{source: JCT, ten_year_billion: 1100, ...}, ...]
Presets on disk today (verify with python3 scripts/presets.py list — load_preset raises
on names that don't exist): reforms arpa-ctc-restoration, obbba-salt-bump; baseline
tcja-extension. A pre-obbba baseline is wanted but not yet authored. Add a preset by copying
a nearby file and, if any external source scored the shape, filling in published_scores — see
presets/README.md.
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 · 173 lines · 217 tokens per session scan A 26d0a3606f1b
policyengine-prior-scores is a skill published in the GitHub repository PolicyEngine/policyengine-claude (32 stars, last pushed 2d ago), licensed MIT. It adds 217 tokens to every session and 2,367 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
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-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…
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…