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-datagit 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-data)<a href="https://agentmods.dev/skills/policyengine/policyengine-claude/policyengine-data"><img src="https://agentmods.dev/badge/skills/policyengine/policyengine-claude/policyengine-data/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-data"><img src="https://agentmods.dev/badge/skills/policyengine/policyengine-claude/policyengine-data.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 107 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00263 | $0.06179 |
| Opus 5.5 | $0.00105 | $0.02472 |
| Sonnet 5.5 | $0.00053 | $0.01236 |
| Haiku 4.5 | $0.00026 | $0.00618 |
Grade A, and why
policyengine-data 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 today.
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 — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PolicyEngine data
How the microdata behind PolicyEngine population runs is built, calibrated, versioned, and
named. For using datasets in a simulation, see the policyengine skill (this skill is about
where the data comes from). For diagnosing why one score disagrees with a benchmark, see
policyengine-calibration-diagnostics.
The current data stack is Microcosm (repo PolicyEngine/microcosm, local mirror
~/PolicyEngine/microcosm; read its README.md + DESIGN.md). It replaced the technique-named
packages of the previous stack (microimpute / microcalibrate / L0 / policyengine-us-data), which
shared no datatype and had their worst bugs at the seams between flat DataFrames. Build new
imputation on microcosm-fit and new calibration on microcosm-calibrate, never on microimpute,
microcalibrate or L0. microdf stays: policyengine-core depends on it.
The Microcosm architecture
Microcosm is one kernel datatype — the Frame — with packages as operators on it. It is a
PEP 420 namespace (microcosm.*) shipped as independently-installable shard distributions, so an
analyst doing imputation never has to install torch and vice versa. Microcosm releases pin the
shards as a constellation.
| Package | Import | Role | Succeeds |
|---|---|---|---|
microcosm-frame |
microcosm.frame |
the kernel: Frame, typed weights, strata, links, weighted accounting, unit structure, the RulesEngine protocol |
microunit, and microdf inside Microcosm |
microcosm-fit |
microcosm.fit |
conditional models (weight-aware by construction) | microimpute, ad hoc imputation scripts |
microcosm-calibrate |
microcosm.calibrate |
targets → calibrated weights (Adam; opt-in L0 pruning, or L1 via prox) |
microcalibrate, L0 (l0-python) |
microcosm-build |
microcosm.build |
build plans, donor graphs, release gates, country build stages | one-off build drivers |
microcosm-data |
microcosm.data |
published population registry + lazy engine loaders | country-specific data packages |
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.
- today Changed · +21 lines · +9 tokens per session b69652c4e6e8
- 2d ago Changed · +89 lines · +1 tokens per session 8fcbb5c6bc6c
- 2mo ago First seen · 223 lines · 253 tokens per session scan A cda6ca658cac
policyengine-data is a skill published in the GitHub repository PolicyEngine/policyengine-claude (31 stars, last pushed yesterday), licensed MIT. It adds 263 tokens to every session and 6,179 once invoked, about $0.0011 per session on Opus 5.5. 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.
policyengine-data compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| policyengine-dataPolicyEngine/policyengine-claude | Skill | 31 | yesterday | MIT | A | 263 | Claude Code |
| torchdrugK-Dense-AI/scientific-agent-skills | Skill | 57k | today | MIT | A | 64 | Claude Code |
| arboretoK-Dense-AI/scientific-agent-skills | Skill | 57k | today | MIT | A | 55 | Claude Code, Codex |
| deepspot-mK-Dense-AI/scientific-agent-skills | Skill | 57k | today | MIT | A | 70 | Claude Code |
| pyhealthK-Dense-AI/scientific-agent-skills | Skill | 57k | today | MIT | A | 84 | Claude Code, Codex |
| nemo-mbridge-perf-expert-parallel-overlapNVIDIA/skills | Skill | 3.9k | today | Apache-2.0 | A | 56 | Claude Code |
| ml-training-recipesOrchestra-Research/AI-Research-SKILLs | Skill | 14k | 29d ago | MIT | A | 88 | Claude Code |