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-cloud-costsgit 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-cloud-costs)<a href="https://agentmods.dev/skills/policyengine/policyengine-claude/policyengine-cloud-costs"><img src="https://agentmods.dev/badge/skills/policyengine/policyengine-claude/policyengine-cloud-costs/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-cloud-costs"><img src="https://agentmods.dev/badge/skills/policyengine/policyengine-claude/policyengine-cloud-costs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00246 | $0.05209 |
| Opus 5.5 | $0.00098 | $0.02084 |
| Sonnet 5.5 | $0.00049 | $0.01042 |
| Haiku 4.5 | $0.00025 | $0.00521 |
Grade C, and why
policyengine-cloud-costs 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/PolicyEngine/policyengine-skills/main/skills/policyengine-cloud-costs/scripts/check_deploy_config.py | python3 - . Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/PolicyEngine/policyengine-skills/main/skills/policyengine-cloud-costs/scripts/check_deploy_config.py | python3 - . How it starts
The opening of the file, as written. The whole thing — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud costs for your own tool
For anyone building a standalone tool (a dashboard backend, a calculator API, a data job) and deploying it themselves. The defaults below cost nothing while nobody uses the tool. Each rule comes from a PolicyEngine bill; the incidents are listed at the end.
The defaults are not bans. Warm containers for a launch, a minimum instance for an endpoint that must answer quickly, or 20 GiB workers for a national run are all fine when you declare them where they are set (section 2). A declaration is how the reviewer, the checker and the next maintainer know the setting is deliberate and what it costs.
Load this when:
- scaffolding a tool with a backend (the dashboard-builder agents and
/new-toollink here); - a PR changes deploy scripts, Modal decorators,
cloudbuild.yamlor GitHub workflows; - before the first deploy, before a launch or busy period, and when a tool is replaced or retired.
1. Write the cost plan before the first deploy
Copy templates/running-costs.md into the tool's README and answer five questions:
- What runs while nobody uses it? The default answer is "nothing".
- What is the most it can cost in an hour? Maximum containers or instances × the
hourly rate (prices at the end). Where Modal CPU or memory is a
(request, limit)pair, price the limit: Modal bills the higher of request and use, and a container can use up to its limit. - What makes extra copies, and what ends each one? Traffic tags, versions, PR preview apps, test and drill deploys.
- Where do the secrets live? A secret store, never the repo.
- Who owns it, and when is it reviewed or retired?
2. Defaults, and how to declare something else
| Setting | Default | Rule to declare |
|---|---|---|
Modal min_containers, buffer_containers, keep_warm |
0 or unset | MO1 |
Cloud Run --min, --min-instances |
0 | CR3 |
Modal max_containers |
Set, from the expected peak | MO2 (to leave it unset) |
Cloud Run --max |
Set, from the observed peak | CR2 (to leave it unset) |
| CPU and memory | From a measured run; 4 or more cores, or 16 GiB or more, needs a reason | RS1 |
| A revision-level minimum together with a traffic tag per deploy | Never | CR1 |
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 353 lines · 246 tokens per session scan C 5a92713fe5c9
policyengine-cloud-costs is a skill published in the GitHub repository PolicyEngine/policyengine-claude (31 stars, last pushed yesterday), licensed MIT. It adds 246 tokens to every session and 5,209 once invoked, about $0.0010 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-07.
policyengine-cloud-costs compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| policyengine-cloud-costsPolicyEngine/policyengine-claude | Skill | 31 | yesterday | MIT | C | 246 | Claude Code |
| gke-compute-classesgoogle/skills | Skill | 24k | today | Apache-2.0 | A | 83 | Claude Code, Codex |
| gke-workload-securitygoogle/skills | Skill | 24k | today | Apache-2.0 | A | 171 | Claude Code, Codex |
| gke-reliabilitygoogle/skills | Skill | 24k | today | Apache-2.0 | A | 85 | Claude Code, Codex |
| cloud-architectJeffallan/claude-skills | Skill | 12k | 10d ago | MIT | A | 71 | Claude Code |
| nemo-automodel-launcher-configNVIDIA/skills | Skill | 3.9k | today | Apache-2.0 | A | 30 | Claude Code |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | today | MIT | A | 78 | Claude Code |