A command that installs PolicyEngine-themed loading messages into Claude Code settings. PolicyEngine models tax and benefit policies, while spinner messages are the words shown while the assistant is working.

Use it to add or replace the spinnerVerbs setting in ~/.claude/settings.json with PolicyEngine-related phrases.

It adds project-specific status text while preserving the other settings and checks before replacing an existing spinner configuration.

setup-verbs — Command by PolicyEngine

Install

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.

agentmods

npx agentmods add commands/policyengine/policyengine-claude/setup-verbs

Clone the repo

git clone --depth 1 https://github.com/PolicyEngine/policyengine-claude

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 447 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00011	$0.00447
Opus 5	$0.00005	$0.00224
Sonnet 5	$0.00002	$0.00089
Haiku 4.5	$0.00001	$0.00045

Measured 2d ago against content hash ea5b824171d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

setup-verbs scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Install PolicyEngine-themed spinner verbs (the loading messages that appear while Claude is thinking) into the user's `~/.claude/settings.json`.

commands/setup-verbs.md · 59 lines

What it actually says

Install PolicyEngine spinner verbs

Install PolicyEngine-themed spinner verbs (the loading messages that appear while Claude is thinking) into the user's ~/.claude/settings.json.

Steps

Read the user's current ~/.claude/settings.json
Check if spinnerVerbs is already configured
If already configured, show the user what's there and ask if they want to replace it
If not configured (or user confirms replacement), merge the following spinnerVerbs block into their settings JSON, preserving all other existing settings:

"spinnerVerbs": {
  "mode": "replace",
  "verbs": [
    "Microsimulating",
    "Means-testing",
    "Phasing out benefits",
    "Calculating MTRs",
    "Clawing back subsidies",
    "Navigating the subsidy cliff",
    "Modeling counterfactuals",
    "Imputing income",
    "Reweighting the CPS",
    "Parsing the CFR",
    "Adjudicating eligibility",
    "Benchmarking silver plans",
    "Risk-adjusting",
    "Sunsetting provisions",
    "Scoring the bill",
    "Applying the benefit reduction rate",
    "Overfitting",
    "Simulating takeup",
    "Inflation adjusting",
    "Ignoring behavioral responses",
    "Querying HMRC",
    "Means-testing the telly licence",
    "Freezing the thresholds",
    "Preserving the triple lock",
    "Scoring the autumn budget",
    "Estimating impacts",
    "Building the baseline",
    "Reforming the tax code",
    "Calculating taxes",
    "Simulating policy",
    "Crunching the numbers"
  ]
}

Write the updated JSON back to ~/.claude/settings.json with proper formatting (2-space indent)
Tell the user the verbs are installed and they'll see them next time Claude is thinking

IMPORTANT: Preserve all existing settings (permissions, hooks, enabledPlugins, etc.). Only add or replace the spinnerVerbs key.

Changes

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 · 59 lines · 11 tokens per session scan B ea5b824171d4

Subscribe to this mod's changes

setup-verbs is a command published in the GitHub repository PolicyEngine/policyengine-claude (31 stars, last pushed 7d ago), licensed MIT. It adds 11 tokens to every session and 447 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

setup-verbs

Getting it into your agent

What it costs to keep this loaded

Grade B, and why

Reads agent configuration directoriesmediumAgent snooping

What it actually says

Install PolicyEngine spinner verbs

Steps

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement