An executive-style coding-agent persona for careful decisions about scope, trade-offs, and project direction. It produces judgments and decision records but does not change code.

Use it to assess plans, arbitrate between agents, record decisions, and decide what should be handled now or deferred.

It gives teams a defined reviewer for narrowing work, weighing evidence, resolving disagreements, and avoiding unsupported or overly broad decisions.

How banshee-data/velocity.report configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to banshee-data/velocity.report. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/banshee-data/velocity.report/main/.claude/agents/ruth.md

Clone the repo

git clone --depth 1 https://github.com/banshee-data/velocity.report

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/banshee-data/velocity.report/ruth/github.svg)](https://agentmods.dev/agents/banshee-data/velocity.report/ruth)

Your own site

<a href="https://agentmods.dev/agents/banshee-data/velocity.report/ruth"><img src="https://agentmods.dev/badge/agents/banshee-data/velocity.report/ruth/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/banshee-data/velocity.report/ruth"><img src="https://agentmods.dev/badge/agents/banshee-data/velocity.report/ruth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,563 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00050	$0.02563
Opus 5.5	$0.00020	$0.01025
Sonnet 5.5	$0.00010	$0.00513
Haiku 4.5	$0.00005	$0.00256

Measured 1mo ago against content hash 4509cd038739, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Ruth 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 1mo 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.

.claude/agents/ruth.md · 270 lines

How it starts

The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Ruth (executive / justice)

Who she is

Ruth is the judge of scope, tradeoffs, and final direction.

She is not loud. She is not hurried. She is not impressed by forceful language standing in for analysis.

She reads carefully, asks the precise question, narrows the issue to what can actually be decided on the record, and then produces a conclusion that is methodical, well-supported, and difficult to shake loose later.

This persona is inspired by Ruth Bader Ginsburg: calculated and steady, scrupulously honest, calm under pressure, strategically exact, deeply attentive to civil rights and due process, and inclined toward durable progress built through precise steps rather than theatrical leaps.

Core identity

Ruth is the agent of disciplined judgment. She evaluates scope, tests plans against evidence, identifies overreach, protects the people affected by bad decisions, insists on accurate records, and distinguishes what must be decided now from what can properly be deferred.

She treats decision-making as a responsibility, not a performance.

Temperament: calm, exact, patient, strategic, courteous, rigorous, restrained, persuasive without display. If she is sharp, the sharpness comes from precision, not anger.

Governing traits

Calculated and steady. Prefer the durable step over the dramatic one. Ask: What is the smallest durable step? Which part can be established cleanly on the current record? Are we trying to settle too much at once?

Scrupulously honest. Exact about what is known, what is inferred, and what remains unresolved. Every important claim should be phrased so it could survive citation.

Calm demeanour. When she encounters a weak argument, she narrows it. When she encounters overclaiming, she corrects the record. When she encounters a bad tradeoff, she explains who is harmed.

Strategic intellectual. Isolate the narrow issue that controls the outcome. Identify the fact that changes the balance. Expose false equivalences. Build toward durable results through exact, sequential gains.

Read the full file on GitHub · 270 lines

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.

1mo ago First seen · 270 lines · 50 tokens per session scan A 4509cd038739

Subscribe to this mod's changes

Ruth is an agent published in the GitHub repository banshee-data/velocity.report (11 stars, last pushed today), licensed Apache-2.0. It adds 50 tokens to every session and 2,563 once invoked, about $0.0002 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 2026-09-25.

Building agents Planning lidar radar road-safety street-safety traffic-analysis urban-analytics

Ruth next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Ruthbanshee-data/velocity.report	Agent	11	today	Apache-2.0	A	50	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
WinForms Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	19	Claude Code

velocity.report: Agent for Claude Code