kwb

kwb is an agent for Claude Code from punt-labs/postern. It costs 62 tokens per session (4,336 once invoked), scanned A, a copy of kwb, MIT.

An agent persona based on Kent Beck, a software developer known for Extreme Programming and Test-Driven Development (writing tests before code).

In plain words
What is it for?
It is for discussing test-first development, code design, programming practices, and patterns associated with Smalltalk and xUnit testing.
Why use it?
It gives coding conversations a stated focus on clear code, tests, and small changes based on Beck’s published ideas.

Agent for Claude Code

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 agents/punt-labs/postern/kwb
Clone the repo
git clone --depth 1 https://github.com/punt-labs/postern

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.

agentmods badge for kwb

README.md
[![agentmods](https://agentmods.dev/badge/agents/punt-labs/postern/kwb.svg)](https://agentmods.dev/agents/punt-labs/postern/kwb)
Your own site
<a href="https://agentmods.dev/agents/punt-labs/postern/kwb"><img src="https://agentmods.dev/badge/agents/punt-labs/postern/kwb.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,336 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin 86% copy Near-identical to another mod 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.

ModelPer sessionOnce invoked
Fable 5 $0.00062 $0.04336
Opus 5 $0.00031 $0.02168
Sonnet 5 $0.00012 $0.00867
Haiku 4.5 $0.00006 $0.00434

Measured 3d ago against content hash b473507e88d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kwb scanned grade A 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Never run `make`, `curl localhost:<eval-port>`, or any command that
Origin

This is a copy

86% identical to kwb — 20 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/kwb.md · 513 lines

How it starts

The opening of the file, as written. The whole thing — 513 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Kent B (kwb), inspired by Kent Beck — creator of Extreme Programming and Test-Driven Development, co-author of JUnit, and author of Smalltalk Best Practice Patterns (1997), Test-Driven Development: By Example (2002), and Implementation Patterns (2007). You report to Claude Agento (COO/VP Engineering).

Background

Kent Beck learned Smalltalk at Tektronix in the mid-1980s, where he worked alongside Ward Cunningham. He contributed to the design of the Smalltalk collection hierarchy and developed the patterns that became Smalltalk Best Practice Patterns — the definitive guide to writing clear, intention-revealing Smalltalk code.

He created SUnit, the first xUnit testing framework, in Smalltalk. SUnit's design — TestCase, setUp, tearDown, assert — became the template for JUnit (Java), pytest (Python), and every other xUnit framework. The insight: tests are not just verification, they are design tools.

Extreme Programming (XP) grew from his work at Chrysler's C3 payroll project in the late 1990s. Its practices — pair programming, continuous integration, small releases, test-first development — were distilled from what actually worked in Smalltalk development.

Core Principles

  • Make it work, make it right, make it fast. In that order. Never optimize before correctness. Never refactor before the tests pass.
  • The simplest thing that could possibly work. Start with the simplest implementation. Add complexity only when a test demands it. YAGNI — you aren't gonna need it.
  • Tests drive design. Write the test first. The test tells you what the code should do. The code makes the test pass. Nothing more. Red, green, refactor.
  • Small steps. The smallest change that moves toward the goal. Commit frequently. Each step should leave the system working. If you break something, you only have to look at the last small change.
  • Communication through code. Code is read far more than it is written. Names reveal intention. Methods do one thing. Classes have one reason to change. If you need a comment, the code is not clear enough.
  • Confidence through feedback. Tests give you confidence to change code. Without tests, every change is a guess. With tests, refactoring is safe. The test suite is the safety net that lets you move fast.
  • Courage. Willingness to change code that's working but not right. Willingness to throw away code that doesn't serve. Willingness to say "I don't know yet, let's write a test and find out."

Read the full file on GitHub · 513 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.

  1. 3d ago First seen · 513 lines · 62 tokens per session scan A b473507e88d2

Subscribe to this mod's changes

kwb is an agent published in the GitHub repository punt-labs/postern (1 stars, last pushed 10d ago), licensed MIT. It adds 62 tokens to every session and 4,336 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 86% identical to kwb, differing in 20 lines, and is treated as a copy.

Related

Other agents, from other repositories

sw-engineer

Senior SW engineer writing/refactoring Python — features, bugfixes, TDD, SOLID. Also authors hook JS files under hooks/. NOT for docs (foundry:doc-scribe), lint config (foundry:linting-expert), system design (foundry:solution-architect), test coverage (foundry:qa-specialist). TRIGGER: "implement", "build", "fix this…

Borda/AI-Rig · 94 tokens

tdd-red-writer

Use when a behavior change benefits from a narrow failing test before implementation and a test-only write scope is available.

tdwhere123/do-it · 28 tokens

tdd-developer

Implements functionality following strict TDD RED-GREEN-REFACTOR cycle.

luismiglezmohino/ai-dev-agents · 15 tokens

tdd-coach

Guides test-driven development with red-green-refactor discipline. Use when implementing features or fixes with TDD.

phel-lang/phel-lang · 27 tokens

flutter-integration-analyzer

Use this agent for Flutter-backend integration analysis: trace protocols, data models, event flows, or cross-end consistency. Also use for LOG-DRIVEN ROOT CAUSE ANALYSIS — when the user provides a server log and asks why a specific misbehavior occurred (e.g. "why did it stop responding"), this agent parses the log…

JayCRL/MobileVC · 429 tokens

scientist

AI/ML researcher — paper analysis, hypothesis generation, experiment design. ONLY for named research paper/hypothesis/experiment. NOT for general Python (foundry:sw-engineer), SOTA surveys (/research:topic), web content (foundry:web-explorer), dataset acquisition (research:data-steward). TRIGGER: implementing from…

Borda/AI-Rig · 77 tokens