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.
git clone --depth 1 https://github.com/msbaek/msbaek-claude-pluginsWrote 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/plugins/msbaek/msbaek-claude-plugins/msbaek-tdd)<a href="https://agentmods.dev/plugins/msbaek/msbaek-claude-plugins/msbaek-tdd"><img src="https://agentmods.dev/badge/plugins/msbaek/msbaek-claude-plugins/msbaek-tdd/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/plugins/msbaek/msbaek-claude-plugins/msbaek-tdd"><img src="https://agentmods.dev/badge/plugins/msbaek/msbaek-claude-plugins/msbaek-tdd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
msbaek-tdd 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 26d 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.
What it actually says
{
"name": "msbaek-tdd",
"version": "1.50.0",
"license": "MIT",
"description": "Java + Spring Boot TDD workflow plugin with requirements input drafting, RGB cycle, feature-level autonomous implementation, Cucumber acceptance testing, local tidying, system-wide refactoring, and 18 optional refactoring skills. Plan phase and Web App acceptance/skeleton setup now delegate to dedicated agents instead of running in the main context. Zero-token observability layer logs agent invocations (duration, success) via PostToolUse hooks.",
"author": {
"name": "msbaek"
},
"keywords": ["tdd", "java", "spring-boot", "red-green-blue", "feature-driven", "autonomous", "reviewable-commits", "tidying", "refactoring", "split-phase", "value-object", "naming", "null-object", "stream-pipeline", "assertion", "functional-core", "cucumber", "gherkin", "acceptance-test", "protocol-driver"]
}
What it installs
The manifest is a name and a version. 28 skills, 10 agents, 2 hooks travel with it, and installing the plugin installs all of them — 4,234 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill tdd-feature A 281 tokens
- Skill cucumber-acceptance A 109 tokens
- Skill intent-revealing-names A 190 tokens
- Skill tdd-plan-input A 109 tokens
- Skill segregate-functional-core A 124 tokens
- Skill system-wide-refactoring A 121 tokens
- Skill extract-method-object A 105 tokens
- Skill introduce-parameter-object A 111 tokens
- Skill naming-process A 118 tokens
- Skill discover-value-object A 124 tokens
- Skill encapsulate-collection A 110 tokens
- Skill first-class-collection A 113 tokens
- Skill replace-conditional-with-poly A 111 tokens
- Skill separate-query-modifier A 111 tokens
- Skill tdd A 130 tokens
- Skill decompose-conditional A 122 tokens
- Skill explicit-parameters A 132 tokens
- Skill introduce-assertion A 102 tokens
- Skill introduce-special-case A 103 tokens
- Skill lift-up-conditional A 114 tokens
- Skill replace-loop-with-pipeline A 107 tokens
- Skill tdd-legacy A 67 tokens
- Skill consolidate-conditional A 144 tokens
- Skill replace-temp-with-query A 98 tokens
- Skill tdd-tidy A 114 tokens
- Skill tdd-profile A 116 tokens
- Skill tdd-rgb A 156 tokens
- Skill tdd-plan A 168 tokens
- Agent tdd-red A 48 tokens
- Agent tdd-blue A 66 tokens
- Agent tdd-green A 46 tokens
- Agent tdd-plan-critic A 89 tokens
- Agent tdd-skeleton-builder A 76 tokens
- Agent tdd-acceptance-builder A 70 tokens
- Agent tdd-domain-modeler A 87 tokens
- Agent tdd-example-designer A 89 tokens
- Agent tdd-test-list A 71 tokens
- Agent tdd-anchor-drafter A 82 tokens
- Hook PostToolUse A not measured
- Hook PreToolUse A not measured
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.
- 26d ago Changed c4891080693d
- 27d ago Changed 6d2a6bfa85f6
- 1mo ago Changed · +1 lines f0a9c04d8fde
- 1mo ago Changed 28a6e6bdc804
- 1mo ago Changed 35596aa025a4
- 1mo ago Changed 2686f906512c
- 1mo ago First seen · 10 lines scan A a490284f6836
msbaek-tdd is a plugin published in the GitHub repository msbaek/msbaek-claude-plugins (8 stars, last pushed 5d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.
Other plugins, from other repositories
python-development
Python development toolkit: pytest techniques with canonical testing authoring, code refactoring with complexity metrics, performance profiling, async patterns, uv package management, dead code detection, comment auditing, project scaffolding, deep Pydantic v2.13 guide…
superpowers-laravel
Laravel-focused skills for Claude Code: TDD (Pest/PHPUnit), migrations, queues, quality checks (Pint/Insights), and pragmatic architecture patterns — Sail and non-Sail compatible.
tdd-laravel
Laravel-specific quality tools for TDD workflow. Pest Laravel Plugin, HTTP tests, Eloquent patterns.
tdd-python
Python quality tools for TDD workflow. pytest, mypy, Black/isort integration.
python
Python code quality: ruff linting (ZERO noqa), type checking (ZERO type:ignore), clean code (SOLID), TDD with pytest.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.