agent-tdd
v0.2.7Design Spec orchestrator + strict Red-Green-Refactor TDD for Claude Code. Accepts full requirements/design/research from agent-isdd, validates research, slices into TDD-sized phases with Ralph Loops, then executes Red-Green-Refactor with optional test-author split for high-risk. Token-efficient (30-60% savings via caching and early escalation).
By Renford NelsonLicense: SEE LICENSE IN LICENSE0 GitHub starsUpdated 3 days ago
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 3 skill or MCP entries
- Source updated
- Sep 20, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install agent-tdd for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install agent-tdd@agent-plugin-marketplacePaste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/renfordn/claude-pluginsClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is agent-tdd/.
Plugin files
├── .claude-plugin/plugin.json├── SKILL.md├── skills/design-spec-direct/SKILL.md└── skills/slice-spec/SKILL.md
Included Skills3
Implement features via research validation, task slicing, and strict Red-Green-Refactor per slice. Orchestrates per-slice reviews at appropriate levels (Quick/Standard/Deep) and post-slices coherence review (Deep/Ultra based on high-risk composition).
Harness-bug fallback for Design Spec Mode. Reproduces agent-TDD's Research Validation, Task Slicing, Ralph Loops, Risk Tier assignment, and per-slice Red-Green-Refactor contract as a Skill invocation (no Agent tool) instead of an Agent-tool subagent spawn. Use only when agent-isdd/INTEROP.md's "Fallback — Direct Implementation" Detection conditions are confirmed for the current session — this is a fallback, not a preferred path.
Assemble a Slice Spec for agent-TDD (and, for high-risk slices, test-author) from the task at hand, and emit it as a correctly formatted spawn prompt block. Use this before spawning either agent, or whenever a caller needs to check that a Slice Spec is complete and valid against the contract in INTEROP.md and references/slice-spec.schema.json.
Plugin manifests1
{
"name": "agent-tdd",
"version": "0.2.7",
"description": "Design Spec orchestrator + strict Red-Green-Refactor TDD for Claude Code. Accepts full requirements/design/research from agent-isdd, validates research, slices into TDD-sized phases with Ralph Loops, then executes Red-Green-Refactor with optional test-author split for high-risk. Token-efficient (30-60% savings via caching and early escalation).",
"author": {
"name": "Renford Nelson"
},
"homepage": "https://github.com/renfordn/agent-tdd",
"license": "SEE LICENSE IN LICENSE",
"keywords": [
"tdd",
"red-green-refactor",
"testing",
"agent",
"claude-code"
]
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[agent-tdd on Agent Plugins Marketplace](https://pluginsmp.com/plugins/agent-tdd)