By kelp
Language-agnostic TDD pipeline with test-first agents, review loops, and verify gates.
Standard briefing for coding agents. Covers file rules, shell rules, quality bar, and directive to read CLAUDE.md for project-specific context.
Use when reviewing implementation code written by the implementer agent. Checks correctness, resource management, code quality, and dependencies.
Use when dispatching an agent to write implementation code for a module. Tests already exist. Agent writes ONLY the source file to make tests pass.
Add TDD pipeline configuration template to this project's CLAUDE.md. Run this to set up the pipeline for a new project.
Enforce strict red-green-refactor TDD for any task. Use when implementing features, fixing bugs, adding functionality, or building new modules. Routes to the full 7-agent pipeline for new modules with 3+ behaviors, or runs inline red-green-refactor for bug fixes and small changes. Triggers on: "use TDD", "fix this bug", "add a feature", "implement", "run the pipeline", "TDD pipeline", "build a module with TDD", or any coding task in a project with TDD in its CLAUDE.md.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Two plugins that make Claude Code write correct code: one enforces TDD, the other fixes Zig 0.15.x.
/plugin marketplace add kelp/kelp-claude-plugins
Claude generates broken Zig 0.15.x code for 12 specific patterns. This plugin corrects them by appending the right patterns to your project's CLAUDE.md so every agent reads them.
/plugin install zig-claude-kit@kelp-claude-plugins
Open a Zig project. The plugin detects Zig source files
and prompts you to run /zig-init. From that point,
Claude writes correct Zig.
Commands:
/zig-init -- inject corrections into CLAUDE.md/zig-patterns -- quick reference with code examples/zig-check -- audit files for outdated API usageClaude skips tests, writes stubs, and reviews its own work. This plugin stops that. It splits every module into seven stages across separate agents -- no single agent both writes and reviews code.
/plugin install tdd-pipeline@kelp-claude-plugins
Run /tdd-init to configure your project, then
/tdd-orchestrate parser to build a module.
The pipeline:
1. Test Writer write tests + type stubs (RED)
2. Test Reviewer review tests, fix loop
3. Red Gate confirm all tests fail against stubs
4. Implementer write code to pass tests (GREEN)
5. Verify Gate tests pass, no stubs, lint clean
6. Code Reviewer review implementation, fix loop
7. Integrate update build files, full tests, commit
The orchestrator -- your main Claude session -- dispatches agents and never writes code. Each agent receives a role skill that constrains what it can touch. Language-specific context comes from CLAUDE.md, not the plugin -- so the pipeline works with any language.
CLAUDE.md connects these plugins:
zig-claude-kit appends language correctionstdd-pipeline reads test commands and file patternsPublic domain.
npx claudepluginhub kelp/kelp-claude-plugins --plugin tdd-pipelineCorrective context for Zig 0.15.x that fixes Claude's outdated training data. Covers I/O (Writergate), build.zig, format strings, ArrayList, BoundedArray, usingnamespace, division, tokenize, args, JSON, and for-loop index.
Test-driven development methodology with red-green-refactor cycles and code review
Strict red-green-refactor TDD loop. Failing test, then minimum code, then refactor. Commits after each cycle.
Test-driven development workflow for writing tests before implementation - red-green-refactor cycle with deterministic unit tests
Automated Test-Driven Development enforcement
Test-driven development skill that enforces red-green-refactor, one test at a time
Battle-tested skills, agents, and commands for Claude Code — TDD workflows, systematic debugging, code review, and parallel task execution.