A shared set of Claude Code skills for test-driven development (writing tests before code), debugging, test checks, and parallel work by helper agents.

Use it when building or changing software that needs test-first work, debugging support, automated checks, or parallel task handling.

It gives coding sessions repeatable ways to plan, test, debug, and divide work, reducing the need to manage each practice manually.

wrangler — Plugin by bacchus-labs

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.

Claude Code

/plugin marketplace add bacchus-labs/wrangler

agentmods

npx agentmods add plugins/bacchus-labs/wrangler/wrangler

Clone the repo

git clone --depth 1 https://github.com/bacchus-labs/wrangler

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 25 skills, 16 commands, 16 agents cost 2,129 tokens a session between them.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

wrangler 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 2d 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-plugin/plugin.json · 23 lines

What it actually says

{
  "name": "wrangler",
  "description": "Core skills library for Claude Code: TDD, debugging, testing gates, subagent parallelization, etc.",
  "version": "1.2.0",
  "author": {
    "name": "Sam",
    "email": ""
  },
  "homepage": "https://irregularexpressions.com",
  "repository": "https://github.com/samjhecht/wrangler",
  "mcpServers": {
    "wrangler-mcp": {
      "command": "node",
      "args": ["${CLAUDE_PLUGIN_ROOT}/mcp/dist/bundle.cjs"],
      "env": {
        "WRANGLER_MCP_DEBUG": "false",
        "WRANGLER_ISSUES_DIRECTORY": ".wrangler/issues",
        "WRANGLER_SPECIFICATIONS_DIRECTORY": ".wrangler/specifications"
      }
    }
  }
}

Contents

What it installs

The manifest is a name and a version. 25 skills, 16 commands, 16 agents travel with it, and installing the plugin installs all of them — 2,129 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

marketplace.json 337 B

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.

2d ago First seen · 23 lines scan A c7ced327c1b5

Subscribe to this mod's changes

wrangler is a plugin published in the GitHub repository bacchus-labs/wrangler (4 stars, last pushed 6mo 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.

Debugging TDD Testing

backend-development

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development.

wshobson/agents · not measured

tdd-guard

Automated Test-Driven Development enforcement.

nizos/tdd-guard · not measured

superpowers-deepseek-v4

Superpowers DeepSeek v4: composable agent skills for TDD, debugging, and collaboration. Independently maintained; not identical to obra/superpowers.

gylove1994/superpowers-deepseek-v4 · not measured

cantrips

The core engineering loop for coding agents (Claude Code, Codex CLI): grill, spec, tickets, implement with TDD at agreed seams, review, commit, plus a user-gated compound step that turns session learnings into durable project memory. Basic spells a caster always has prepared.

toverux/cantrips · not measured

otter-skills

Portable software-craft skills for thin delivery, TDD, safe change, naming, refactoring, and trustworthy commits.

tottinge/otter-skills · not measured

whetstone

Engineering-craft skills that sharpen the edge: red-green TDD, flaky-test audit, pre-decision doubt review, merge-conflict resolution, skill linting, and a column budget computed from the staged diff. Each carries a deterministic self-verify.

raisedadead/claude-code-plugins · not measured