claudecodex

behavioral-testing

Tests that can actually fail: writing guidance, a test-suite audit that proves weak tests with surviving mutants, a gated repair flow, and fail-to-pass bug reproduction. Five worker agents and two hooks.

0 on GitHubby Michael Lockyerv0.1.3MITupdated 3 days agodevelopment
/

Plugin behavioral-testing from marketplace mdlockyer-plugins in mdlockyer/code-quality-plugins. Commands read from the repo's manifest — 2 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (4)

  • behavioral-unit-testing

    Write tests that can actually fail — expected values from the spec, not from running the code; evidence the test fails on the bug and not only passes on the fix; no silent changes to tests; no satisfying the check instead of the request. Use whenever writing, fixing, strengthening, or reviewing test

  • bug-repro

    Turn a bug report, issue, failing scenario, or suspected defect into a fail-to-pass reproduction test with proof that it fails on the current code for the right reason and would pass on any correct fix. Use when asked to "reproduce this bug", "write a failing test for this issue", "prove this is bro

  • test-audit

    Audit a test suite for tests that cannot fail, tests that pass on the bug, tests that enforce wrong behavior, tests pinned to one implementation, and flaky tests; prove each finding with a surviving mutant; report with coverage and stop for approval. Use when asked to audit, review, grade, or assess

  • test-repair

    Repair tests that a test audit found weak, flaky, pinned to one implementation, or suspicious, with proof for every change: a surviving mutant that now dies, a revert that now goes red, or a shuffled run that now agrees. Use after a test audit when the user approves findings, or when asked to \"fix

Subagents (5)

  • oracle-writer

    Derives expected values for tests from the specification, docstrings, type signatures, callers, issue text, and hand arithmetic, without reading the implementation under test, so that the expectation is independent of the code's current behavior. Dispatched by test-repair before any test is rewritte

  • test-auditor

    Examines one test file during a test audit, running five single-question lenses one at a time (can't fail; would pass on the bug; enforces suspicious behavior; pinned to one implementation; brittle or flaky) and recording candidates with file:test_name, the line, and what the test should assert inst

  • test-prover

    Proves or disproves a test-audit candidate by breaking the production code the test guards (flip a comparison, move a boundary, delete a branch, return a constant), running the test, recording whether it stayed green, and restoring the code; also proves repairs by showing the recorded mutant now die

  • test-repairer

    Rewrites one approved test-audit finding into a test that can fail, using expected values derived by the oracle-writer and the oracle ladder's rewrite patterns, preserving the project's conventions, one behavior per test, and recording before/after with the derivation of every literal. The only role

  • test-verifier

    Adversarially verifies test-audit findings and test repairs with fresh context: re-reads every cited line, checks whether another test already catches the recorded mutant, whether the mutant is equivalent, whether a "suspicious" expectation is actually the spec, whether a repaired test fails on the

Hooks (2)

  • PostToolUse

    python3 "${CLAUDE_PLUGIN_ROOT}"/hooks/scripts/passing_test_reminder.py

  • PostToolUse

    python3 "${CLAUDE_PLUGIN_ROOT}"/hooks/scripts/test_edit_guard.py

View source on GitHub

More from mdlockyer/code-quality-plugins

All 2 plugins →

Audit a codebase the way years of production use would: enumerate, understand, hunt with single-question lenses, reproduce, verify adversarially, then fix with regression tests. Orchestration skill plus five worker agents.

1 skill · 5 agents

0

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

slidev

claude

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

slidevjs/slidev 49,452

Maintain behavioral-testing?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins2 plugins