claude

testgaps

Turns code-review findings into tests: one test-writer agent per finding writes the smallest test that proves it, runs it, and reports whether it reproduced the defect. A hook confines the writer to test files

3 on GitHubby Jarryd Hoffmanv0.1.0MITupdated 24 days agotesting
/

Plugin testgaps from marketplace jarrydh-agents in Jarryd-W-Hoffman/agents. Commands read from the repo's manifest — 19 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 (1)

  • write

    Write tests that prove review findings. Takes the findings from a four-pass review (the report, a findings.json, or one request in plain words), launches one test-writer agent per finding in parallel, and merges the results into one report that says, per test, whether it reproduced the defect, cover

Subagents (1)

  • test-writer

    Use this agent when you need one review finding turned into a test that proves it — a failing test that reproduces a defect a correctness pass reported, or a passing test that covers behaviour a completeness pass called untested — written in the repository's own test conventions, run once, and class

Hooks (1)

  • PreToolUse

    TEST_SCOPE_GUARD_AGENTS='*test-writer' python3 "${CLAUDE_PLUGIN_ROOT}/hooks/test-scope-guard.py"

View source on GitHub

More from Jarryd-W-Hoffman/agents

All 6 plugins →

fourpass

claude

Four-pass code review: completeness, correctness, compliance and consistency reviewer agents run in parallel, then merged into one ranked report

1 skill · 4 agents · hooks

3

impact

claude

Maps what a change touches and what reaches it: callers, routes, scheduled tasks, queued jobs, event listeners, tests that reach it and changed code none do, data and contracts. Facts, not a review. Launches nothing when only docs or tests changed

1 skill · 1 agent · hooks

3

migrations

claude

Reviews database migrations for what breaks in production: old code against the new schema during a deploy, table locks, data loss, constraints existing rows violate, and missing rollbacks. Launches nothing when a change has no migrations

1 skill · 1 agent · hooks

3

regressions

claude

Checks whether a change undoes what the repository's history already learned: removes a fix's guard, re-introduces reverted code, loosens a regression test, or leaves a usual partner file behind. Launches nothing when the history has nothing to say

1 skill · 1 agent · hooks

3

review

claude

Works out which of this marketplace's plugins a change needs, from the files it touches and with no model, and shows the plan: what would run, what is skipped and why, and what to offer afterwards

2 skills

3

Similar plugins

mattpocock-skills

claude

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

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

agent-browser

claude

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

12 skills

vercel-labs/agent-browser 50,373

Open Code Review

codex

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

Maintain testgaps?

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 plugins6 plugins