Testing agents

dynamics365ninja/d365fo-mcp-server

Agent Claude Code

Authoring role for the D365FO agent eval loop catalog. Drafts a new eval/cases/ .json spec (valid against eval/cases/schema.json), scaffolds its golden folder, and sets goldenpending until the golden is captured on the VM. Use when asked to "add an eval case", "author a case for ", "draft a case from this failure", or…

dynamics365ninja/d365fo-mcp-server

Agent Claude Code

Implementer role of the D365FO agent eval loop. Runs ON THE VM (mcp-server in full mode + C# bridge) against the Contoso sandbox model. Takes an eval case id, drives the grounded MCP tool path to implement it, builds, scores against the golden/SysTest oracle, writes a corpus record, and rolls back. Use when asked to…

dynamics365ninja/d365fo-mcp-server

Agent Claude Code

Improver role of the D365FO agent eval loop. Reads the corpus of run records, ranks failure clusters, reproduces a TOOLDEFECT/KNOWLEDGEGAP/VALIDATORGAP as a minimal VM-free repo test, fixes it, validates against the held-out split, and opens a PR citing corpus evidence. Runs in the repo (never touches the VM). Use…

lkmeta/txtify

Agent Claude Code

QA gatekeeper for Txtify. Use to run the full verification ladder on the current tree and report evidence — before merging, releasing, or when asked "does everything still work?".

zjunlp/DataMind

Agent Claude Code

Evaluate expectations against an execution transcript and outputs.

ZhangShenao/harness9

Agent Claude Code

A full-repository quality review and improvement agent for a Go project. Go is a programming language, and a repository is the project folder containing its source code and supporting files.

vincenthopf/My-Claude-Code

Agent

Verifies implementation work by running code, executing tests, and generating adversarial test cases. Checks against the problem definition and principles, not against the proposal document. Approval is gated on execution results, not code reading.

maxwell2732/paper-replicate-agent-demo

Agent Claude Code

End-to-end verification agent. Checks that slides compile, render, deploy, and display correctly. Use proactively before committing or creating PRs.

windviki/vBookmarks

Agent

Agent "testing" from windviki/vBookmarks, covering testing & real-browser harness (detail), unit tests (detail), manual testing checklist and headless smoke test (docker).

raphaelmansuy/edgeparse

Agent Codex

Evaluate expectations against an execution transcript and outputs.

bonigarcia/context-engineering

Agent

Implement Idea and scoreidea in src/backlog.py, and verify them with tests/testbacklog.py. Use the formula impact 5 + strategicfit 3 - effort 2.

koolamusic/claudefiles

Agent

Part of jira

Validates that the executed sprint actually meets PLAN.md's Nyquist criteria. Fills coverage gaps by writing tests for any criterion not already covered. Implementation files are READ-ONLY. Spawned by /jira:execute after jira-executor finishes.

chaohong-ai/ai-auto-work

Agent Claude Code

Evaluate expectations against an execution transcript and outputs.

czlonkowski/n8n-mcp-cc-buildier

Agent Claude Code

Use this agent when you need to test n8n webhook endpoints with specific input data and verify their execution results. This agent creates bash test scripts (handling JWT tokens when needed), executes them, and cleans up afterward. Keeps test execution isolated from the main conversation context.

jamesmontemagno/ohmyposh-configurator

Agent

Tests the Oh My Posh Configurator MCP server. Use this agent to validate MCP tools like listing segments, creating configurations, validating configs, and exporting in different formats.

bitsocialnet/5chan

Agent Claude Code

Verifies UI changes in the browser using playwright-cli across Blink, Gecko, and WebKit. Use after making visual or interaction changes to React components, CSS, layouts, or routing to confirm they render and behave correctly.

haacked/dotfiles

Agent

Use this agent when you need to write comprehensive unit tests for existing code, when implementing test-driven development, when code coverage needs improvement, or when refactoring requires test safety nets. Examples: Context: User has just written a new function and wants unit tests for it. user: 'I just wrote this…

minorun365/my-claude-code-settings

Agent

A testing and debugging assistant for web applications, using browser inspection, automated browser tests, local runs, and application logs.

ccashwell/evm-cortex

Agent

Foundry fuzz testing, Foundry invariant testing, Medusa and Echidna stateful fuzzing campaigns.

zhensherlock/protocol-launcher

Agent

A coding workflow for adding new Protocol Launcher tools, which open applications through special links. It creates the implementation, exports, configuration entries, and unit tests needed for a new protocol.

idiotLeoLYJ/Daliu-Awesome-Skills

Agent

Part of skill-creator-cn

Compare two outputs WITHOUT knowing which skill produced them.

idiotLeoLYJ/Daliu-Awesome-Skills

Agent

Part of skill-creator-cn

Evaluate expectations against an execution transcript and outputs.

aaddrick/claude-pipeline

Agent Claude Code

Validates PHPUnit test comprehensiveness and integrity. Use after code review to audit PHP/Laravel tests for cheating, TODO placeholders, insufficient coverage, or hollow assertions. Reports failures requiring developer subagent correction.

panaversity/ksor

Agent Codex

Evaluate expectations against an execution transcript and outputs.