Isolated install-and-smoke test drives for DeepSeek Harness plugins: installs a repo or npm package into a throwaway DSH_HOME profile, verifies the bundle patch layer and boot logs, records a structured pass/fail result matrix (JSON/Markdown) for scoring pipelines, and quarantines every temp directory it owns

ci developer-tools dsh workflow-automation ai-agents cordis ai-agent deepseek compatibility-matrix plugin-testing deepseek-harness dsh-plugin install-smoke

• Updated Nov 6, 2026
• TypeScript

Benchmark harness for A/B testing Claude Code plugins against OOLONG long-context reasoning tasks. Compare truncation vs RLM-RS recursive chunking strategies. Features Claude Code hooks integration, SQLite persistence, and comprehensive scoring aligned with the OOLONG paper methodology.

python nlp cli benchmark developer-tools chunking claude rlm oolong ai-evaluation llm long-context anthropic context-window claude-code plugin-testing recursive-language-model

• Updated Apr 13, 2026
• Python

Preflight, test, release and hot-reload DeepSeek Harness plugins: one CLI, 34 tests, real output in the README.

nodejs cli hot-reload release-automation dsh preflight deepseek plugin-testing deepseek-harness dsh-plugin plugin-tooling

• Updated Nov 12, 2026
• JavaScript

Trustworthy, automated testing for REAPER plugins and extensions - point it at a plugin and get a real pass/fail, no test code required. (macOS today; Windows/Linux WIP)

python testing qa lua daw reaper dylib vst3 clap jsfx audio-plugins plugin-testing no-false-results

• Updated Jul 17, 2026
• Python

This repository hosts the pre-built web output (flutter build web) of a Flutter project used to test and demo plugin behavior in the browser. It is not the source code — only the deployable artifacts (main.dart.js, CanvasKit, assets, and the service worker) live here.

dart github-pages demo static-site flutter flutter-web canvaskit plugin-testing

• Updated Jul 18, 2026
• JavaScript

Binary-criteria evaluation harness for Claude skills with planned extension to plugins, agents, and MCP servers. Score every change yes/no across 7 layers — package integrity, trigger quality, functional quality, regression protection, baseline value, model variance, rollout safety. Never gradients.

mcp regression-testing skill-evaluation ai-evaluation llm-eval claude-code plugin-testing eval-harness agent-eval binary-criteria

• Updated Nov 12, 2026
• TypeScript

🚀 Automate the evaluation of Claude Code plugin components to ensure accurate triggering of skills, agents, commands, and hooks.

cli typescript test-automation developer-tools evaluation-framework claude llm ai-testing anthropic claude-code claude-agent-sdk plugin-testing

• Updated Oct 12, 2026
• TypeScript

Lifecycle conformance testing for DeepSeek Harness plugins

integration-testing dsh plugin-testing deepseek-harness dsh-plugin

• Updated Oct 10, 2026
• TypeScript

Vendor-neutral research umbrella for measuring AI plugin, agent, and MCP server quality across CLI runtimes (Claude Code, Gemini CLI, Copilot CLI, Codex CLI).

mcp skill-discovery opentelemetry ai-evaluation gemini-cli claude-code plugin-testing cross-cli agent-eval invocation-rate

• Updated Nov 12, 2026
• Python

Regression and compatibility testing for Claude Code, plugins and MCP servers. Detect breaking changes, automate CI checks and capture reproducible evidence.

cli typescript continuous-integration mcp regression-testing ai-agents security-testing compatibility-testing release-monitoring github-actions model-context-protocol claude-code plugin-testing claude-code-canary

• Updated Nov 9, 2026
• TypeScript

Deterministic, answer-keyed Obsidian vaults for testing plugins, plus faithful hand-authored starter vaults for PKM methods and roles. MIT + CC0.

markdown gtd test-data note-taking para obsidian pkm knowledge-management zettelkasten second-brain personal-knowledge-management obsidian-plugin obsidian-md obsidian-vault plugin-testing maps-of-content

• Updated Jul 24, 2026
• Python

Testing harness for AI agent skills and plugins — contract-driven YAML specs with mocked environments

cli typescript testing-framework ai-agent claude-code agent-testing plugin-testing skill-testing

• Updated Apr 4, 2026
• TypeScript

DeepSeek prices, plugin search and model specs inside DeepSeek Harness. We run free sandbox install tests on every DSH plugin — see which ones actually work.

mcp sandbox pricing deepseek plugin-testing model-specs deepseek-harness dsh-plugin

• Updated Nov 7, 2026
• JavaScript

Reproducible paired A/B experiments for DeepSeek Harness plugins, with isolated runners, auditable evidence, and deterministic promotion gates.

cli benchmarking typescript ab-testing reproducibility dsh ai-agents llm-evaluation agent-evaluation plugin-testing deepseek-harness dsh-plugin

• Updated Aug 26, 2026
• TypeScript

Unattended REAPER host tests for VST3 plugins on Windows: render null tests, bypass, save and reopen, instance churn, in an isolated REAPER configuration.

windows powershell reaper vst3 audio-plugins plugin-testing null-test

• Updated Nov 7, 2026
• PowerShell

DSH plugin market index where every entry carries its real sandbox install verdict. 4,367 plugins, free to subscribe.

sandbox discover plugin-testing plugin-market deepseek-harness dsh-plugin

• Updated Nov 5, 2026
• JavaScript

A disposable, isolated Docker test lab for OpenCode V2 plugins: build and load any plugin in the real runtime and verify loading, tools, collisions, failure isolation, cleanup and provenance.

nodejs docker open-source opencode developer-tools test-harness opencode-plugin plugin-testing

• Updated Oct 23, 2026
• JavaScript

Performed end-to-end manual testing and source code analysis on the easy.jobs WordPress Plugin (v2.7.1), identifying 8 bugs across 22 test cases covering authentication, job management, candidate management, security, and edge cases.

test-cases wordpress-plugin qa functional-testing software-testing bug-report manual-testing plugin-testing

• Updated Apr 27, 2026

Independent GitHub Action that proves DeepSeek Harness plugins install, compose, boot, and answer HTTP in a clean profile.

compatibility-testing github-actions plugin-testing deepseek-harness

• Updated Aug 15, 2026
• JavaScript

Testing framework for Codify plugins with complete lifecycle testing, IPC communication, and cross-platform support

plugin testing framework test ipc integration-testing codify plugin-testing

• Updated Apr 23, 2026
• TypeScript