Coding & dev tools
qarunbook
A test runbook for web and mobile apps: an AI assistant drafts the plan, and testers or agents record results over MCP.
What qarunbook does
qarunbook (QA Runbook) is a web app for manual and user acceptance testing. A team keeps a test plan for each app, where every check has steps, an expected result and the platforms it covers (web, Android, iOS). Testers mark checks passed or failed and raise issues on the check that found them, with screenshots, recordings and logs attached.
When an issue is marked fixed, the check moves to retest instead of back to passed, and it stays there until someone checks again. Access is set per project, and a join link can add a whole group.
AI comes in through MCP. Claude Code, Claude Desktop, Codex, Cursor and other MCP clients connect to a hosted endpoint with a personal token, and a plugin adds two skills: /test-checklist drafts checks from your codebase, and /qa-runbook works through the plan, records results and retests fixes. An AI import feature turns an existing file or text into a plan; the privacy policy says that content goes to Anthropic's Claude. Paid plans add a REST API with workspace keys for filing issues from a support desk or reporting results from CI. GitHub and Linear are listed integrations.
The plugin repository is MIT-licensed; the hosted service is not described as open source. qarunbook suits small teams and solo developers who test releases by hand and already use an AI coding assistant.
- Have an AI assistant draft a test plan from an app's code before a release.
- Run user acceptance testing across web, Android and iOS with a shared checklist.
- Keep bugs attached to the checks that found them and retest after fixes.
- Let a coding assistant read failing checks and mark issues resolved over MCP.
- Report automated results from CI through the REST API.
Who should use it
- Small teams that test releases by hand.
- Developers who use Claude Code, Codex or Cursor and want tester findings available to their assistant.
Who should look elsewhere
- Unit testing or automated test running; the README says it is built for human acceptance testing.
- Free-plan users who need the REST API, which starts on the Team plan.
Strengths
- A fixed issue sends its check to retest until someone verifies it.
- Flat workspace pricing with no per-seat charge.
- MCP connection and two AI skills are included on every plan, including Free.
Limitations
- The Free plan covers one person, one app and 150 checks tested a month.
- The REST API is limited to Team, Business and Enterprise plans.
- AI import sends the supplied file or text to Anthropic's Claude.
- The MCP token acts as the user who created it, with that user's role.
Privacy notes
The privacy policy lists Vercel for hosting, MongoDB Atlas for the database and Backblaze B2 for attached files, and says AI import sends the supplied content to Anthropic's Claude.
Sources
- qarunbook (QA Runbook) — Testing, simplified and effective.Official sitePrimaryqarunbook.com
- Pricing — qarunbookPricing pagePrimaryqarunbook.com
- API documentation — qarunbookOfficial docsPrimaryqarunbook.com
- github.com/Ifeanyiejindu/qarunbookRepositoryPrimary
- github.com/Ifeanyiejindu/qarunbook/blob/main/server.jsonRepositoryPrimary
- qarunbook.com/privacyWeb
- github.com/Ifeanyiejindu/qarunbook/blob/main/LICENSERepositoryPrimary
qarunbook alternatives
AgentDock
Coding & dev tools
A Mac app that shows Claude Code, Codex and other coding agents as status dots and lets you answer them from one Inbox.
PaidFree tierVerifiedAgent Activity
Coding & dev tools
Mac app that shows what AI coding agents do in Xcode: live sessions, build timelines, errors and test results in one window.
PaidVerifiedClair
Coding & dev tools
Answer Claude Code permission prompts, questions and plan reviews from a Wear OS watch or an Android phone.
FreemiumFree tierVerifiedGitHub Copilot
Coding & dev tools
GitHub's AI coding assistant for code completion, chat, agent mode, code review and cloud agents across editors, the CLI and GitHub.
FreemiumFree tierVerifiedClaude Code
Coding & dev tools
Anthropic's coding agent that reads a codebase, edits files and runs commands from the terminal, IDE, desktop app or web.
PaidAPIVerifiedCursor
Coding & dev tools
An AI code editor and coding agent that plans, writes and reviews code on your desktop, in the terminal, in Slack and in the cloud.
FreemiumFree tierAPIVerified
Related open-source projects
Caveman is a skill plus a local proxy that reduce the tokens a coding agent spends, both in what it writes back and in what it reads. The skill changes the reply style: answer first, one idea per sentence, no greeting or recap. Code, commands, file paths, error messages and numbers are kept character for character, and your own prompts are never rewritten. There are three levels (/caveman, /ultracave and /megacave, the last one in classical Chinese) and extra commands for one-line commit messages, terse code review and shrinking memory files such as CLAUDE.md. The second part is the caveman CLI, which runs on your machine and compresses bulky input before the agent sees it: logs, CSV, YAML, JSON and test output. Originals stay on disk so the agent can pull them back. The CLI also has caveman browse for compact web pages and caveman learn, which ranks where tokens went in past sessions. Separate TypeScript and Python middleware packages apply the same compression to agents built on the Vercel AI SDK, LangChain, OpenAI or Anthropic calls. The project's own benchmark reports 33.2% fewer input tokens over 54 Claude Code runs, with 18 of 18 answers correct. The same table shows HTML sessions getting 9.9% worse, because HTML has no compressor yet.
- Stars
- 111K
- Language
- Go
- License
- Apache-2.0
- Momentum
- +1.6% 7dEstablished
ECC is an open-source system that adds reusable engineering workflows, skills, agents, memory, rules, hooks and security checks to coding agents. Its main path is Claude Code, with guided installation also available for Codex and Kimi Code. The repository also contains adapters for other coding agents, but the project warns that support is not equal across them. The current repository includes 68 agents, 293 skills and 94 legacy command shims. The supplied workflows cover tasks such as planning, testing, implementation, review, build repair, security and architecture. ECC also includes AgentShield integration for scanning agent configuration, prompts, hooks, MCP settings, permissions, secrets and related files. Hooks and memory can enforce checks outside the prompt, store session information and support its continuous-learning system. The easiest starting point is the ecc-universal guided installer. Claude Code setup needs Node.js 18 or newer, Git and Claude Code 2.1 or newer on PATH. The multi-agent installer can configure Claude Code, Codex and Kimi Code in one reviewed flow. Kimi installation is more limited: ECC writes managed project files but does not configure Kimi hooks, model or provider settings, or authentication.
- Stars
- 278K
- Language
- JavaScript
- License
- MIT
- Momentum
- +2.2% 7dEstablished
Ponytail is a rule set and skill collection that pushes an AI coding agent to write as little code as a task needs. It ships as a plugin for Claude Code, Codex, GitHub Copilot CLI, Gemini CLI and several other agent hosts, and as plain rules files for editors such as Cursor, Windsurf and Cline. Before writing anything, the agent works down a fixed ladder: drop the feature if it does not need to exist, reuse what the codebase already has, then try the standard library, a native platform feature, an installed dependency and a one-line answer. New code comes only after all of those fail. The README is firm that validation, error handling, security and accessibility are off limits for cutting. Its example: asked for a date picker, the agent reaches for a native <input type="date"> instead of adding a library and a wrapper component. The plugin adds commands to set the intensity (lite, full, ultra or off), to review a diff or a whole repository for over-engineering, and to collect deferred shortcuts into a ledger. The maintainer publishes a benchmark: across twelve feature tasks on a FastAPI and React template with Haiku 4.5, the README reports about 54% fewer lines of code than the same agent without the skill, plus smaller drops in tokens, cost and time.
- Stars
- 162K
- Language
- JavaScript
- License
- MIT
- Momentum
- +5.7% 7dEstablished
Agent Skills is a repository of 25 Markdown workflows for AI coding agents, covering software work from specification and planning through testing, review, performance, security, deployment and documentation. Each skill is a SKILL.md process with triggers, steps, red flags, verification criteria and common rationalizations to counter. The pack can be installed with the skills CLI or integrated with tools including Claude Code, Cursor, Gemini CLI, OpenCode, GitHub Copilot and Codex. Nine slash commands map development tasks to skills. /build auto can generate a plan and implement its tasks after one approval, while stopping on failures or risky steps. This suits teams that want an agent to follow a defined engineering process instead of relying on isolated prompts. The repository also contains four review personas, shared checklists, evaluation cases and host-specific adapters. One installation limitation matters: installing a single skill through npx does not copy the repository-level references/ directory, so links to shared checklists are unavailable unless those files are supplied another way.
- Stars
- 106K
- Language
- JavaScript
- License
- MIT
- Momentum
- +4.9% 7dEstablished