claude

q-engine

A software engineering team as subagents (product manager, product owner, architect, engineer, database, debugger, reviewer, verifier) that hand work to each other through files, with /q-engine:feature and /q-engine:reproduce-bug workflows and coding-guideline, commit and Playwright CLI skills.

1 on GitHubby phuquocchampv0.2.0MITupdated 3 days ago
/

Plugin q-engine from marketplace q-harness in phuquocchamp/q-harness. Commands read from the repo's manifest — 3 days ago.

What it installs

Skills (5)

  • feature

    Take a feature from idea to verified code with the q-engine team (product manager, product owner, architect, engineer, reviewer, verifier), pausing for the user's approval between stages. Each stage writes a file that the next stage reads.

  • playwright-cli

    Drive a real browser from the shell with the playwright-cli tool. Use when you need to open a web page, click or fill a form, take a screenshot or snapshot, read console or network output, reproduce a UI bug, or check UI behavior by hand. Requires the @playwright/cli package (playwright-cli on PATH

  • reproduce-bug

    Reproduce a web app bug in a real browser and write an evidence report. swe-architect plans the hypotheses, swe-verifier reproduces them with playwright-cli, and the main session compiles the report. Proposes a fix but does not apply it.

  • swe-commit

    Commit discipline for git. Use when the user asks to commit, write or fix a commit message, split work into several commits, or prepare changes for a pull request. Stages only related changes, keeps secrets out, and writes messages in the project's convention.

  • swe-core

    Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Subagents (8)

  • swe-architect

    Solution Architecture agent for analyzing, designing, debating, and stress-testing architectural decisions, implementation approaches, and system design choices. Use when you need to: evaluate a proposed architecture, find flaws in an approach, compare design alternatives, audit separation of concer

  • swe-database

    Database engineering specialist for schema design, normalization, query optimization, and data modeling. Use when you need to: design or review a database schema, normalize tables to 1NF/2NF/3NF, model entity relationships (1:1, 1:N, N:N), write or audit migrations, design constraints and triggers,

  • swe-debugger

    Debugging specialist for root-cause analysis. Use when a test fails, an error or stack trace appears, or behavior differs from what is expected and the cause is not yet known. Finds the root cause with evidence and applies the smallest fix. For bugs whose cause is already known, use swe-engineer ins

  • swe-engineer

    Senior software engineer agent for implementing complex, multi-step coding tasks. Use when writing new features, refactoring, implementing user stories or a design, or fixing bugs whose cause is already known. Prefers surgical changes, surfaces tradeoffs, and defines verifiable success criteria befo

  • swe-product-manager

    Product Manager agent that owns the "why" and "what" of the product. Use when you need to: identify or validate a market need, conceptualize a product or feature idea, research and compare competitors, analyze target users and their problems, write or update market research, a feature proposal, a Bu

  • swe-product-owner

    Product Owner agent that turns a validated product idea into concrete, buildable requirements for the engineering team. Use when you need to: break a feature or epic into user stories, write acceptance criteria (Given/When/Then), define functional requirements, write or update use cases, order and r

  • swe-reviewer

    Expert code review specialist. Proactively reviews a diff for correctness, security, and maintainability. Use immediately after writing or modifying code, or before opening or merging a PR. Reviews the code itself; checking the work against requirements is swe-verifier's job.

  • swe-verifier

    Verification agent that checks whether a feature or fix meets its requirements and acceptance criteria, then writes a structured report. Use after implementing a feature, before merging a PR, or when asked to verify, validate, or audit an implementation against requirements. Does not change source c

View source on GitHub

More from phuquocchamp/q-harness

All 5 plugins →

q-pilot

claude

Runs browser tasks and UI tests from a prompt, like jev-ultrafast: Claude writes the task, Jev (TypeSafe) picks every step, Playwright executes it, and a live inspector shows and pauses each decision. Tests are graded by code, never by Jev's DONE; a passing test can be saved as a flow that the stop gate replays with no model when Claude edits UI.

1 skill

1

q-advisor

claude

Context advice at turn boundaries: focuses Claude Code's own autocompact on the plan, decisions and changed files, and suggests compacting, clearing for a new task or switching model, with Jev (Haiku fallback) making the judgement calls. Starts in shadow mode.

1

q-graph

claude

Shows the subagents, teammates and Workflow runs of a session as a live graph: a `q-graph` button above the prompt, an alert when one waits for you, and a pane with the agent tree, what each agent used (tools, skills, MCP servers, rules) and the session's harness.

1

q-panel

claude

Draws each Bash call and each file change (Write, Edit, NotebookEdit) as a bordered panel, and frames the code blocks in replies with copy and collapse buttons.

1

Similar plugins

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

ecc

claudecodex

Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses

200 skills · 98 commands · 71 agents · 1 MCP server · hooks

affaan-m/ECC 302,088

Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives

1 command

anthropics/claude-code 155,476

IoT device lifecycle, telemetry anomaly detection, fleet management, and witness chain verification for Cognitum Seed hardware

5 skills · 1 command · 4 agents

ruvnet/ruflo 81,589

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

ship-mate

claudecodex

Your AI development teammate. Turns a story file into a shipped, reviewed, and tested feature via orchestrator → architect → developer → PR reviewer → QA → Playwright.

1 skill · 2 commands · 6 agents

wshobson/agents 42,461

Maintain q-engine?

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 plugins5 plugins