Manually create a QA incident from a known issue. Usage: /qa-incident <description>
Review QA knowledge base stats, prune stale entries, show learning metrics. Usage: /qa-learn [prune]
Run QA checks. Usage: /qa (commit), /qa full (comprehensive), /qa staging (deployed), /qa prod (read-only).
QA baseline updater — manages test snapshots and golden files for API response validation
Adversarial QA agent that red-teams test plans. Reads the diff, knowledge base, and test plan to find gaps the test strategy missed.
Domain logic quality evaluator. Validates business logic integrity — state machines, enum consistency, constraint rules, and domain-specific correctness. Three-tier evaluation with explicit confidence levels.
E2E test specialist — Playwright browser tests for user workflows
Converts generated test scenarios that caught real bugs into permanent baseline test files. Writes provenance to qa-knowledge.
Executes bash commands
Hook triggers when Bash tool is used
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Claude Code plugins for AI-powered development workflows — agents, skills, and hooks.
Step 1: Get a license key — email [email protected]
Step 2: Activate your key (in terminal, not Claude Code)
npx @arthai/agents activate ARTH-XXXX-XXXX-XXXX-XXXX
This stores your key at ~/.arthai/license. All future sessions use it automatically.
Already have the toolkit cloned at ~/.claude-agents/? Skip steps 1-2 — your existing key at ~/.claude-agents/.license works automatically.
Step 3: Add the marketplace (in Claude Code)
/plugin marketplace add ArthTech-AI/arthai-marketplace
Step 4: Install a bundle (in Claude Code)
/plugin install forge@arthai-marketplace
Step 5: Reload plugins (in Claude Code)
/reload-plugins
Step 6: Start using skills (in Claude Code)
/calibrate # auto-configure for your codebase (first time)
/planning my-feature # start building
The toolkit validates your license key on every interaction:
project-setup hook fires~/.arthai/license or ~/.claude-agents/.licenseWithout a valid key, the plugin is installed but non-functional.
| Scenario | What happens |
|---|---|
| Valid key, first prompt | Validates against server, caches result, skills work |
| Valid key, subsequent prompts | Cache hit, skills work instantly |
| No key | "LICENSE REQUIRED — Run npx @arthai/agents activate..." on every prompt |
| Invalid/revoked key | "LICENSE INVALID — Key not recognized" on every prompt |
| Server down, valid cache | Cache used, skills work |
| Server down, no cache | Fails open (allows usage until server is reachable) |
| Key was revoked | "LICENSE INVALID" on next prompt after cache expires (within 24h) |
| Need a new key after revocation | Email [email protected], then npx @arthai/agents activate ARTH-NEW-KEY |
Pick what you need. Each bundle is a self-contained set of agents, skills, and hooks.
| Bundle | Install | What you get |
|---|---|---|
| forge | /plugin install forge@arthai-marketplace | Full dev workflow: /planning, /implement, /qa, /pr, /precheck, /review-pr + architect, PM, backend, frontend, QA, code-reviewer agents + triage router + escalation guard |
| scalpel | /plugin install scalpel@arthai-marketplace | Bug fixing: /fix, /ci-fix, /issue + code-reviewer + troubleshooter agents |
| spark | /plugin install spark@arthai-marketplace | Project setup: /onboard, /calibrate, /scan, /setup + setup and explore agents |
| Bundle | Install | What you get |
|---|---|---|
| sentinel | /plugin install sentinel@arthai-marketplace | SRE + ops: /sre, /incident, /restart + SRE, ops agents + deploy health, port guard, crash watcher hooks |
| prism | /plugin install prism@arthai-marketplace | Deep QA: /qa, /qa-learn, /qa-incident + 6 QA agents (qa, e2e, domain, challenger, baseline, promoter) |
| shield | /plugin install shield@arthai-marketplace | Safety guardrails: bash guard, edit guard, session bootstrap, triage router, escalation guard (no skills — hooks only) |
| Bundle | Install | What you get |
|---|---|---|
| canvas | /plugin install canvas@arthai-marketplace | Design: /planning + design-studio agents (think, create, critique) + frontend agent |
| compass | /plugin install compass@arthai-marketplace | Product: /planning + PM, GTM, user researcher, content strategist agents |
| counsel | /plugin install counsel@arthai-marketplace | Consulting: 13 skills (client-discovery, proposals, deliverables, ROI, etc.) + 4 consulting agents |
| Bundle | Install | What you get |
|---|---|---|
| cruise | /plugin install cruise@arthai-marketplace | Autonomous mode: /autopilot — picks up issues, implements, QAs, creates PRs. Requires forge + scalpel + sentinel. |
| prime | /plugin install prime@arthai-marketplace | Everything. All agents, skills, and hooks. |
After installing, use skills in Claude Code:
Start a new project:
/onboard # get project briefing
/calibrate # auto-configure toolkit for your codebase
/planning my-feature # design the feature with architect + PM agents
/implement my-feature # build with parallel agent team
npx claudepluginhub arthtech-ai/arthai-marketplaceQA skills for automation domain.
Agents specialized in quality assurance, testing strategies, and test architecture. Focuses on ensuring code quality and reliability.
Use this agent for analyzing test results, synthesizing test data, identifying trends, and generating quality metrics reports. This agent specializes in turning raw test data into actionable insights that drive quality improvements. Examples:\n\n<example>\nContext: Analyzing test suite results
Verification-first engineering toolkit for Claude Code. 15 skills across a 5-phase spine (Investigate → Design → Implement → Verify → Ship), 8 specialist agents, an interactive setup wizard. Every skill has rationalizations + evidence requirements. Built for senior ICs and tech leads.
10 coordinated QA agents for Claude Code: chains diff analysis, AC compliance, test scenarios, browser validation, bug reports, and automation code generation.
Quality assurance - E2E testing, PR review, browser automation