dev-core

Use this agent for system design decisions, cross-cutting architecture, and technical planning across the monorepo. <example> Context: New feature requires architectural decisions user: "Design the caching strategy for the API" assistant: "I'll use the architect agent to design the architecture." </example>

Use this agent for backend implementation tasks in any framework and ORM. Works with NestJS, Express, Fastify, Django, Rails, and any ORM. <example> Context: User needs a new API endpoint user: "Create an endpoint to fetch user preferences" assistant: "I'll use the backend-dev agent to implement the API." </example>

Use this agent for infrastructure, CI/CD, dependency management, and configuration tasks. Works with any build orchestrator, formatter, package manager, and deployment platform. <example> Context: CI/CD pipeline issue user: "GitHub Actions is failing on the typecheck step" assistant: "I'll use the devops agent to debug the CI pipeline." </example>

Use this agent for documentation creation, maintenance, and CLAUDE.md updates. Works with any documentation framework (Fumadocs, Docusaurus, Nextra, plain Markdown). <example> Context: New feature needs documentation user: "Document the new auth module" assistant: "I'll use the doc-writer agent to create the documentation." </example>

Use this agent to fix specific review comments across the entire stack (frontend, backend, tests, config). Receives accepted review findings and applies targeted fixes without writing new features or refactoring beyond what is needed. <example> Context: Review comments have been accepted by the human user: "Fix these accepted review comments: [list of findings]" assistant: "I'll use the fixer agent to apply the fixes across the stack." </example>

Use this agent for frontend implementation tasks in any framework and UI library. Works with TanStack Start, Next.js, Remix, SvelteKit, Nuxt, and any UI component system. <example> Context: User needs a new page or component implemented user: "Implement the user profile page" assistant: "I'll use the frontend-dev agent to implement the UI." </example>

Use this agent for product leadership: requirements gathering, issue triage, prioritization, writing analyses and specs, driving the dev pipeline, and verifying deployed features. <example> Context: New feature needs requirements user: "Gather requirements for the notification system" assistant: "I'll use the product-lead agent to define requirements." </example>

Audit code for security vulnerabilities, review auth flows, and verify compliance with OWASP top 10. <example> Context: Security review needed before release user: "Audit the authentication module for vulnerabilities" assistant: "I'll use the security-auditor agent to perform a security audit." </example>

Use this agent to generate tests, validate coverage, and verify test quality. Works with Vitest, Jest, Pytest, Playwright, Cypress, and any test framework. <example> Context: New feature needs tests user: "Write tests for the auth service" assistant: "I'll use the tester agent to generate test coverage." </example>

Let:

Deep technical analysis — explore existing code, risks, alternatives. Triggers: "analyze" | "technical analysis" | "explore the problem" | "how deep is it" | "deep dive" | "investigate this" | "analyze this feature" | "what are the risks" | "explore the codebase" | "look into this".

Health check — verify dev-core config, GitHub project, labels, workflows, branch protection. Triggers: "checkup" | "health check" | "check setup" | "verify config".

Set up CI/CD — GitHub Actions workflows, TruffleHog, Dependabot, pre-commit hooks, marketplace plugins. Triggers: "ci setup" | "setup ci" | "configure ci" | "setup hooks" | "setup github actions".

Watch a CI run with live status + emoji dashboard; dump logs on failure; watch auto-merge if CI green + auto-merge enabled + "reviewed" label. Triggers: "watch ci" | "ci watch" | "watch the ci" | "watch run" | "monitor ci".

Audit and clean CLAUDE.md, memory, skills, and rules — resolve every finding (fix/promote/relocate/delete), track recurrences, target bloat=0. Triggers: "cleanup context" | "context audit" | "clean memory" | "drain memory" | "prune memory" | "audit memory" | "consolidate rules" | "spa day" | "memory audit".

Clean git branches/worktrees/remotes after merge-status verification. Triggers: "cleanup" | "clean branches" | "cleanup worktrees" | "remove stale branches".

Review branch/PR via fresh domain-specific agents → Conventional Comments → findings + verdict.

Workflow orchestrator — single entry point for the full dev lifecycle. Triggers: "dev" | "start working on" | "work on issue" | "work on #" | "develop" | "pick up issue" | "tackle issue" | "let's work on".

Sync all project docs after a code change — scans every doc for stale references, updates affected sections. Triggers: "sync docs" | "update docs" | "doc sync" | "sync plugin docs" | "update skill docs" | "update the docs".

Set up local dev environment — stack.yml, CLAUDE.md Critical Rules, docs scaffolding, VS Code MDX, LSP. Triggered by /init or standalone. Triggers: "env setup" | "setup environment" | "configure stack" | "scaffold rules".

Apply review findings — auto-apply high-confidence, 1b1 for rest, then batch-apply. Triggers: "fix findings" | "fix review" | "apply fixes" | "fix these" | "apply review comments" | "apply the review" | "fix the review issues" | "address review feedback" | "fix PR comments".

Problem framing — capture problem, constraints, scope, tier. Triggers: "frame" | "frame this" | "what's the problem" | "define the problem" | "scope this out" | "define the scope" | "what are we solving" | "help me think through this problem" | "problem statement".

Connect project to GitHub Project V2 board — discover or create board, labels, branch protection, workspace registration. Triggers: "github setup" | "setup github project" | "connect github board" | "setup project board".

Execute plan — setup worktree, spawn agents, write code + tests. Triggers: "implement" | "build this" | "execute plan" | "start coding" | "write the code" | "code this up" | "let's build it" | "build it out" | "ship it".

Initialize project for dev-core — orchestrates env-setup, github-setup, ci-setup, release-setup. Triggers: "init" | "setup dev-core" | "initialize dev-core".

Structured interview → brainstorm | analysis | spec (with promotion). Triggers: "create a spec" | "interview" | "brainstorm" | "write analysis" | "promote to spec" | "let's brainstorm" | "think through this" | "help me brainstorm" | "let's think this through" | "explore ideas".

Let: τ := `bun ${CLAUDE_PLUGIN_ROOT}/skills/issue-triage/triage.ts` | κ := complexity score

List/dashboard GitHub issues — status, dependencies, backlog. Triggers: "list issues" | "show issues" | "backlog" | "issue dashboard" | "what's blocked" | "what issues are open" | "show backlog" | "show the board" | "what are we working on" | "issue status".

Implementation plan — tasks, agents, file groups, dependencies. Triggers: "plan" | "plan this" | "implementation plan" | "break it down" | "plan this feature" | "how should we build this" | "make a plan" | "create a plan" | "break this down into tasks" | "task breakdown".

Create/update PRs with Conventional Commits title, issue linking & guard rails. Triggers: "create PR" | "open PR" | "submit PR" | "update PR" | "/pr --draft" | "open a pull request" | "make a PR" | "open pull request" | "submit a pull request" | "create a draft PR" | "raise a PR".

Promote staging→main — pre-flight, version bump, changelog, PR & tag. Triggers: "promote staging" | "release" | "deploy" | "cut a release" | "--finalize" | "merge to main" | "promote to production" | "ship a release" | "tag and release" | "publish release".

Audit and upgrade project documentation quality — README.md, CONTRIBUTING.md, plugin READMEs — against the developer-tool pattern (Why, Quick Start, How it works, command tables with categories, diagram). Triggers: "improve readme" | "upgrade docs" | "readme quality" | "improve docs" | "doc audit" | "readme upgrade" | "improve contributing" | "docs health".

Set up commit standards and release automation — Commitizen, commitlint, semantic-release, Release Please, Lefthook/Husky. Triggers: "release setup" | "setup releases" | "commit standards" | "setup release automation".

Bootstrap OSS community health files — CONTRIBUTING.md, LICENSE, SECURITY.md, CODE_OF_CONDUCT.md, README sections (Getting Started, Badges), .github/PULL_REQUEST_TEMPLATE.md, .github/ISSUE_TEMPLATE/. Reads project metadata and CLAUDE.md; generates missing files idempotently. Triggers: "seed community" | "bootstrap community files" | "add contributing" | "add license" | "add security policy" | "github community files".

Populate scaffolded architecture/standards docs with real content extracted from CLAUDE.md and codebase analysis — fills TODO stubs, writes AI Quick Reference sections. Triggers: "seed docs" | "bootstrap docs" | "populate docs" | "fill architecture docs" | "seed architecture".

Solution spec — acceptance criteria, breadboard, slices. Triggers: "write spec" | "spec this" | "solution design" | "what will we build" | "design the solution" | "acceptance criteria" | "define acceptance criteria" | "spec it out" | "write the spec".

Interactive wizard to fill in .claude/stack.yml through guided questions — asks about runtime, backend, frontend, build, testing, deploy, docs, commands, and standards paths, then writes the file. Triggers: "stack setup" | "setup stack" | "configure stack" | "fill stack.yml" | "stack wizard" | "stack-setup".

Generate/run unit, integration & Playwright e2e tests. Triggers: "test this file" | "write tests" | "add coverage" | "run tests" | "e2e tests" | "add tests" | "test coverage" | "generate tests" | "test this" | "write unit tests" | "add integration tests".

Run all quality gates (lint, typecheck, test, env, i18n, license) and produce a structured pass/fail report. Triggers: "validate" | "check everything" | "quality check" | "pre-push check" | "are we green".

3 hooks across 2 events