dev-team

Plugin dev-team from marketplace bfinster in bdfinst/agentic-dev-team. Commands read from the repo's manifest — today.

Skills (101)

• adr-tools

  Create and manage Architecture Decision Records using the npryce adr-tools CLI. Use when the user asks to "add an ADR", "record this decision", "create an ADR", "supersede ADR N", "link ADRs", "generate the ADR table of contents", or any request involving the `adr` command. Pairs with the adr-author

• agent-audit

  Audit code-review agents, skills, and hooks for structural compliance. Use this when adding or modifying any agent, skill, or hook file, or for a periodic health check of the toolkit. Trigger phrases: "audit the agents", "check compliance", "validate the skills", "are the agents correct", or any tim

• agent-eval

  Run eval fixtures against review agents and grade results. Use this after adding or modifying a review agent, to validate detection accuracy, or when the user says "run the evals", "test the agents", "check for regressions", or "how accurate is the agent". Read, Grep, Glob, Bash(readlink *, ls *, da

• agent-readiness

  Score how ready the current repository is for AI-assisted development against the Agent-Readiness Scorecard. Use when the user asks "how agent-ready is this repo", "score this repo for agents", "agent readiness", or wants a tiered readiness report. Scores YOUR project repo's readiness — not the dev-

• api-design

  Contract-first API design for stable, evolvable interfaces. Use whenever defining a new API endpoint, inter-service boundary, or modifying an existing contract. Includes backward compatibility checklist and error contract specification.

• apply-fixes

  Apply correction prompts generated by /code-review. Use this whenever the user wants to apply, fix, or action the results of a code review — phrases like "apply the fixes", "fix the issues", "apply corrections", or after /code-review has run and produced a corrections/ directory.

• apply-test-doubles

  Apply `/cd-test-architecture`'s Step 4b build-vs-document decision logic against an existing, saved assessment report — or, when no valid report path is given, against a target to assess first — without re-running the full Steps 0-6 assessment each time. Use when the user wants to revisit or change

• artifact-lifecycle

  Report on skill and agent usage data from ~/.claude/metrics/artifact-usage.json, classifying each artifact as active, stale (>= 30 days unused), or an archive candidate (>= 90 days unused). Proposes CLAUDE.md overrides for stale artifacts and exclusions for archive candidates. Pinned skills are alwa

• autoship

  Orchestrate a bounded round of automated issue processing: reclaim orphaned in-progress issues, discover eligible `autoship:ready` issues, and invoke `/ship` sequentially for each — stopping at cost or count caps and surfacing blocked items without halting the round. Requires `--max-issues` and `--m

• benchmark

  Capture runtime performance metrics (Core Web Vitals, resource sizes, load times) for web pages. Compare against baselines and performance budgets. Use when the user says "benchmark", "check performance", "page speed", "web vitals", "performance regression", or "how fast is this page".

• branch-workflow

  Clean branch completion workflow — PR creation, merge strategy, and cleanup. Use this skill when implementation is complete and it's time to ship — after Phase 3 human gate passes. Also use when the user says "create a PR", "merge this", "ship it", "finish this branch", or asks about merge strategy.

• browse

  Launch a browser to navigate URLs, take screenshots, click elements, and fill forms. Use for visual verification, e2e testing, and interactive debugging.

• browser-testing

  Patterns and templates for browser-based QA using Playwright. Covers navigation, form interaction, screenshot capture, visual verification, and CAPTCHA/auth handoff.

• careful

  Toggle careful mode. When active, destructive commands (rm -rf, force-push, DROP TABLE, etc.) are blocked instead of just warned about.

• cd-test-architecture

  Evaluate an existing application's tests and recommend a CD-pipeline-aligned test architecture — fast, deterministic tests with minimal tooling that fully validate behavior (including cross-service interaction) and run in CI without configuring the rest of the system. Use when the user says "evaluat

• ci-debugging

  Systematic CI/CD failure diagnosis with hypothesis-first approach, environment delta analysis, and anti-patterns. Use when CI fails, pipelines break, or the user says "CI is failing", "build broke", "pipeline error", or "tests pass locally but fail in CI".

• claude-setup-review

  Audit this project's Claude Code harness — CLAUDE.md completeness, rule clarity, skill and agent wiring, path accuracy, and agent frontmatter schema compliance. Use when the user says "review my CLAUDE.md", "audit my Claude setup", "is my Claude config right", "check my agent frontmatter", "are my s

• co-evolution-audit

  Flag production files that churn repeatedly while their paired test files do not change — the "Red Queen" co-evolution gap. Uses git log --stat to compute per-file change frequency over a configurable window, applies language-aware pairing heuristics (Python, JS/TS, Go, Java, C#), and produces a ran

• code-review

  Run all enabled review agents against target files. Use this whenever the user asks for a code review, wants feedback on their code, says "review my code", "check this before I PR", "what's wrong with this", "run the agents", or has just finished implementing a feature. Use proactively before commit

• competitive-analysis

  Compare this plugin against external plugins, tools, feature sets, or ideas to find gaps and weaknesses. Produces a structured gap analysis report with rough specs for closing each gap. Use this skill whenever the user references capabilities from OUTSIDE the plugin — another plugin they found, a co

• context-loading-protocol

  Decide which agents and skills to load for a given task. Use at the start of every task to select the minimum viable context load, calculate the token budget, and stay below the 40% utilization ceiling.

• continue

  Resume work from a prior session by reading phase progress files in .claude/memory/ and active plans. Use this when starting a new session on in-progress work, or when the user says "continue", "pick up where I left off", "resume", or "what was I working on".

• cost-report

  Report actual token spend and dollar cost of dispatched work — per agent and total — and flag cost regressions. Use when the user asks "how much did that cost", "token spend", "cost of this run", "cost report", or wants to check for a cost regression after /code-review or an orchestration run. Bash(

• coverage-baseline

  Multi-workflow coverage baseline worker. Detects the repo's coverage tool from its build manifest, runs it, records the resulting line+branch percentages as the baseline, and posts the number to the parent issue (or local `FEATURE.md`). This number is the floor every later phase must improve on. Cal

• coverage-delta

  Multi-workflow coverage delta worker. Reads the baseline coverage, re-runs the same coverage tool against the current suite, computes the delta on line+branch percentages, and posts it to the parent issue (or local `FEATURE.md`). Called after each Story so the operator sees coverage move with every

• design-doc

  Produce a written design document in docs/specs/ with user approval before planning begins. Use this skill during the Research phase when a feature request, architectural change, or non-trivial task enters the pipeline. Ensures misunderstandings are caught before any planning or implementation work

• design-interrogation

  Relentlessly interview the user about a plan, design, or feature spec to surface unresolved decisions, hidden assumptions, and edge cases. Use when the user says "grill me", "stress-test this plan", "poke holes in my design", "what am I missing", or before committing to a plan that feels under-exami

• design-it-twice

  Generate multiple radically different interface designs for a module using parallel sub-agents, then compare and synthesize. Based on Ousterhout's "Design It Twice" principle. Use when the user wants to explore interface options, design an API, compare module shapes, or says "design it twice", "what

• docker-image-audit

  Audit Docker images and Dockerfiles for security vulnerabilities, bloat, and best-practice violations using hadolint, Trivy, and Grype. Produces a structured severity report with actionable fixes. Use this skill whenever the user wants to check a Docker image for security issues, scan a container fo

• docker-image-create

  Generate production-ready Dockerfiles from project source code. Detects language/framework automatically and produces multi-stage builds with minimal, distroless, or slim base images. Use this skill whenever the user wants to containerize an application, create a Dockerfile, dockerize a project, bui

• doctor

  Diagnose the dev-team plugin install and this repo's dev-team configuration, and create missing runtime directories with --fix.

• domain-analysis

  Strategic DDD health assessment of an existing system. Use whenever someone asks to analyze their architecture, assess domain health, find coupling problems, map bounded contexts, trace event flows across services, or understand what is slowing down delivery. Trigger on phrases like "what's wrong wi

• domain-driven-design
• exploratory-testing
• explore
• farley-score
• feature-file-validation
• feedback-learning
• fix
• freeze
• frontend-architecture
• gherkin-derive
• gherkin-public
• governance-compliance
• guard
• handoff
• harness-audit
• harness-e2e-check
• headless-run
• help
• hexagonal-architecture
• human-oversight-protocol
• issues-from-assessment
• issues-from-plan
• lane
• legacy-code
• long-eval
• mermaid-diagramming
• mutation-night-watch
• mutation-testing
• orchestration-benchmark
• performance-benchmark
• performance-metrics
• plan
• pr
• project-init
• property-based-testing
• proxy-resilience
• quality-gate-pipeline
• quality-targets-converge
• repo-review
• report-pdf
• review-agent
• review-summary
• review
• run-report
• semantic-duplication-scan
• semantic-scan
• semgrep-analyze
• session-review
• setup
• ship
• source-verification
• specs
• speculative-build
• static-analysis-integration
• stryker-xunit-v2-shim
• systematic-debugging
• telemetry
• test-audit-disable
• test-design-advisor
• test-design
• test-driven-development
• test-health
• test-improve
• threat-modeling
• triage
• ubiquitous-language
• unfreeze
• upgrade
• version

Subagents (48)

• a11y-review

  WCAG 2.1 AA compliance, semantic HTML, ARIA, keyboard navigation, focus management

• acceptance-examiner

  Source-blind acceptance examiner that runs the plan's commands and reports one verdict per criterion, dispatched by /build Step 7.6 and never directly

• adr-author

  Creates and manages Architecture Decision Records (ADRs) with a decision framework for when to create one

• ai-provenance-review

  Checks whether AI-authored test assertions and non-obvious production decisions carry human-verification evidence, flags verification debt and regeneration-risk candidates

• angular-reactivity-review

  Angular Zone.js change-detection pitfalls, OnPush + immutability violations, RxJS subscription leaks, async-pipe alternatives

• arch-review

  Architectural alignment — ADR compliance, layer boundary violations, dependency direction, pattern consistency

• architect

  System design, architecture definition, and technical decision oversight

• autoship-batch-proposer

  Propose issue-number groupings among currently-ungrouped autoship candidates from their titles and bodies

• claude-setup-review

  CLAUDE.md completeness, rules, skills, path accuracy, and agent frontmatter schema compliance

• codebase-recon

  Reconnaissance agent that surveys a codebase's structure, entry points, dependencies, security surface, and git history. Produces a contract-conformant RECON artifact at `.claude/memory/recon-<slug>.{md,json}` that other agents consume.

• component-architecture-review

  Reusable component extraction and frontend duplication — repeated UI patterns, prop drilling, component granularity, inconsistent component APIs

• concurrency-review

  Race conditions, async pitfalls, idempotency, shared state safety

• correctness-review

  Functional/behavioral defects where implementation diverges from evident intent (missing assignments, wrong operators, inverted conditions, missing guard clauses, off-by-one/boundary errors, unverified runtime/library claims, error-signalling divergence)

• data-flow-tracer

  Traces a use case through all architecture layers, mapping data access patterns, caching, external integrations, and identifying gaps. Read-only analysis agent — it never edits code; its one execution grant is a scoped Bash(graphify *) for running the Graphify CLI's read-only query commands.

• doc-review

  Documentation accuracy, README staleness, API doc alignment, inline comment drift, ADR update triggers

• domain-review

  Domain boundaries, abstraction leaks, business logic placement

• gherkin-quality-critic

  Adversarially reviews freshly-derived or freshly-authored Gherkin scenarios for coverage gaps and positive/negative balance, immediately after generation

• js-fp-review

  Array mutations, parameter mutations, global state, impure side effects, and point-free/composition opportunities in JS/TS

• mutation-kill

  Autonomous mutation survivor-reduction loop — runs a scoped mutation tool, generates targeted tests for survivors in priority order, verifies they compile and pass, commits, and repeats until survivors stop decreasing. Gates on hard kills only (timeouts excluded). Complements the advisory /mutation-

• naming-review

  Naming clarity, conventions, magic values, and consistency

• orchestrator

  Central dispatcher that routes tasks to specialized agents and coordinates multi-agent collaboration

• performance-review

  Resource leaks, N+1 queries, unbounded growth, timeouts, algorithmic issues

• plan-review-acceptance

  Adversarially critiques an implementation plan's acceptance criteria, Gherkin scenarios, and step traceability before the human plan-review gate

• plan-review-design

  Adversarially critiques an implementation plan's technical design — coupling, abstraction boundaries, structural risks, and pattern adherence — before the human plan-review gate

• plan-review-parallelization

  Verifies that an implementation plan's declared same-wave concurrency is real — no file collisions, no disjoint-file behavioral coupling, no residual graph mis-layering — before the human plan-review gate

• plan-review-strategic

  Adversarially critiques an implementation plan's problem-solution fit, scope, risk, and opportunity cost before the human plan-review gate

• plan-review-ux

  Adversarially critiques an implementation plan's usability, accessibility, and error experience before the human plan-review gate; self-skips for plans with no user-facing surface

• platform-engineer

  CI/CD pipeline design, deployment strategy (blue-green, canary, rolling), rollback planning, observability (SLOs, alerting, dashboards), and reliability/incident-mode design — dispatch when the user asks "how should we deploy this", "design the pipeline", "what's our rollback plan", "make this obser

• product-manager

  Requirements clarification, priority management, and stakeholder alignment

• progress-guardian

  Tracks plan step completion, enforces commit discipline, and gates plan changes through human approval

• qa-engineer

  Senior SDET — partner on acceptance criteria, coach teams on test design and CD-aligned test architecture, dispatch test-health and test-design skills; non-gatekeeping. Champions pipeline-as-product and DORA-driven feedback.

• quality-reviewer

  Coordinates code quality review agents and drives the fix loop for a freshly-implemented unit of work

• react-reactivity-review

  React hook rules violations, stale closures in useEffect, missing dependency arrays, setState-during-render, subscription leaks

• refactor-opportunity-review

  Assesses refactoring opportunities after tests pass (TDD REFACTOR phase), distinguishing semantic duplication from structural similarity

• security-engineer

  Design-time threat modeling and secure-architecture guidance before code exists — dispatch when a task touches authentication, authorization, cryptography, session management, or secrets handling, introduces a new external integration or API surface, or the user asks to "threat model this", "design

• security-review

  Injection, auth/authz, data exposure, security headers, crypto

• session-analysis

  Map an aggregated session digest to probable plugin causes and ranked, tagged improvement suggestions

• software-engineer

  Full-stack development, code generation, implementation, and refactoring

• spec-compliance-review

  Verify implementation matches specification before quality review agents run

• spec-reviewer

  Verifies a freshly-implemented unit of work against its acceptance criteria and Gherkin scenarios before quality review runs

• sql-review

  SQL anti-patterns that break under schema or data change - positional INSERT, correctness traps, index-defeating predicates, unsafe migrations

• structure-review

  SRP violations, DRY, coupling, nesting depth, cognitive load, async-pattern judgment, file organization

• tech-writer

  Project documentation, terminology consistency, and ubiquitous language enforcement

• test-review

  Test quality, coverage gaps, assertion quality, and test hygiene

• test-smell-review

  xUnit test smells, test double selection, and test-pyramid layer placement

• token-efficiency-review

  Token usage optimization, file length, CLAUDE.md size, LLM anti-patterns

• ui-ux-designer

  User interface design, UX optimization, and accessibility compliance

• vue-reactivity-review

  Vue ref/reactive unwrapping pitfalls, watchEffect dependency tracking, reactive proxy escapes, composition API subscription leaks

Hooks (30)

• SessionStart

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/pending_review_notify.py"

• SessionStart

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/repo_review_nudge.py"

• SessionStart

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/mcp_json_repowise_nudge.py"

• SessionStart

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/codegraph_bootstrap.py"

• SessionStart

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/autocompact_setup_nudge.py"

• SessionStart

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/post_compact_state_reinject.py"

• UserPromptSubmit

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/telemetry.py"

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/pre_tool_guard.py"

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/contract_version_guard.py"

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/refactor_test_freeze_guard.py"

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/boundary_events_write_guard.py"

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/feature_record_guard.py"

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/verify_guard_edit_marker.py"

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/destructive_guard.py"

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/refactor_test_bash_guard.py"

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/pre_pr_review.py"

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/internal_double_gate.py"

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/pre_commit_knowledge_index.py"

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/telemetry.py"

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/verify_guard.py"

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/bash_retry_guard.py"

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/stryker_xunit_shim_guard.py"

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/mutation_testing_smoke_gate.py"

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/scan_bash_command_for_banned_scripts.py"

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/boundary_events_write_guard.py"

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/telemetry.py"

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/code_intelligence_nudge.py"

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/code_intelligence_nudge.py"

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/code_intelligence_nudge.py"

• PreToolUse

  sh "${CLAUDE_PLUGIN_ROOT}/hooks/py.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/agent_dispatch_ledger.py"