agentic-dev-team

Install a Claude Code plugin and register it in settings.json so the full team can replicate the install. Use this whenever adding a new plugin to the project — it keeps settings.json in sync with what is actually installed.

Scaffold a new review agent from a description or URL. Use this whenever the user wants to add a new review agent, detect a new category of code issue, or says things like "add an agent for X", "create a reviewer for Y", "I want to check for Z in code reviews". Also use when given a URL to a coding standard or best-practices guide that should become a review agent.

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 time agent/skill files change.

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".

Remove an agent from the system — deletes the agent file, cleans up all registry entries, removes cross-references, and updates documentation. Use when the user says "remove the X agent", "delete X-review", "retire the X role", or "we no longer need X". Handles both team agents and review agents. Always confirms before deleting.

Create and maintain agent and skill files. Use when adding a new agent, creating a new skill, or updating existing ones.

Contract-first API design for stable, evolvable interfaces. Use when defining new API endpoints, service boundaries, or modifying existing contracts.

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.

System design, architecture definition, and technical decision oversight. Use when the user needs architecture review, system design, or technical decisions.

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

Execute an approved implementation plan using TDD. Reads the plan, implements each step with RED-GREEN-REFACTOR, runs inline review checkpoints, and produces verification evidence. Use when the user says "build this", "implement the plan", "start building", or after /plan has been approved.

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

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 commits and pull requests.

```text

```json

Compare this plugin against external plugins, tools, feature sets, or ideas to find gaps and weaknesses. Accepts a URL, local path, feature list, or concept as input. Produces a structured gap analysis report with rough specs for closing each gap.

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

Compress conversation history when context utilization approaches 40%. Write a structured summary to memory/ and start a fresh context window.

Resume work from a prior session by reading phase progress files in 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".

Machine learning model development, data analysis, and statistical validation. Use when the user needs ML models, data analysis, or statistical work.

Pipeline design, deployment strategy, observability, and reliability planning. Use when the user needs CI/CD, deployment, monitoring, or infrastructure work.

Strategic DDD health assessment of an existing system. Assess bounded contexts, context map, event flows, value stream, and friction report.

Model software around the business domain. Use when designing bounded contexts, defining aggregates, mapping context relationships, or working with complex business logic.

Capture amend/learn/remember/forget keywords and update agent or skill configurations. Use when the user issues any feedback trigger word.

Scope-lock file editing to a specific glob pattern. Only files matching the pattern can be edited until /unfreeze is called.

Audit logging, quality gates, and ethics procedures. Use for compliance reviews, task completion logging, or ethical concern escalation.

Activate both careful mode and freeze mode together. Blocks destructive commands and scope-locks editing to the specified pattern. Use for production-critical debugging sessions.

Analyze review agent effectiveness, model routing, and orchestration complexity against actual usage data. Produces a report of harness components that may be candidates for simplification or removal. Use periodically to prevent harness staleness as model capabilities improve.

List all available slash commands with their descriptions.

Design with ports and adapters to separate business logic from infrastructure. Use when designing services, reviewing structural compliance, or introducing external dependencies.

Approval gates, intervention commands, and transparency requirements. Use to classify actions, respond to override/pause/stop commands, or structure plan reviews.

Break a plan into independently-grabbable GitHub issues. Use when the user says "create issues from this plan", "break this into tickets", "file issues", or wants to distribute plan steps across a team.

Safely modify code that lacks tests. Apply characterization tests and dependency-breaking techniques before making behavioral changes.

Run a mutation testing tool (Stryker/pitest/mutmut) and triage surviving mutants. AI classifies survivors and writes fix tests.

Central dispatcher that routes tasks to specialized agents and coordinates multi-agent collaboration. Use for complex or ambiguous tasks that need multi-agent coordination.

Log task completion data to metrics/. Record tokens, cost, agents used, rework cycles, and hallucination events.

Create a structured implementation plan with goal, acceptance criteria, incremental TDD steps, and a pre-PR quality gate. Use this for tasks that need a plan but not the full three-phase orchestration, or when the user says "plan this", "make a plan", "break this down", or "how should I implement this".

Run a pre-PR quality gate (tests, typecheck, lint, code review) and then create a pull request with a structured summary. Use when the user says "create a PR", "open a PR", "submit for review", or "I'm done with this feature".

Requirements clarification, priority management, and stakeholder alignment. Use when the user needs feature scoping, prioritization, or user stories.

Acceptance test driven development, test generation, quality metrics, and regression testing. Use when the user needs test strategy, acceptance tests, or quality validation.

Unified quality gate — self-validation, verification evidence, and review-correction loops. Use before delivery, at completion, and during rework.

Run a single named review agent against target files. Use this when the user names a specific agent (e.g. "run security-review", "check for test issues", "run js-fp-review on this file") rather than wanting the full suite. Prefer this over /code-review when only one concern is relevant or speed matters. Also used by the orchestrator for inline review checkpoints during Phase 3 implementation.

Generate a compact summary of the most recent code review results and save it for future sessions. Use this at the end of a coding session after /code-review has run, or when the user says "summarize the review", "save the results", "generate a summary", or wants to preserve review context before closing a session.

Alias for /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.

Threat modeling, security analysis, vulnerability assessment, and secure design guidance. Use when the user needs security review or threat analysis.

Run Semgrep static analysis on target files and return structured findings. Use this when the user wants static analysis, SAST scanning, or security scanning — phrases like "run semgrep", "scan for vulnerabilities", "static analysis on this code", or as a pre-review gate when security findings are needed before AI agents run.

Detect a project's tech stack and auto-generate project-level CLAUDE.md, PostToolUse hooks, and language-specific agent templates in one shot. Use this when onboarding a new project, or when the user says "setup", "bootstrap", "configure this project", or "detect my stack".

Full-stack development, code generation, implementation, and refactoring. Use when the user needs code written, bugs fixed, or code refactored.

Collaborative specification workflow producing four artifacts (Intent, BDD scenarios, Architecture notes, Acceptance Criteria) before implementation. Use when starting a new feature or behavior change, or when the user says "write specs", "specify this", or "what should we build".

Project documentation, terminology consistency, and ubiquitous language enforcement. Use when the user needs technical docs, style consistency, or user guides.

Structured STRIDE security analysis for identifying threats, attack surfaces, and mitigations. Use before implementing new APIs, auth changes, or data flows crossing trust boundaries.

Investigate a bug, find its root cause, and file a GitHub issue with a TDD fix plan. Use when the user reports a bug and wants it triaged, says "triage this", "investigate and file an issue", or wants a hands-off bug investigation that produces an actionable issue.

User interface design, UX optimization, and accessibility compliance. Use when the user needs UI patterns, accessibility review, or design specs.

Lift the scope lock set by /freeze. All files become editable again.

Check for and apply plugin updates. Pulls the latest version, shows what changed, and applies the update from within a Claude Code session.

Report the installed version of the agentic-dev-team plugin.

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

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

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

System design, architecture definition, and technical decision oversight

CLAUDE.md completeness, rules, skills, and path accuracy

Cyclomatic complexity, nesting depth, function size, parameter count

Race conditions, async pitfalls, idempotency, shared state safety

Machine learning model development, data analysis, and statistical validation

Pipeline design, deployment strategy, observability, and reliability planning

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

Domain boundaries, abstraction leaks, business logic placement

Array mutations, parameter mutations, global state, impure patterns in JS/TS

Captures institutional knowledge after feature completion or complex bug fixes — gotchas, patterns, decisions, and edge cases

Naming clarity, conventions, magic values, and consistency

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

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

Requirements clarification, priority management, and stakeholder alignment

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

Acceptance test driven development, test generation, quality metrics, and regression testing

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

Threat modeling, security analysis, vulnerability assessment, and secure design guidance

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

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

Verify implementation matches specification before quality review agents run

SRP violations, DRY, coupling, nesting depth, file organization

Svelte reactivity pitfalls, closure state leaks, $state proxy issues, store subscription leaks

Project documentation, terminology consistency, and ubiquitous language enforcement

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

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

User interface design, UX optimization, and accessibility compliance

Traces a use case through all architecture layers, mapping data access patterns, caching, external integrations, and identifying gaps. Analysis-only agent (read-only).

Initialize a new JavaScript project with ES modules, functional style, prettier, eslint, editorconfig, vitest, and gitignore. Use this skill whenever the user wants to start a new JS project, scaffold a Node.js app, create a new package, bootstrap a JavaScript repo, or says things like "init a new project", "set up a JS project", "create a new node app", "start a new frontend project", or "bootstrap a new package". Also trigger when the user asks to add standard JS tooling (linting, formatting, testing) to an empty or near-empty directory.