Skill Claude CodeCodex
Turn an EARS spec + donewhen.yaml contract into the full test pyramid: existence checks (ripgrep/tree-sitter), unit tests (example-based + property-based), integration tests (with testcontainers, no mocks), e2e (Playwright/Cypress/Appium/Maestro), and mutation-testing configuration as an anti-reward-hacking layer…
Plugin Claude Code
Agent Teams Product Development Pipeline - 7-phase adversarial collaborative development with multi-agent debate, competition, and cross-validation at every critical decision point, including red team attacks, adversarial debugging, independent bug fix loop, and requirement verification.
Agent
A final acceptance reviewer that checks whether a software change meets its requirements and technical standards.
Agent
A coding agent that fixes build, type-checking, and lint errors by changing only the code needed. It checks the result and reports what changed.
Agent
A code-quality review agent that examines naming, structure, error handling, performance, duplicated code, and whether tests genuinely check the intended behavior.
Agent
A deployment agent that puts approved code into a production environment and checks that it works afterward. It also prepares a rollback if deployment fails.
Agent
An architecture decision agent that compares competing software designs and chooses a final approach using a scoring table.
Agent
A visual design reviewer that compares a design reference, such as a Figma file or screenshot, with the rendered website or its code.
Agent
A documentation assistant that updates project documents to match changes already made in the code. It can work with files such as a README, API documentation, a changelog, and architecture records.
Agent
A bug-fixing assistant that applies test-driven development (TDD): first writing a test that reproduces the bug, then making the smallest code change that fixes it, and finally checking for regressions.
Agent
An AI role that writes and defends product requirement documents from the user's point of view. A product requirement document explains what a product should do and why.
Agent
A read-only code-quality checker that reviews completed work while other agents are implementing tasks. It looks for issues such as misleading tests or missing checks.
Agent
A security review assistant that actively tries to exploit vulnerabilities in an application and traces each attack from its entry point to its effect.
Agent
A neutral reviewer that combines reports from requirements, code, security, and red-team reviewers into one final assessment. It removes duplicate findings, ranks their seriousness, and issues a release recommendation.
Agent
A task-plan reviewer that examines how a software project is divided into work and rates risks across five areas.
Agent
A structured review of software security from the defender’s point of view. It checks common areas such as login, permissions, input handling, data protection, sessions, dependencies, and configuration.
Agent
An architecture-design assistant that studies the product requirements, existing code, and architecture records before proposing a system design. It can also respond to technical criticism and revise the design.
Agent
A requirements checker that compares the finished code with a product requirements document (PRD), architecture decision records (ADRs), and API specifications. It produces a table showing which requirements are covered.
Agent
A planning assistant that turns product requirements and architecture decisions into small development tasks, with task dependencies and file ownership notes.
Agent
A coding assistant for working as one member of a team of agents. It implements an assigned task, follows TDD, checks file ownership, commits the change, and reports progress.
Agent
A technical reviewer who stress-tests architecture proposals and searches for weaknesses in scalability, security, cost, and complexity. Scalability means continuing to work as the system or workload grows.
Agent
A codebase investigator who examines the existing architecture and challenges whether a product requirement is technically realistic. It reports hidden complexity, performance effects, security risks, and affected areas.
Skill Claude CodeCodex
A team-based architecture design process in which several architects propose solutions, a critic challenges them, and an arbiter combines the results. An architecture is the high-level structure and technical choices of a system.
Skill Claude CodeCodex
A requirements-writing process in which a product-focused agent and a technically skeptical agent debate a proposed feature for two rounds. It produces a requirements document after checking both the desired outcome and the codebase's technical limits.