Agent Claude Code
Code quality reviewer. Evaluates elegance, complexity, pattern adherence, test coverage, and maintainability. Use after implementation. NOT for domain correctness (domain agents).
Agent Claude Code
Documentation quality reviewer. Evaluates structure, accuracy, completeness, actionability, and audience fit. Use when docs are generated or modified. NOT for code quality (code-critic).
Agent Claude Code
Hook timeout safety and Node.js ESM conventions reviewer. Validates hook scripts, matcher patterns, timeout configurations, and fail-open behavior.
Agent Claude Code
CLI/backend contract guardian. Validates command schemas, output contracts, error handling, and process lifecycle across Coral integrations.
Agent Claude Code
SKILL.md quality reviewer. Validates frontmatter correctness, argument-hint declarations, reference resolution, and protocol clarity.
Agent Claude Code
Post-implementation test auditor. Verifies implemented tests against production behavior and rejects unnecessary, duplicate, brittle, or overengineered verification.
Agent Claude Code
Plugin UX reviewer. Evaluates cognitive clarity, discoverability, workflow composition, and progressive disclosure of Coral CLI commands, skills, and user-facing text.
Agent
Architecture & debugging advisor. Use PROACTIVELY when reviewing code structure, design patterns, dependency analysis, or debugging complex issues. Also participates as a structural reviewer in the /plan protocol. NOT for requirements analysis (gap-finder).
Agent
Plan & code change critic. Use PROACTIVELY when reviewing implementation plans, schema changes, or significant code modifications. NOT for code analysis (architect) or requirements gathering (gap-finder).
Agent
Systematic bug diagnosis via hypothesis testing, reproduction tracing, and root cause analysis.
Agent
Requirements gap analyst. Catches missing questions, undefined guardrails, scope risks, and edge cases before planning. Use PROACTIVELY when scoping new features, API changes, state lifecycle changes, or concurrency behavior modifications. NOT for project scanning (scanner), code debugging (debugger), or plan review…
Agent
Generate a diverse, differentiated discussion persona based on role and topic. Spawned in parallel by discuss-lead.
Agent
Finds the most elegant form of any design or solution, regardless of cost.
Agent
Adversarial test generator - writes tests targeting blind spots the implementer missed.
Agent
Feedback synthesizer and contradiction resolver. Synthesizes reviewer findings using Vada frame, resolves constraint collisions via TRIZ, and applies changes directly to the plan file. Spawned by plan skill at step 4b. NOT for reviewing (architect/critic) or planning (plan skill).
Agent
Project scanner and process investigator. Maps architecture, traces dependencies, investigates systemic issues. Use for project understanding, repo analysis, or process-level root cause investigation. NOT for requirements gaps (gap-finder), code bugs (debugger), or code architecture review (architect).
Agent
Pipeline step processor for inline prompt literals in workflow DSL. Executes user-provided instructions against pipeline context.