Model-agnostic coding-agent CLI for command workflows, delegation, subagents, and human-controlled issue-to-ship automation.
This repository also configures its own agents. See what scramjet tells them →
Agent Claude Code
Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequences.
Agent Claude Code
Deeply analyzes existing codebase behavior, data flow, algorithms, side effects, and issue-specific patterns to inform new development.
Agent Claude Code
Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues.
Agent Claude Code
Identifies simplification opportunities in recently modified code and recommends concrete clarity, consistency, and maintainability improvements while preserving functionality.
Agent Claude Code
Analyzes code comments for accuracy, completeness, and long-term maintainability, identifying comment rot, misleading documentation, and opportunities for improvement.
Agent Claude Code
Verifies that a pull request fully implements the requirements from its linked issue and implementation plan, identifying missing or partially implemented features.
Agent Claude Code
Independently re-derives a verdict on each supplied finding — from a code review or a plan review — from the underlying evidence rather than the original author's conclusion, then classifies each using the labels the dispatching brief specifies.
Agent Claude Code
Identifies silent failures, inadequate error handling, and inappropriate fallback behavior in code changes, ensuring every error is properly surfaced and actionable.
Agent Claude Code
Reviews code changes for test coverage quality and completeness, identifying critical gaps in behavioral coverage, edge cases, and error handling.
Agent Claude Code
Designs test strategies from requirements and architecture, providing per-test cost/benefit assessments, coverage intent categorization, and test-first recommendations for bug fixes.
Agent Claude Code
Analyzes type design for encapsulation quality, invariant expression, usefulness, and enforcement, providing quantitative ratings and actionable improvement suggestions.
Agent Claude Code
Use when creating or substantially redesigning Scramjet commands or command sets.
Agent Claude Code
Use when a Scramjet command has a concrete observed outcome that differs from the user's intent.
Agent Claude Code
Use when a proposed or authored Scramjet command change warrants independent holistic review.
Agent Claude Code
Use when command behavior spans multiple files or large definitions need to be compressed for another agent.
Agent Claude Code
Use when another reviewer has produced command findings that require fresh independent adjudication before fixes are authorized.
Agent Claude Code
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.
Agent Claude Code
Produces bounded current-state evidence about responsibilities, dependencies, contracts, consumers, and evidence limits.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: