gitwand-executor
145Agent Claude Code
Implements an approved GitWand plan, one step at a time, test-first. Full edit access. Use after a plan is approved to write the actual code on a feature branch.
2,479 tagged cli, measured the same way as everything else here.
Browse within: bun 117Multi-Agent 96Autonomous Agents 64coding-assistant 60agentic 58langgraph 58drone 56gazebo 56human-in-the-loop 56google-antigravity 51observability 51prompt-engineering 51scaffolding 51client 50
Agent Claude Code
Implements an approved GitWand plan, one step at a time, test-first. Full edit access. Use after a plan is approved to write the actual code on a feature branch.
Agent Claude Code
Turns a GitWand spec or roadmap item into a step-by-step implementation plan. Read-only except for writing the plan document. Use when you have an approved design/spec and need a detailed, reviewable implementation plan before any code is written.
Agent Claude Code
Adversarially verifies a GitWand change before PR — runs the test suites, checks AGENTS.md compliance, and reviews the diff. Read-only (no Edit/Write) so the review stays honest. Use after the executor finishes, before opening a PR.
Agent Claude Code
End-to-end tester for the current VibeFrame CLI. Use when asked to test everything, run full tests, or verify the repo works.
Agent Claude Code
Read-only health audit of the VibeFrame monorepo. Use for a periodic project review — structure, CLI/doc drift, dead code, dependency hygiene, test/lint health, and tech debt — producing a prioritized cleanup plan. Proposes actions; does not make sweeping edits.
Agent Claude Code
Checks version, generated references, public docs, and metadata sync. Use proactively after version bumps, releases, CLI changes, or doc changes.
Agent
System Architect for writing plan.md with architecture decisions and component design. Use for increment technical planning during sw:increment orchestration.
Agent
Increment closer that runs the full sw:done closure pipeline (code-review, simplify, grill, judge-llm, PM validation, sync) in a fresh context. Use when closing increments after task completion to avoid context overflow.
Agent
Test-Aware Planner for generating tasks.md with BDD test plans. Reads spec.md and plan.md to produce implementation tasks with Given/When/Then scenarios. Use during sw:increment orchestration.
Agent Claude Code
Internal agent for reviewing staged code changes against CAS rules. Checks for rule compliance, patterns, and quality. Spawned before commits or on demand.
Agent Claude Code
Internal agent for generating session summaries at stop. Creates a concise summary of work done, decisions made, and learnings captured. Spawned by Stop hook.
Agent Claude Code
Internal agent for verifying task completion. Spawned automatically on task close. Do not invoke directly.
Agent
How claude-mpm enforces compatibility between the CLI and agent repositories, enabling safe breaking changes to agent templates.
Agent
Step-by-step guide to creating custom agents.
Agent
The Research Agent is a specialized AI agent designed to analyze projects, understand codebases, and provide actionable insights for development workflows. Enhanced with skill gap detection and intelligent recommendations, it automatically identifies missing Claude Code skills based on your project's technology stack.
Agent
Creates implementation plans from context and requirements.
Agent
Code review specialist for quality and security analysis.
Agent
Fast codebase recon that returns compressed context for handoff to other agents.
Agent
Creates implementation plans from context and requirements.
Agent
Code review specialist for quality and security analysis.
Agent
Fast codebase recon that returns compressed context for handoff to other agents.
Agent
Use when reviewing code changes for quality, security, and convention compliance.
Agent
Use when working on CI/CD pipelines, GitHub Actions, Docker, or deployment automation.
Agent
Use when preparing releases, version bumps, changelog updates, or publishing packages.