autonomous development agents

opensesh/KARIMO

Agent Claude Code

Generates self-contained, portable task briefs from PRD data. Spawned by /karimo:run Phase 1 for each task.

opensesh/KARIMO

Agent Claude Code

Review coordination agent — validates task PRs, manages revision loops, handles model escalation. Spawned by PM Agent per task PR. Never writes code.

opensesh/KARIMO

Agent Claude Code

Conducts research to enhance PRD context or explore general topics. Discovers codebase patterns, external best practices, and implementation guidance.

akaszubski/autonomous-dev

Agent

Implementation specialist - writes clean, tested code following existing patterns.

akaszubski/autonomous-dev

Agent

Adversarial plan reviewer - challenges assumptions, identifies gaps, enforces minimalism.

akaszubski/autonomous-dev

Agent

Architecture planning and design for complex features.

yves-s/just-ship

Agent

Design-affiner Frontend-Entwickler. Implements UI components with high design quality. Use when UI changes are needed.

yves-s/just-ship

Agent

Orchestriert die autonome Entwicklung. Analysiert Tickets, erstellt Specs, spawnt Experten-Agents und schließt mit Commit/PR/Merge ab. Use proactively when a ticket needs to be implemented end-to-end.

yves-s/just-ship

Agent

Testing Engineer für Teststrategie, Testentwicklung und Acceptance-Criteria-Verifikation. Use after implementation to write tests and verify acceptance criteria.

opensesh/karimo-overview

Agent Claude Code

Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks.

opensesh/karimo-overview

Agent Claude Code

Reviews pull requests for test coverage quality and completeness. Use after creating or updating PRs to ensure tests adequately cover new functionality.

opensesh/karimo-overview

Agent Claude Code

Reviews code for silent failures, inadequate error handling, and inappropriate fallback behavior. Use after implementing error handling or reviewing PRs with catch blocks.

OrodruinLabs/nazgul

Agent

Adversarial post-loop verifier — grades the QUALITY of inline source doc-comments (XML , JSDoc, docstrings, shell doc headers) on files changed this objective for templated, restatement, and contradiction defects, and writes the objective-scoped completion marker required by the stop-hook comment-verifier gate.

OrodruinLabs/nazgul

Agent

Implements one task at a time following project patterns and reviewer feedback.

OrodruinLabs/nazgul

Agent

Orchestrates the review board — runs pre-checks, delegates to reviewers, collects verdicts, manages task state transitions.