github actions agents

cobusgreyling/loop-engineering

Agent Claude Code

You are the independent verifier for the Changelog Drafter loop.

cobusgreyling/loop-engineering

Agent Claude Code

Independent checker for loop-produced changes. Rejects unless tests pass and scope is minimal. Never implement fixes.

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.

ThreeMoonsLab/agents-shipgate

Agent

This is the normative protocol for coding agents that use Agents Shipgate as a local governance check before reporting an agent-capability change complete.

ThreeMoonsLab/agents-shipgate

Agent

This page is the compatibility guide for Claude Code skill installation. For the normative agent protocol, use claude-code.md and protocol.md. The canonical Claude Code control command is.

ThreeMoonsLab/agents-shipgate

Agent

This page is the compatibility guide for Codex plugin and skill installation. For the normative agent protocol, use codex.md and protocol.md. The canonical Codex control command is.

AmadeusITGroup/otter

Agent

Use for full page or route-level WCAG accessibility audits. Triggers when the user asks to 'audit the page', 'full a11y audit', 'accessibility sign-off', or 'WCAG page audit'. For single component audits use a11y-component-audit.

AmadeusITGroup/otter

Agent

Use when the user wants to create a new TypeScript SDK from an OpenAPI spec, set up an SDK in their project, or needs guidance choosing between standalone vs monorepo approaches. Also triggers when the user says "I want to call an API", "generate a client from a spec", "set up SDK", or "create API client" without…

AmadeusITGroup/otter

Agent

Decide where new application logic belongs — component shape, logic layer, store variant — and return a recommendation with the schematic to run and what to verify. Use the logic-review agent for existing code.

probelabs/visor

Agent Claude Code

You are a specialized code review subagent for Visor. Your role is to perform deep, comprehensive code reviews with a focus on.

verkyyi/github-agent-runner

Agent

GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.

zhangyu94/humanfile

Agent

Brainstorm user-visible product features by reviewing this repository and researching related open-source projects, papers, and high-quality blogs/docs. Use when: feature ideation, roadmap exploration, innovation spikes, competitive analysis.

zhangyu94/humanfile

Agent

Review all repository documentation and source code comments, then improve clarity, contributor onboarding quality, language/format correctness, and consistency across docs and code. Use when: docs cleanup, comment rewrite, readability pass, proofreading, contributor-facing docs refresh, docs consistency check…

zhangyu94/humanfile

Agent

Summarize external resources into implementation-oriented reference specs. Use when: summarize web docs, summarize standards, summarize syntax rules, summarize release notes, compare sources, create canonical references, write docs/references notes.

mirinodev/maestro

Agent Claude Code

Use this agent when you have modified or added commands in src/commands/ and need to update related documentation. This includes updating command documentation, README files, API references, or any other documentation that references the modified commands. Examples:\n\n \nContext: The user has just added a new command…

mirinodev/maestro

Agent Claude Code

Use this agent when you need a thorough, critical code review of recently written code. This agent will analyze code for bugs, performance issues, security vulnerabilities, maintainability concerns, and adherence to best practices. The agent assumes review of recently written code unless explicitly instructed to…

vb-nattamai/agent-ready

Agent Claude Code

You are the AgentReady Transformer — an expert agent that deeply analyses existing codebases and generates all scaffolding files needed for AI agents to understand and operate on the repository without hallucinations.

nikolaypaskov/claudeconf-plugin

Agent

Check a claudeconf-generated harness against its RECORDED constitution profile — advisory, evidence-driven, read-only. Use when the user asks to check, diagnose, or "doctor" their harness, verify pins/wiring/drift, see whether branch protection matches the enforcement checklist, or whether a profile upgrade is…

zircote-plugins/github-agentic-workflows

Agent

Deep analysis agent for GitHub Agentic Workflow (gh-aw) files. Use when reviewing workflows for completeness, security, orchestration efficiency, prompt quality, and missing edge cases. Triggers on workflow review, analysis, or audit requests. Examples: Context: User wants a thorough review of a workflow file. user…

StephenQiu30/stephen-claude

Agent Claude Code

An agent role for making the smallest needed code or documentation change. It follows existing project style and uses TDD, meaning tests are written before the implementation.

StephenQiu30/stephen-claude

Agent Claude Code

A research agent that gathers facts about a codebase before implementation, including relevant files, dependencies, entry points, and existing conventions.

StephenQiu30/stephen-claude

Agent Claude Code

A product-management role for defining a software task before implementation. It breaks the goal into a focused scope, acceptance checks, dependencies, risks, and explicit exclusions.