119 tagged ai-workflows, measured the same way as everything else here.
Browse within: agentic-coding 88ai-pipelines 47ai-skills 47ai-code-review 44agent-orchestration 27claude-code-plugin 22antigravity 20infrastructure-as-code 19Multi-Agent 13ai-coding 11context-engineering 11deepmind 11artifical-intelligense 7claude-3-7-sonnet 7
KhanXBT/get-shit-done-antigravity
Agent
Creates project roadmaps with phase breakdown, requirement mapping, success criteria derivation, and coverage validation. Spawned by /gsd:new-project orchestrator.
Agent Claude Code
You are the ADR Guard, responsible for ensuring code changes comply with applicable Architecture Decision Records.
Agent Claude Code
You are the ADR Steward, responsible for managing Architecture Decision Records in this repository.
Agent
Use this agent for UX validation, interaction design, user flows, accessibility review, and design-system consistency checks. Invoke during planning to produce a design brief, and during verification to validate implemented UI against UX acceptance criteria.
Agent
Use this agent for feature implementation, bug fixes, writing tests, and code delivery. Invoke after the team-lead has produced the implementation plan. This agent writes production code, maintains test coverage, and hands off to qa with evidence.
Agent
Use this agent for CI/CD pipelines, infrastructure-as-code, deployment automation, container configuration, secrets management, and observability setup. Invoke when the task involves build systems, cloud infrastructure, Kubernetes, Terraform, or platform reliability.
strikersam/autonomous-ai-agency
Agent Claude Code
The Judge agent runs at the end of an agent session as the release-readiness gate. It performs a holistic review of all changes made during the session and decides whether the work is complete and safe.
strikersam/autonomous-ai-agency
Agent Claude Code
The Planner agent owns the planning phase of any multi-step implementation. It reads the instruction, inspects the repo, and produces a structured AgentPlan with ordered steps, file targets, risk notes, and acceptance criteria.
Agent
The upstream discovery supervisor — runs the discovery-loop skill to turn a raw product idea into a ratified, build-ready decision brief. Holds the discovery-workspace (the typed sidecar) in one reasoning context, diverges across candidate product shapes, drives the lens roster to convergence, pauses at the consent…
Agent
Discovery-time reliability + operability ONLY — a forked-context, read-only reviewer for discovery artifacts (the journey map, service blueprint, screen flows, architecture, decision brief). Required at the discovery loop's G2 reconcile. A DISTINCT agent from work-loop's code quality-engineer — it reviews the design's…
Agent
Discovery-time threat-modeling + regulated-domain compliance ONLY — a forked-context, read-only reviewer for discovery artifacts (the intent tree, domain framing, journey map, service blueprint, screen flows, architecture, decision brief). Required at the discovery loop's G2 reconcile. A DISTINCT agent from…
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: