ai-workflow agents

266 tagged ai-workflow, measured the same way as everything else here.

Browse within: ai-coding 158agent-orchestration 95claude-code-plugin 92adaptive-learning 73ai-development 44hooks 44coding-agent 38codex-cli 34a-b-testing 29ai-agent-orchestration 29ai-code-review 29ai-orchestration 29ai-pair-programming 29ai-routing 29

docs-checker

49

w2ur/claude-code-setup

Agent

Use this agent to audit documentation accuracy and git hygiene on any project. Cleans up plan files committed by mistake, verifies .gitignore coverage, checks README and CLAUDE.md accuracy against actual project state, and optionally verifies URLs match canonical domains. Examples: "Run docs-checker" — full audit "Run…

not rated 2 11d ago A 92 tokens original MIT

implementer

50

w2ur/claude-code-setup

Agent

Executes well-scoped implementation tasks with clear specifications. Use when the plan is defined and subtasks have explicit "done when" criteria. Not for architecture decisions or ambiguous tasks.

not rated 2 11d ago A 39 tokens original MIT

troubleshooter

51

w2ur/claude-code-setup

Agent

Diagnoses structural problems after implementation has failed twice. Evaluates root cause, recommends solutions including rearchitecture, stack changes, or rewrites. Does NOT write production code — produces a plan for the implementer.

not rated 2 11d ago A 47 tokens original MIT

design-doc-writer

52

Maximumsoft-Co-LTD/claude-flightdeck

Agent Claude Code

Author zero-fix Design Docs that let a downstream implementation agent ship in one pass with no re-delegation. Target ≥500 lines for non-trivial tasks (correlates with zero post-delegation rework). Includes AC type-contradiction scan, LSP type verification, touched-files matrix, and lesson references. Use proactively…

not rated 2 2mo ago A 87 tokens original MIT

Maximumsoft-Co-LTD/claude-flightdeck

Agent Claude Code

Top-level PM / orchestrator agent for {{PROJECTNAME}}. Use to pick the next task, plan a sprint phase, sequence parallel work, or summarize current sprint state. Reads docs/project/sprints/S /tasks.md, docs/project/backlog.md, and per-sprint files; never modifies code itself — delegates to the right specialized agent.

not rated 2 2mo ago A 80 tokens original MIT

k8s-engineer

54

Maximumsoft-Co-LTD/claude-flightdeck

Agent

Implement / review Kubernetes infrastructure work for {{PROJECTNAME}} — Helm umbrella charts, Kustomize overlays, ArgoCD Applications, ingress + cert-manager, RBAC, secret management, StatefulSets, CI/CD pipeline (image build → registry → sync controller). Use for image tag bumps, new service deployments, secret…

not rated 2 2mo ago A 81 tokens original MIT

backend-phase-4

55

TouheedCode/claude-dev-workflow

Agent Claude Code

You are the Repository Layer Agent. You build the data access layer using test-driven development. You write tests FIRST, then implement the repository to make them pass. You use Testcontainers for real PostgreSQL integration tests.

not rated 2 2d ago A 0 tokens original MIT

backend-phase-5

56

TouheedCode/claude-dev-workflow

Agent Claude Code

You are the Service Layer Agent. You build the business logic layer using test-driven development. You write tests FIRST with mocked repositories, then implement services to make them pass. Services orchestrate domain logic and transform data between domain and API types.

not rated 2 2d ago A 0 tokens original MIT

backend-phase-6

57

TouheedCode/claude-dev-workflow

Agent Claude Code

You are the Controller Layer Agent. You build thin HTTP controllers using test-driven development. You write E2E tests FIRST with Supertest, then implement controllers that validate input and delegate to services. Controllers are the HTTP boundary — they deal with requests, responses, and status codes.

not rated 2 2d ago A 0 tokens original MIT

WORKFLOW

63

PANZHENYUANPZY/AI-powered-decision-analysis-engine

Agent

User Input (2 YAML files) │ ▼ ATLAS ─── validates input │ ├──parallel──→ ORACLE ──→ data/researchoracle.md │ ECHO ──→ data/researchecho.md │ ▼ ATLAS ─── merges research + input │ ▼ MODEL ENGINE (Python) ──→ output/analysisraw.json │ ├──parallel──→ DEVIL ──→ data/challengedevil.md │ SAGE ──→ data/forecastsage.md │ ▼…

not rated 2 5mo ago A 0 tokens

database-architect

67

niclejeune/pi-agents-config

Agent

Database architecture and design specialist. Use PROACTIVELY for database design decisions, data modeling, scalability planning, microservices data patterns, and database technology selection.

not rated 2 4mo ago A 36 tokens original MIT

prompt-engineer

68

niclejeune/pi-agents-config

Agent

Expert prompt optimization for LLMs and AI systems. Use PROACTIVELY when building AI features, improving agent performance, or crafting system prompts. Masters prompt patterns and techniques.

not rated 2 4mo ago A 40 tokens original MIT

researcher

69

niclejeune/pi-agents-config

Agent

Deep research agent — uses Claude Code as the primary reasoning engine, parallel tools for web discovery.

not rated 2 4mo ago A 21 tokens original MIT

domain

70

ZhaoYis/My-Skills

Agent

How the engineering skills should consume this repo's domain documentation when exploring the codebase.

not rated 2 5d ago A 0 tokens

deep-reasoner

71

jeroromano/claude-code-orchestration-template

Agent Claude Code

Scoped hard reasoning - architecture trade-offs, cross-module debugging, security analysis, migration risk, performance investigation. Use whenever a single hard question needs deep analysis but not a conversation, even if nobody says "delegate". One question in, one decision-grade analysis out. Read-only; never…

not rated 1 25d ago A 64 tokens original MIT

diff-reviewer

72

jeroromano/claude-code-orchestration-template

Agent Claude Code

Local code reviewer and the designated reviewer for Codex-authored diffs. Use before any merge whenever the diff was authored by Codex (Codex never reviews its own work), Codex is unavailable, its quota window is exhausted, or the code must not leave the machine. Reviews the branch diff against its spec for…

not rated 1 25d ago A 85 tokens original MIT

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: