agentic-coding agents

ambystechcom/AmbyKit

Agent Claude Code

Developer — AmbyKit role for implement; use for that perspective.

ambystechcom/AmbyKit

Agent Claude Code

Product Manager — AmbyKit role for specify/clarify/revise; use for that perspective.

ma-nucho-pro/supervisor-claude-plugin

Agent

Architecture Judge. Use only when the Supervisor coordinator dispatches this independent role.

ma-nucho-pro/supervisor-claude-plugin

Agent

Completeness Judge. Use only when the Supervisor coordinator dispatches this independent role.

ma-nucho-pro/supervisor-claude-plugin

Agent

Correctness Judge. Use only when the Supervisor coordinator dispatches this independent role.

shipwrights/core

Agent

Final code review before PR is human-ready. Reviews the integrated feature branch against repo conventions, hard rules, and the refined epic's acceptance criteria. Returns concrete fix-ups. May make small fix-up commits directly on the feature branch (rename, format, comment) but escalates anything bigger.

shipwrights/core

Agent

Senior frontend engineer. Designs UI composition, component breakdown, state ownership, accessibility, responsive behaviour, and design-token usage. In Shipwright Stage 3 (design-and-build) you write code on your scratch branch within your declared scope. You consume the contract surface — you do not change it after…

shipwrights/core

Agent

Senior Product Owner. Refines vague backlog items into actionable epics with crisp user stories, acceptance criteria, edge cases, and UAT scenarios. Reconciles stakeholder asks. Returns prose; does not write code. Engaged at Shipwright Stage 1 (refine).

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.

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.

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.

scolladon/craft

Agent

You triage the findings of a harness run. Your invocation carries: the absolute working directory (work ONLY there), and EITHER the findings already filtered to the change's lines OR — when the technique's output is not canonical — the path to the raw output file plus the scope spec, in which case shaping and scoping…

scolladon/craft

Agent

You write the implementation plan from an accepted design. Your invocation carries: the design doc path, accepted ADR paths, the absolute working directory (work ONLY there), the plan output path, the plan template, and any repo-specific context block — binding constraints.

scolladon/craft

Agent

You review one dimension of a change. Your invocation carries: the dimension and its definition, the absolute working directory, the diff scope (a git range or a fix-delta commit range plus prior findings), the design doc path, and any repo-specific context block — binding constraints.

albiol2004/trio-agent-loop

Agent Claude Code

Opus adversarial evaluator of the duo loop. Verifies the Lead's iteration against PLAN.md's acceptance criteria by actually exercising the code, using Sonnet explorers for scoped reconnaissance and Sonnet implementors only when delegated verification support is needed. Writes VERDICT.md with SHIP / ITERATE (optionally…

albiol2004/trio-agent-loop

Agent Claude Code

Opus lead of the duo loop — plans, delegates the main implementation pass to Sonnet builders, then reviews and corrects their work. Maintains PLAN.md and REPORT.md and owns the final result.

albiol2004/trio-agent-loop

Agent

Native Trio coordinator that runs the fixed Scout, Lead, Builder, review, and Evaluator protocol.

Black-coffe/vulyk

Agent Claude Code

Blind acceptance gate. Receives the human's brief, the repository and a run command - never plan.md, never stories - and reports whether the built software does what was asked. Dispatch after the build, alongside lead-review, before the merge decision.

Black-coffe/vulyk

Agent Claude Code

Implements exactly one story from docs/specs. The workhorse of the hive - use for all Tier 1-4 implementation. Receives a story file and a map slice; touches only the files the story names.

Black-coffe/vulyk

Agent Claude Code

Writes or repairs tests for exactly one story. Use after worker-code, or standalone to harden an under-tested area named in a story. Tests behavior, not implementation details.

danweinerdev/claude-sdd-planner

Agent

Adversarial fresh-eyes code reviewer. Receives the diff only — no plan, spec, or design — and deliberately hunts for the scenarios intent-aware reviewers forgive: concurrency, retries, encoding, security, production failures, maintenance traps, and unknown-unknowns. Every finding is a concrete scenario, not a vague…

danweinerdev/claude-sdd-planner

Agent

Reviews implementation plans and design documents for completeness, feasibility, convention compliance, and gap analysis. Invoke before approving a plan, when a plan is revised, or when a design needs a structural sanity check. Returns findings with severity and a verdict of Approve or Revise.

danweinerdev/claude-sdd-planner

Agent

Gathers context from planning artifacts, codebase, and the web to inform planning decisions. Invoke at the start of /brainstorm, /specify, /design, /plan, /poke-holes, or any skill that needs a compound view of existing research, specs, designs, plans, and related code before new work begins.

vindm/dotclaude

Agent

Pre-implementation validation — maps integration points, parallel paths, and cross-boundary risks BEFORE any code is written. Read-only; produces a Clear-for-Takeoff / Caution / Abort verdict with a risk matrix and an implementation plan. Run before starting a non-trivial or boundary-crossing change. NOT a code…