spec-driven-development agents

shoootyou/get-shit-done-multi

Agent

Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.

shoootyou/get-shit-done-multi

Agent

Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by {{COMMANDPREFIX}}new-project or {{COMMANDPREFIX}}new-milestone orchestrators.

jsegov/shipspec-claude-code-plugin

Agent

Use this agent to verify task implementation aligns with SDD design and PRD requirements. Examples.

jsegov/shipspec-claude-code-plugin

Agent

Use this agent to manage task lifecycle operations on TASKS.json files. Examples.

jsegov/shipspec-claude-code-plugin

Agent

Use this agent for task decomposition and planning. Examples.

dinhnguyenngoc/spec-driven-claude-code

Agent Claude Code

Requirements engineer who elicits, analyzes, and documents what to build and why.

dinhnguyenngoc/spec-driven-claude-code

Agent Claude Code

Expert frontend developer specializing in Next.js, React, TypeScript, and modern UI development.

dinhnguyenngoc/spec-driven-claude-code

Agent Claude Code

Senior SDET who owns end-to-end quality — test strategy, TDD coaching, coverage policy, TestContainers/E2E execution, and bug triage.

jumppad-labs/spektacular

Agent

When you have drafted substantial content for the user to review — an architecture write-up, a set of options, a written section, a summary, a plan or spec excerpt — always present that draft as normal, readable chat text first, in full. Never embed the draft itself inside a structured yes/no or multiple-choice dialog…

jumppad-labs/spektacular

Agent

In this repository, treat every file under .spektacular/specs/ and .spektacular/plans/ as a historical, archaeological record. Each one describes the intent behind a past change — why something was proposed, what was in scope at that moment, and how the author framed the problem. None of them are a description of what…

jumppad-labs/spektacular

Agent

While working — debugging, reading code to understand how something works, making a non-obvious choice — watch for the moment you surface something durable and non-obvious: a convention inferred from code that isn't written down anywhere, a gotcha hit while debugging, the reasoning behind a choice that wasn't the…

pilotspace/ADD

Agent Claude Code

The ADD advisor — the roster's second mind, serving EVERY beat (direction · build · verify). Spawned by add-worker (or the skill orchestrator) to PROPOSE a plan before a beat, PRESSURE-TEST a drafted bundle, or DECIDE a delegable ambiguity so the worker never stalls. Loads the best-fit advisory persona and reasons…

pilotspace/ADD

Agent Claude Code

The ADD execution shell — ONE agent for every EXECUTION beat of the loop. The spawn prompt names the beat (direction · build · verify) or the persona service mode; the agent loads that beat's phase guide plus the best-fit persona and becomes the specialist. Personas carry the expertise; this agent carries the…

joanseg/specmanager

Agent

Designs the actual screens for a SpecManager feature as a single self-contained HTML file — high-fidelity, stacked mockups grounded in ./docs/DESIGN.md, with formatted explanatory notes between each screen. Writes via the createdesignbrief MCP tool.

joanseg/specmanager

Agent

Drafts the execution Plan (plan.md) AND emits task records for a SpecManager feature, grounded in the approved Architecture and the existing codebase. Plans MUST be organised into phases with Fibonacci-scored tasks ≤3.

joanseg/specmanager

Agent

Writes a per-phase Walkthrough document for a SpecManager feature, or — in phase: "final" mode — a feature-level roll-up that links each phase walkthrough.

DanielHashmi/Q4_learning

Agent

Implements the smallest safe fix for Project 4 and verifies it.

DanielHashmi/Q4_learning

Agent

Strict read-only checker for Project 4 fix candidates.

sighup/claude-workflow

Agent

Coding worker that executes tasks using the 11-step protocol. Use to implement a specific task from the task board with atomic commits and proof artifacts.

sighup/claude-workflow

Agent

Read-only verification child that independently re-runs a task's proof commands and post-verification checks, returning a structured per-proof PASS/FAIL verdict. Use from cw-execute Steps 6 and 9 to gate task completion on observed results instead of the implementer's self-report.

sighup/claude-workflow

Agent

Code reviewer that examines files for bugs, security issues, and spec compliance. Operates in two modes: file-partitioned (cw-review) or concern-partitioned (cw-review-team).

firatcand/forge

Agent

General-purpose code reviewer. Reviews diffs against CLAUDE.md conventions and best practices. Invoked by /review.

firatcand/forge

Agent

Authors the compound learning store. Invoked by /learn (write). Retrieval (the old /pickup-task read flow) is now Loom — forge loom recall (FORGE-200).

firatcand/forge

Agent

Specialist for tracker synchronization. Invoked by /push-to-tracker and /sync-status. Dispatches per .forge/settings.yaml tracker.type (linear|github|notion).