497 tagged spec-driven-development, measured the same way as everything else here.
Browse within: context-engineering 149meta-prompting 113github-copilot 56spec-kit 43spec-driven 42copilot-coding-agent 41openai-codex 33claude-code-hooks 30workflow 30vscode-extension 27sdd 21ai-skills 19bmad-method 19copilot-chat 13
SufficientDaikon/sdd-vscode-agents
Agent
Spec-Driven Development agent that takes a comprehensive specification and implements it faithfully, section by section. Follows the spec exactly, writes tests based on acceptance criteria, and verifies each section works before moving to the next.
SufficientDaikon/sdd-vscode-agents
Agent
UI Design agent that creates beautiful, production-grade visual designs including design tokens, component libraries, hero sections, and high-fidelity page designs.
andreaserradev-gbj/dev-workflow
Agent
Design implementation structure for PRD.
andreaserradev-gbj/dev-workflow
Agent
Research codebase to populate PRD's Research Findings section.
andreaserradev-gbj/dev-workflow
Agent
Compares a feature's PRD against the actual implementation and produces a concise, scannable alignment report — tables and bullets, architect-level, no wall of prose. Read-only codebase exploration.
Agent
Use this agent for business requirements gathering, stakeholder analysis, business case development, and creating BRD documents. Focuses on practical, implementable business requirements. Context: Starting discovery phase for a new product user: "/peachflow:discover online marketplace for handmade goods" assistant…
Agent
Use this agent for analyzing existing codebases to onboard them to peachflow. Performs reverse-discovery by extracting business context, architecture, and requirements from implemented code. Context: Onboarding an existing project user: "/peachflow:analyze" assistant: "I'll invoke codebase-analyst to analyze the…
Agent
Use this agent for system architecture design, technology decisions (ADRs), high-level design documents, and technical feasibility assessment. Context: Need to make a technology decision user: "Should we use PostgreSQL or MongoDB?" assistant: "Let me have software-architect analyze the options and create an ADR."…
Agent
Cross-artifact consistency audit - finds specs with no covering plan, plans chasing stale specs and spec/code divergence. Read-only; reports findings, changes nothing.
Agent
Investigates libraries, APIs, and implementation approaches. Provides recommendations with tradeoffs for the builder agent.
Agent
Checks that .director/ documentation matches the current codebase state. Updates docs that have drifted. Only modifies files in .director/.
Agent
Reads analysis files from parallel agents and synthesizes them into a cohesive summary. Works in two modes: research synthesis (from deep researchers) and codebase synthesis (from deep mappers).
Agent Claude Code
Claude Code plugin development specialist. Knows plugin structure, official docs, and marketplace best practices.
Agent
Shaping agent that turns vague problems into structured pitches. Use when a user wants to start a new feature, has a vague idea, says 'what should we build', 'I have a problem with X', 'shape this idea', 'start a feature', or needs to clarify what to build before the LSA build cycle. Adapts its domain-expert role per…
Agent
Roadmap steward that recommends what to work on next, decomposes pitches into epics, and tidies roadmap hygiene. Use when a user asks about roadmap, what to work on next, project status, what's in flight, sequence the backlog, decompose this pitch, break down this feature, what's blocked, show me the backlog…
Agent
Migration fact-finder. Spawn only in projects with a migration config (.specseal/parity.md) to establish what the original code actually does — facts with coordinates, no verdicts. Called by smith during implementation and by the review orchestrator during parity review.
Agent
Implementation agent. Spawn for feature work, ticket implementation, refactors, and incorporating review feedback. Follows the implement skill (SDD procedure, three-axis document layout); hands finished work to the review chain.
Agent
Review agent. Spawn to review a PR, diff, or branch — spec compliance first, then quality. Reads earlier review rounds and inherits their verdicts; returns a report for the orchestrator to verify and post.
Agent
Implements exactly one mstack work item, writes the tests that prove it, and records the requirement-to-test map. Never marks its own work approved or done.
Agent
Independently reviews one mstack implementation against its requirements, its tests and the real diff. Runs the verification itself. Returns APPROVED or CHANGESREQUESTED and never edits the code.
Agent
Writes the spec for one item under the mstack spec path. Produces proposal, design, tasks and requirements with stable R-ids, then hands off. Never reviews its own spec.
Agent
Applies fixes to code review findings from REVIEW.md. Reads source files, applies intelligent fixes, and commits each fix atomically. Spawned by /gsd-code-review-fix.
Agent
Reviews source files for bugs, security issues, and code quality problems. Produces structured REVIEW.md with severity-classified findings. Spawned by /gsd-code-review.
Agent
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.