ByeongminLee

60 mods across 1 repository, 3 stars between them.

planner

49

ByeongminLee/nextjs-claude-code

Agent Claude Code

Reads feature spec/design docs, creates PLAN.md and CONTEXT.md inside the feature directory, then spawns the lead-engineer agent after user confirmation. Invoked by the /dev skill. Supports solo mode (default) and team mode (/dev --team) with domain analysis and task tagging.

3 5mo ago A 61 tokens original MIT

pr-creator

50

ByeongminLee/nextjs-claude-code

Agent Claude Code

Creates a pull request with auto-generated body from feature spec. Handles branch strategy-aware target selection, changelog updates, and version bumping. Invoked by the /pr skill.

3 5mo ago A 40 tokens original MIT

ByeongminLee/nextjs-claude-code

Agent Claude Code

Orchestrates the /reforge legacy-to-spec transformation pipeline. 5 phases — deep analysis of legacy codebase, change specification (Q&A), delta analysis, spec generation, validation & handoff. Reads legacy folder (read-only), writes to spec/reforge/[name]/ and spec/feature/[name]/. Invoked by the /reforge skill.

3 5mo ago C 79 tokens original MIT

ByeongminLee/nextjs-claude-code

Agent Claude Code

Generates standard NCC spec.md + design.md for a single feature by blending legacy analysis with requested changes. Reads reforge documents (ANALYSIS.md, CHANGES.md, DELTA.md) and target project context. Invoked by reforge-orchestrator during Phase 4.

3 5mo ago A 62 tokens original MIT

reviewer

53

ByeongminLee/nextjs-claude-code

Agent Claude Code

Compares implemented code against spec.md requirements and project rules. Produces a compliance report showing which requirements are met, partial, or missing. Does not modify code. Called as part of the /review skill (paired with code-quality-reviewer).

3 5mo ago A 52 tokens original MIT

rule-writer

54

ByeongminLee/nextjs-claude-code

Agent Claude Code

Creates or updates project coding rules in spec/rules/. Each rule is a separate markdown file. Never modifies source code or spec/rules/workflow.md. Invoked by the /rule skill.

3 5mo ago A 43 tokens original MIT

security-reviewer

55

ByeongminLee/nextjs-claude-code

Agent Claude Code

Audits code for security vulnerabilities against SECURITYSTRATEGY.md. Checks OWASP Top 10, secrets, injection, auth gaps, data exposure. Invoked by /security or conditionally by /review.

3 5mo ago A 46 tokens original MIT

spec-writer

56

ByeongminLee/nextjs-claude-code

Agent Claude Code

Writes or updates feature spec.md and design.md files for Next.js/React projects. Clarifies missing information before writing. Never modifies source code. Invoked by the /spec skill.

3 5mo ago A 41 tokens original MIT

status

57

ByeongminLee/nextjs-claude-code

Agent Claude Code

Reads spec/STATE.md to output a concise project status summary. Shows all tracked features with their phases, reads each feature's PLAN.md for task progress, and lists completed items and blockers. Does not modify any files. Invoked by the /status skill.

3 5mo ago A 54 tokens original MIT

task-executor

58

ByeongminLee/nextjs-claude-code

Agent Claude Code

Fresh-context subagent for [lead] domain tasks (types, utilities, hooks, API routes, server actions, page wiring, configuration, mocks). Spawned by lead-engineer orchestrator with a clean context window per task, preventing context rot. For [db]/[ui] tasks, the orchestrator spawns db-engineer/ui-engineer instead.

3 5mo ago A 76 tokens original MIT

tester

59

ByeongminLee/nextjs-claude-code

Agent Claude Code

Executes tests based on TESTSTRATEGY.md and feature-level TEST.md. Runs unit/integration tests via test runner, reports results, and updates TEST.md checklists. In TDD mode, generates TEST.md skeletons during /spec. In post-dev mode, generates TEST.md and test code after /dev completion.

3 5mo ago A 67 tokens original MIT

ui-engineer

60

ByeongminLee/nextjs-claude-code

Agent Claude Code

UI implementation engineer. Handles components, styling, animations, responsive design, and visual polish. Uses Figma MCP when available. Spawned per [ui] task as a fresh-context subagent (solo mode) or team member (team mode).

3 5mo ago A 53 tokens original MIT