Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By forsonny
Opinionated developer-session workflow plugin. Encodes a deterministic pipeline from first message to merged branch as skills that hand off to each other in a fixed order.
npx claudepluginhub forsonny/leyline --plugin leylineThis directory holds specialized subagent definitions dispatched by stage-7 review skills.
Senior Code Reviewer. Dispatched by requesting-code-review for branch-level review, and by subagent-driven-development's code-quality-reviewer-prompt.md for per-task review. Reviews a diff against plan alignment, quality, architecture, docs, and security. Returns findings categorized Critical / Important / Suggestions.
Senior Experience Reviewer. Dispatched by requesting-design-review for branch-level review, and by subagent-driven-development's design-quality-reviewer-prompt.md for per-task review. Reviews surfaces against the UX spec, flows, states, accessibility, voice, and platform conventions. Harness-aware; falls back to structural review when tools absent.
Use whenever you are about to claim a user-facing surface is complete - before committing, before marking the task done, before any success claim. Requires running an accessibility check fresh in the current message and reading its output before any completion claim. An overlay during stage 5 alongside verification-before-completion.
Use when the human partner asks to build, add, change, or modify anything (features, components, functionality, behavior). Explores intent, requirements, and design before implementation. Hard-gated; nothing implements until the human partner approves the written product spec.
Use after the product spec is approved, before any implementation work. Pressure-tests the spec with a 100-question self-interrogation where each question builds on the previous answer. Returns critical issues, strengths, and a revised proposal. Material revisions loop back to brainstorming.
Use when the approved product spec touches any user-facing surface, before any implementation skill runs on that surface. Explores flows, states, accessibility, and voice. Hard-gated; nothing implements until the human partner approves the written UX spec.
Use when implementing any task whose "Files:" block touches a user-facing surface, before writing the code for that surface. Enforces the DRAW-BUILD-RECONCILE cycle: the UX artifact is the source of truth, the implementation instantiates it, and any divergence is resolved explicitly. An overlay during stage 5 alongside test-driven-development.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Harness-native ECC plugin for engineering teams - 64 agents, 262 skills, 84 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Complete writing system for epic fantasy novels using the Crucible Structure—a 36-beat narrative framework with three interwoven story strands. Includes planning, outlining, prose writing with bi-chapter reviews, and editing.
Massively Decomposed Agentic Processes (MAD) - Break complex tasks into atomic steps with near-zero errors
An opinionated developer-session workflow plugin for Claude Code, Cursor, Codex, OpenCode, GitHub Copilot CLI, and Gemini CLI.
Leyline encodes one coherent developer session from first message to merged branch as a deterministic pipeline of skills that hand off to each other in a fixed order. Every stage has an entry gate, a verifiable output, and an explicit successor. No stage silently skips. No completion claim ships without evidence. The iron laws are enforced at every handoff.
Before any response or action - including clarifying questions - check whether any Leyline skill applies. If one does (probability >= 1%), invoke it before narrating. If none does, name the skills you considered and why you rejected each.
This rule is the single highest-leverage instruction Leyline ships. It appears verbatim in CLAUDE.md, AGENTS.md, GEMINI.md, and skills/using-leyline/SKILL.md so every load path delivers it to the agent. Drift between files is caught by scripts/check-manifests.sh.
writing-skills enforces TDD-for-prose: baseline pressure test, write minimal rebuttal, verify, refactor. Every skill change requires traces.Human partner: "let's build X"
|
v
[1] Discovery ........... brainstorming + design-brainstorming
| approved product + UX specs
v
[2] Interrogate ......... deep-discovery + design-interrogation
| 100-question pressure tests; loop back on material revisions
v
[3] Isolate ............. using-git-worktrees
| isolated branch workspace, green baseline
v
[4] Plan ................ writing-plans
| 2-to-5-minute tasks with exact paths, code, verification
v
[5] Execute ............. subagent-driven-development OR executing-plans
| fresh subagent per task + up to 4 review passes
v <-- governed by [6] Discipline overlays:
| Code: TDD, systematic-debugging, verification-before-completion
| Experience: design-driven-development, accessibility-verification
v
[7] Review .............. requesting/receiving-code-review (+ design when surfaces)
| code-reviewer and design-reviewer subagents
v
[8] Finish .............. finishing-a-development-branch
| merge / PR / keep / discard
v
Pipeline terminates with evidence trail in docs/leyline/
Install commands for each supported harness. All paths resolve against github.com/forsonny/leyline.
/plugin marketplace add forsonny/leyline
/plugin install leyline@leyline-marketplace
The first command registers this repo as a marketplace via .claude-plugin/marketplace.json. The second installs the plugin it lists.
Cursor consumes Claude Code-compatible plugins. Use the same marketplace add-and-install flow in Cursor's plugin interface, pointing at https://github.com/forsonny/leyline.
copilot plugin marketplace add https://github.com/forsonny/leyline
copilot plugin install leyline
gemini extensions install https://github.com/forsonny/leyline
codex plugin marketplace add forsonny/leyline