Add fe-rail to Development Engineering

.claude-plugin/marketplace.json

@@ -897,6 +897,26 @@
         "subagent"
       ]
     },
+    {
+      "name": "fe-rail",
+      "source": "./plugins/fe-rail",
+      "description": "Harness dedicated to frontend projects. Supports Next.js App Router / Vite SPA + TypeScript, Tailwind v3/v4, shadcn/ui. Automates the spec→build→review→PR cycle.",
+      "version": "1.14.1",
+      "author": {
+        "name": "Seungho",
+        "email": "seungho5623@gmail.com"
+      },
+      "category": "Development Engineering",
+      "homepage": "https://github.com/ccplugins/awesome-claude-code-plugins/tree/main/plugins/fe-rail",
+      "keywords": [
+        "frontend",
+        "nextjs",
+        "vite",
+        "typescript",
+        "harness",
+        "workflow"
+      ]
+    },
     {
       "name": "enterprise-onboarding-specialist",
       "source": "./plugins/enterprise-onboarding-specialist",
@@ -1672,4 +1692,4 @@
       ]
     }
   ]
-}
+}

README.md

@@ -123,6 +123,7 @@ Install or disable them dynamically with the `/plugin` command — enabling you
 - [code-architect](./plugins/code-architect)
 - [desktop-app-dev](./plugins/desktop-app-dev)
 - [enterprise-integrator-architect](./plugins/enterprise-integrator-architect)
+- [fe-rail](./plugins/fe-rail)
 - [flutter-mobile-app-dev](./plugins/flutter-mobile-app-dev)
 - [frontend-developer](./plugins/frontend-developer)
 - [mobile-app-builder](./plugins/mobile-app-builder)

plugins/fe-rail/.claude-plugin/marketplace.json

@@ -0,0 +1,20 @@
+{
+  "name": "fe-rail-market",
+  "description": "Claude Code plugin marketplace for frontend projects — fe-rail",
+  "owner": {
+    "name": "Seungho",
+    "email": "seungho5623@gmail.com"
+  },
+  "plugins": [
+    {
+      "name": "fe-rail",
+      "description": "Harness dedicated to frontend projects. Supports Next.js App Router / Vite SPA + TypeScript, Tailwind v3/v4, shadcn/ui. Automates the spec→build→review→PR cycle.",
+      "category": "engineering",
+      "tags": ["frontend", "nextjs", "typescript", "harness", "workflow"],
+      "source": {
+        "source": "github",
+        "repo": "sh5623/fe-rail"
+      }
+    }
+  ]
+}

plugins/fe-rail/.claude-plugin/plugin.json

@@ -0,0 +1,12 @@
+{
+  "name": "fe-rail",
+  "description": "Harness dedicated to frontend projects. Supports Next.js App Router / Vite SPA + TypeScript, Tailwind v3/v4, shadcn/ui. Automates the spec→build→review→PR cycle.",
+  "version": "1.14.1",
+  "author": {
+    "name": "Seungho",
+    "email": "seungho5623@gmail.com"
+  },
+  "homepage": "https://github.com/sh5623/fe-rail",
+  "repository": "https://github.com/sh5623/fe-rail",
+  "license": "MIT"
+}

plugins/fe-rail/.github/CODE_OF_CONDUCT.md

@@ -0,0 +1,67 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, caste, color, religion, or sexual
+identity and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment:
+
+- Demonstrating empathy and kindness toward other people
+- Being respectful of differing opinions, viewpoints, and experiences
+- Giving and gracefully accepting constructive feedback
+- Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+- Focusing on what is best not just for us as individuals, but for the overall
+  community
+
+Examples of unacceptable behavior:
+
+- The use of sexualized language or imagery, and sexual attention or advances
+  of any kind
+- Trolling, insulting or derogatory comments, and personal or political attacks
+- Public or private harassment
+- Publishing others' private information, such as a physical or email address,
+  without their explicit permission
+- Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Project maintainers are responsible for clarifying and enforcing our standards
+of acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior they deem inappropriate, threatening, offensive, or
+harmful.
+
+## Scope
+
+This Code of Conduct applies within all community spaces (issues, pull
+requests, discussions) and also applies when an individual is officially
+representing the community in public spaces.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the maintainer at **seungho5623@gmail.com**. All complaints will
+be reviewed and investigated promptly and fairly.
+
+All maintainers are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.1, available at
+[https://www.contributor-covenant.org/version/2/1/code_of_conduct.html][v2.1].
+
+[homepage]: https://www.contributor-covenant.org
+[v2.1]: https://www.contributor-covenant.org/version/2/1/code_of_conduct.html

plugins/fe-rail/.github/CONTRIBUTING.md

@@ -0,0 +1,76 @@
+# Contributing to fe-rail
+
+Thanks for considering a contribution. `fe-rail` is a Claude Code plugin (harness) for
+frontend projects — not an application itself. Changes here affect every consumer project
+that installs the plugin, so please read this before opening a PR.
+
+## Before you start
+
+- Skim `CLAUDE.md` for the harness architecture (agents / hooks / skills layers) and the
+  model-tier policy.
+- Check open issues and PRs first to avoid duplicate work.
+- For anything non-trivial (new agent, new hook, changed workflow), open an issue to
+  discuss the approach before writing code.
+
+## Development setup
+
+```bash
+git clone https://github.com/sh5623/fe-rail
+cd fe-rail
+```
+
+There's no build step — agents/skills/hooks are plain Markdown + shell. Install the
+plugin locally in a test project to exercise changes end to end:
+
+```bash
+/plugin marketplace add /path/to/your/local/fe-rail
+/plugin install fe-rail@fe-rail-market
+```
+
+Hooks only load at session start — restart your Claude Code session after installing
+or editing a hook for the change to take effect.
+
+## Testing your change
+
+Run the deterministic regression suite before opening a PR — it checks hook behavior,
+profile toggles, and self-lint (agent model aliases, skill frontmatter, `hooks.json`
+integrity):
+
+```bash
+bash eval/run.sh
+```
+
+A failing run blocks the PR. If you added a new hook or agent, extend `eval/run.sh`
+with coverage for it.
+
+## Making changes
+
+- **Agents** (`agents/*.md`): keep `model` as an alias (`opus`/`sonnet`/`haiku`), never
+  a pinned version. Respect the tier policy in `CLAUDE.md` — don't upgrade an agent to
+  `opus` without a judgment/gate justification.
+- **Hooks** (`hooks/`): blocking hooks (exit 2) must have a clear, low-false-positive
+  trigger. Prefer warning (stderr) over blocking when uncertain. Wire new hooks into
+  `hooks/hooks.json` and the profile logic in `hooks/scripts/profile-lib.sh`.
+- **Skills** (`skills/*/SKILL.md`): keep `allowed-tools` scoped to what the skill
+  actually needs. If a skill delegates to sub-agents, its `allowed-tools` must include
+  `Task`/`Agent`.
+- **Docs**: `README.md` is the canonical (English) doc; keep `README.ko.md` in sync.
+  `CLAUDE.md` targets the agent, not humans — update both when behavior changes.
+
+## Commit / PR style
+
+- Conventional-ish prefixes are used in this repo's history (`fix:`, `feat:`, `chore:`,
+  `docs:`) — follow the existing log (`git log --oneline`) for tone.
+- Keep PRs scoped to one concern. Don't bundle unrelated agent/hook/doc changes.
+- Fill out the PR template checklist, including the `eval/run.sh` result.
+
+## Reporting bugs / requesting features
+
+Use the issue templates (Bug report / Feature request). Include which consumer project
+type you're testing against (Next.js App Router, Vite + TanStack Router, Vite + React
+Router 7, monorepo) — behavior is framework-detected and can diverge.
+
+## Code of Conduct
+
+This project follows the [Contributor Covenant](CODE_OF_CONDUCT.md). By participating
+you agree to abide by it.

plugins/fe-rail/.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,54 @@
+---
+name: Bug report
+about: Something in the harness (agent, hook, skill) isn't behaving as documented
+title: "[Bug] "
+labels: bug
+assignees: ''
+---
+
+## Describe the bug
+
+A clear description of what went wrong (e.g. a hook blocked something it shouldn't
+have, an agent used the wrong model tier, a skill failed to trigger).
+
+## Which layer is affected?
+
+- [ ] Agent (which one: )
+- [ ] Hook (which one: )
+- [ ] Skill (which one: )
+- [ ] Docs (CLAUDE.md / README)
+
+## Consumer project type
+
+- [ ] Next.js App Router
+- [ ] Vite + React (TanStack Router)
+- [ ] Vite + React (React Router 7)
+- [ ] Monorepo
+- [ ] Other:
+
+## Steps to reproduce
+
+1.
+2.
+3.
+
+## Expected behavior
+
+What you expected to happen.
+
+## Actual behavior
+
+What actually happened. Paste relevant stderr/stdout from the hook or agent output if
+available.
+
+## Environment
+
+- fe-rail version:
+- Claude Code version:
+- OS:
+- Package manager (npm/pnpm/yarn/bun):
+
+## Additional context
+
+`FE_RAIL_HOOK_PROFILE` / `FE_RAIL_DISABLED_HOOKS` values if non-default, and anything
+else relevant.

plugins/fe-rail/.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,40 @@
+---
+name: Feature request
+about: Suggest a new agent, hook, skill, or workflow improvement
+title: "[Feature] "
+labels: enhancement
+assignees: ''
+---
+
+## Problem
+
+What's missing or painful in the current spec → build → review → PR workflow? Describe
+the gap, not the solution yet.
+
+## Proposed solution
+
+What you'd like to see added or changed. If this maps to a specific harness layer,
+say which:
+
+- [ ] New agent
+- [ ] New/changed hook
+- [ ] New/changed skill
+- [ ] Workflow change (e.g. `fe-start` sequencing)
+- [ ] MCP integration
+- [ ] Other:
+
+## Alternatives considered
+
+Any other approaches you thought about, and why you didn't go with them.
+
+## Consumer project type this targets
+
+- [ ] Next.js App Router
+- [ ] Vite + React (TanStack Router)
+- [ ] Vite + React (React Router 7)
+- [ ] Monorepo
+- [ ] Framework-agnostic
+
+## Additional context
+
+Links, examples, or references (e.g. a similar pattern in another Claude Code plugin).

plugins/fe-rail/.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,35 @@
+## Summary
+
+What does this PR change and why? (1-3 bullets)
+
+-
+
+## Layer(s) touched
+
+- [ ] Agent (`agents/*.md`)
+- [ ] Hook (`hooks/*.sh`, `hooks/hooks.json`)
+- [ ] Skill (`skills/*/SKILL.md`)
+- [ ] Docs (`CLAUDE.md`, `docs/*.md`, `README*.md`)
+- [ ] Eval (`eval/run.sh`)
+
+## Checklist
+
+- [ ] `bash eval/run.sh` passes (hook behavior, profile toggles, self-lint)
+- [ ] Agent `model` fields use aliases (`opus`/`sonnet`/`haiku`), not pinned versions
+- [ ] New/changed hooks are wired into `hooks/hooks.json` and, if blocking, justified
+      (low false-positive trigger — see `CLAUDE.md` hook profile policy)
+- [ ] Skill `allowed-tools` stays scoped to what the skill needs (includes `Task`/`Agent`
+      only if it delegates)
+- [ ] `README.md` and `README.ko.md` updated together if user-facing behavior changed
+- [ ] `CLAUDE.md` updated if agent/hook/skill structure changed
+- [ ] `.claude-plugin/plugin.json` version bumped if this PR changes agent/hook/skill
+      runtime behavior (so consumers detect the update) — not needed for docs-only changes
+
+## Test plan
+
+How did you verify this? (e.g. installed in a local test project, ran a specific
+workflow end to end, `eval/run.sh` output)
+
+## Related issue
+
+Closes #

plugins/fe-rail/.gitignore

@@ -0,0 +1,3 @@
+.claude/
+
+.DS_Store