fe-rail
claudeHarness dedicated to frontend projects. Supports Next.js App Router / Vite SPA + TypeScript, Tailwind v3/v4, shadcn/ui. Automates the spec→build→review→PR cycle.
5 skills · 15 agents · hooks
Change-aware Playwright E2E — runs only the specs a change can reach (widening to a full run whenever unsure), records every run against a code fingerprint so a stale green is never reused, and shards by measured durations. An autopilot skill and hooks run that flow after a code change. The plugin puts the CLI on PATH (personal mode, nothing in the repo), or a team pins it in the repo (pnpm add -D github:sh5623/e2e-rail#v0.4.3).
Plugin e2e-rail from marketplace guardrail in sh5623/guardrail. Commands read from the repo's manifest — 9 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
autopilotUse when you changed source or test code in a repository set up for e2e-rail (an e2e-rail.config.mjs at the root, or a personal one `e2e-rail status` finds) and are about to report the work as done, commit or hand it off, without the user naming E2E or this skill; and when the e2e-rail Stop hook say
gateUse when E2E tests must run and their result be reported — after select, before a commit, merge or handoff, before any "E2E passes" claim, or when asked "did the E2E pass?" or "is this already tested?". Runs the suite through the e2e-rail CLI (machine lock + ledger), verifies the result against the
initUse when a repository with Playwright E2E tests does not use e2e-rail yet (no e2e-rail.config.mjs, or `e2e-rail` is missing), or when its config needs review after adding an app, a route table, a monorepo package or a new tsconfig. Installs the CLI, writes the config, checks how well specs map to so
measureUse when the E2E suite feels slow or flaky — long gate times, timeouts, retries, picking a worker count, or deciding whether and how to shard across CI jobs. Reads durations and retry rates from the e2e-rail ledger, separates where a slow spec spends its time, compares worker counts on this machine
selectUse when a code change needs its E2E scope decided — before running Playwright on a branch, worktree or PR, or when asked "which E2E specs does this change need?". Computes the selection with the e2e-rail CLI, checks the couplings the script cannot see, and produces the selection block (change · sel
shadowUse when a round ends, after the integration step's full E2E run, or when asked whether selected runs can be trusted to replace full runs. Pairs the full run with the selection computed for the same code, records hit or miss with the e2e-rail CLI, reports the streak and puts promotion (or demotion)
e2e-impact-analystREAD-ONLY. Given a diff and .e2e-rail/selection.json, finds couplings the static graph cannot see (modal openers, deep links, string-literal navigation, runtime-registered routes, import.meta.glob, shared fixtures, mobile-only branches) and returns `--add` candidates with one-sentence reasons. Never
cat "${CLAUDE_PLUGIN_ROOT}/hooks/doctrine.md"
node "${CLAUDE_PLUGIN_ROOT}/bin/e2e-rail.mjs" hook turn-start
node "${CLAUDE_PLUGIN_ROOT}/bin/e2e-rail.mjs" hook stop
node "${CLAUDE_PLUGIN_ROOT}/bin/e2e-rail.mjs" hook post-bash
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.
5 skills · 15 agents · hooks
Conventions that fix themselves — evidence-gated convention repair loop plus a budget/archive system for bloated rule docs. Stack-agnostic (FE/BE/scripts/docs).
3 skills · 1 agent · hooks
Run subagents in parallel across isolated git worktrees and harvest the finished ones upstream — bootstrap, dispatch, harvest, and the failure modes a green gate cannot see. Harness- and stack-agnostic.
1 skill
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
Long-term semantic memory for Claude Code, powered by OpenViking
5 skills · 1 command · 1 MCP server · hooks
Connect providers and targets, write eval suites, and set up or run red team scans with promptfoo
4 skills
Automates browser interactions for web testing, form filling, screenshots, and data extraction
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.