auroraview: Skill for Claude Code

.codebuddy/skills/e2e-self-iteration/SKILL.md

e2e-self-iteration is a skill for Claude Code, Codex from loonghao/auroraview. It costs 78 tokens per session (1,041 once invoked), scanned A, original, MIT.

A workflow for checking web interfaces with browser-based end-to-end tests and recorded visual evidence. End-to-end tests exercise an application through the user interface, while visual comparison checks whether its appearance changed unexpectedly.

In plain words
What is it for?
Use it to inspect interactive elements, capture screenshots or sessions, compare a page with a baseline, verify UI changes, and prepare proof for a code review.
Why use it?
It helps find broken interactions and visual regressions after interface changes. It also supports repeating the cycle of building, testing, fixing, and testing again.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is loonghao/auroraview's own configuration. It tells Claude Code and Codex how to work on auroraview itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything auroraview configures →

Reuse

Borrowing it

Nothing to install: this file belongs to loonghao/auroraview. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/loonghao/auroraview/main/.codebuddy/skills/e2e-self-iteration/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/loonghao/auroraview

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for e2e-self-iteration

README.md
[![agentmods](https://agentmods.dev/badge/skills/loonghao/auroraview/e2e-self-iteration/github.svg)](https://agentmods.dev/skills/loonghao/auroraview/e2e-self-iteration)
Your own site
<a href="https://agentmods.dev/skills/loonghao/auroraview/e2e-self-iteration"><img src="https://agentmods.dev/badge/skills/loonghao/auroraview/e2e-self-iteration/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for e2e-self-iteration

Your own site · 80×15
<a href="https://agentmods.dev/skills/loonghao/auroraview/e2e-self-iteration"><img src="https://agentmods.dev/badge/skills/loonghao/auroraview/e2e-self-iteration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,041 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.01041
Opus 5 $0.00039 $0.00521
Sonnet 5 $0.00016 $0.00208
Haiku 4.5 $0.00008 $0.00104

Measured 10d ago against content hash fa51eced947b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

e2e-self-iteration scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.codebuddy/skills/e2e-self-iteration/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

E2E Self-Iteration Skill

Combines ProofShot (visual proof recording) and agent-browser (headless browser control) with the self-improvement loop for automated E2E testing, visual regression detection, and iterative bug fixing.

Quick Reference

Situation Action
Need to verify UI changes vx just e2e-proofshot
Found visual regression Log to .learnings/ERRORS.md, fix, re-run
Self-iteration loop vx just e2e-iterate
PR needs proof vx just e2e-pr
Explore UI elements vx just e2e-snapshot
Compare against baseline vx just e2e-diff

Prerequisites

# Install ProofShot + agent-browser
vx just e2e-install

Workflows

1. Quick Visual Verification

After making UI changes, verify them visually:

vx just e2e-start          # Build + start Gallery with CDP
vx just e2e-snapshot        # See interactive elements
vx just e2e-screenshot      # Capture annotated screenshot
vx just e2e-stop            # Cleanup

2. Full ProofShot Session

Record a complete verification session with video + artifacts:

vx just e2e-proofshot       # Full automated flow

This will:

  1. Pack Gallery (debug mode)
  2. Start with CDP enabled
  3. Record ProofShot session
  4. Capture snapshots and screenshots
  5. Run Playwright CDP tests
  6. Stop and generate artifacts

3. Self-Iteration Loop

When fixing bugs or implementing features, iterate:

# Cycle: build → start → verify → fix → repeat
vx just e2e-iterate

# Review artifacts after each iteration
ls proofshot-artifacts/

4. agent-browser Primitives

Direct browser control commands:

# Element discovery
vx just e2e-snapshot

# Navigation
vx just e2e-open "http://localhost:5173/settings"

# Interaction
vx just e2e-click "@e5"
vx just e2e-fill "@e2" "test value"

# Screenshot
vx just e2e-screenshot

5. Visual Regression Testing

Compare current state against baseline:

vx just e2e-diff

Read the full file on GitHub · 162 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 162 lines · 78 tokens per session scan A fa51eced947b

Subscribe to this mod's changes

e2e-self-iteration is a skill published in the GitHub repository loonghao/auroraview (44 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 1,041 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

browse

Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).

garrytan/gstack · 32 tokens

playwright-cli

A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.

UnicomAI/wanwu · 76 tokens

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

anthropics/skills · 35 tokens

create-verification-skill

Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".

get-bb/bb · 57 tokens

browser-qa

A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.

hashgraph-online/awesome-codex-plugins · 58 tokens

test-electron-app

Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…

PostHog/posthog-foss · 112 tokens