e2e-debug

e2e-debug is a skill for Claude Code from YoungjaeDev/my-claude-plugins. It costs 202 tokens per session (2,146 once invoked), scanned A, original, MIT.

A workflow for investigating and repairing failed or unreliable Playwright end-to-end tests, which test complete user journeys in a browser. It retrieves CI trace files, examines what happened, and uses a healer role to repair the test or quarantine it honestly.

In plain words
What is it for?
Use it to debug failed CI runs, broken pull-request tests, flaky browser tests, and Playwright suites that need repair.
Why use it?
It turns a failed automated test into an evidence-based diagnosis instead of requiring someone to reproduce the failure manually. A trace is a recorded run that shows the browser's actions and state.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the dev plugin — 12 skills, 3 agents shipped together

Good fit Use it to debug failed CI runs, broken pull-request tests, flaky browser tests, and Playwright suites that need repair.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add YoungjaeDev/my-claude-plugins
Claude Code
/plugin install dev

Made for: Claude Code.

Or install dev, the plugin that ships this one along with the rest of its 12 skills, 3 agents.

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-debug

README.md
[![agentmods](https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/e2e-debug/github.svg)](https://agentmods.dev/skills/youngjaedev/my-claude-plugins/e2e-debug)
Your own site
<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/e2e-debug"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/e2e-debug/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-debug

Your own site · 80×15
<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/e2e-debug"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/e2e-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 202 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,146 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.
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 $0.00202 $0.02146
Opus 5.5 $0.00081 $0.00858
Sonnet 5.5 $0.00040 $0.00429
Haiku 4.5 $0.00020 $0.00215

Measured 13d ago against content hash 860a58e79a08, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

e2e-debug 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 13d 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.

plugins/dev/skills/e2e-debug/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

E2E Debug: trace analysis + healer (close the loop)

The third leg of the harness. A CI failure is a sensor reading; this skill turns it back into a green test (or an honest quarantine), closing the planner -> generator -> healer self-improving loop.

Two runtime families, three execution paths, same bounded loop: on Claude Code the healer is the named agent playwright-test-healer that e2e-setup generated (Path A); on Codex that agent file is not registerable, so the healer runs as a generic subagent carrying the bundled contract from references/role-contracts.md (Path B), or in-agent sequentially when no delegation is available (Path C).

The headless npx playwright trace CLI exists only in newer Playwright releases; probe for it (Precondition check) instead of trusting a version number. On Path A, npx playwright trace install-skill installs Playwright's own agent skill for it (it writes to .claude/skills/ only, so it does nothing for Codex). The GUI viewer npx playwright show-trace <trace.zip> is also available if a human wants to look.

Precondition check

  • Need gh CLI authenticated to fetch CI artifacts.
  • Path A only: confirm the named healer exists (.claude/agents/playwright-test-healer.md). If missing and you are on Claude Code, route to dev:e2e-setup. Do not demand this Claude agent file under Codex; there the bundled healer contract stands in (see Step 0).
  • Probe the headless trace CLI used in Step 2: run npx playwright trace --help and check that it printed the trace subcommand's own usage, not the top-level help (an unknown subcommand can answer with the top-level help and exit 0). When it is missing: fall back to the GUI viewer npx playwright show-trace <trace.zip>.

Workflow

  1. Resolve the plugin root + pick the execution path: run once. The resolver reaches the bundled healer contract on Path B/C; the path decision governs Step 3. Tell the user which path you took in one sentence.
    # Claude exports CLAUDE_PLUGIN_ROOT; Codex does not. Each branch verifies
    # the target (CHK) exists before committing, so a stale env falls through.
    CHK="references/role-contracts.md"
    PLUGIN_ROOT=""
    [ -n "${CLAUDE_PLUGIN_ROOT:-}" ] && [ -e "$CLAUDE_PLUGIN_ROOT/$CHK" ] && PLUGIN_ROOT="$CLAUDE_PLUGIN_ROOT"
    [ -z "$PLUGIN_ROOT" ] && [ -e "plugins/dev/$CHK" ] && PLUGIN_ROOT="plugins/dev"
    if [ -z "$PLUGIN_ROOT" ]; then
      cache_root="${CODEX_PLUGIN_CACHE:-$HOME/.codex/plugins/cache}"
      while IFS= read -r d; do
        [ -e "$d/$CHK" ] && { PLUGIN_ROOT="$d"; break; }
      done < <(ls -1d "$cache_root"/*/dev/*/ 2>/dev/null | awk -F/ '{print $(NF-1)"\t"$(0)}' | sort -t. -k1,1rn -k2,2rn -k3,3rn | cut -f2- | sed 's#/$##')
    fi
    { [ -n "$PLUGIN_ROOT" ] && [ -e "$PLUGIN_ROOT/$CHK" ]; } || { echo "e2e-debug: role contracts not resolved (need $CHK)" >&2; exit 1; }
    echo "PLUGIN_ROOT=$PLUGIN_ROOT"
    
    • Path A: named playwright-test-healer is registered (Claude Code). Dispatch it by name (Step 3, unchanged).
    • Path B: named agent not registerable but a generic subagent tool is available (Agent). Dispatch a generic subagent carrying the healer contract from ${PLUGIN_ROOT}/references/role-contracts.md inline.
    • Path C: no delegation available. Run the healer role yourself per the same contract.

Read the full file on GitHub · 92 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. 13d ago Changed 860a58e79a08
  2. 23d ago Changed 5e154fbd06af
  3. 25d ago Changed fbdb49f7b57d
  4. 1mo ago Changed · +42 tokens per session e264c4392898
  5. 1mo ago Changed 8f0d97a237ce
  6. 1mo ago Changed d3876f542766
  7. 2mo ago First seen · 92 lines · 160 tokens per session scan A 7a6ce2ba425e

Subscribe to this mod's changes

e2e-debug is a skill published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed today), licensed MIT. It adds 202 tokens to every session and 2,146 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-08-31.

Related

Other skills, from other repositories

reproduce-bug

Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…

googleapis/mcp-toolbox · 130 tokens

verify-omnigent

Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…

omnigent-ai/omnigent · 100 tokens

testing-blocks

Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.

adobe/skills · 61 tokens

reality-verification

This skill should be used when the user asks to "verify a fix", "reproduce failure", "diagnose issue", "check BEFORE/AFTER state", "VF task", "reality check", "check test quality", "mock-only tests", or needs guidance on verifying fixes by reproducing failures before and after implementation, or detecting mock-heavy…

tzachbon/smart-ralph · 81 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 · 112 tokens

debugging

Playwright test debugging conventions for the scaffold — reading failure messages, classifying failure modes (TimeoutError, ZodError, strict-mode violation, locator not found, network errors, schema drift), the playwright.config.ts capture defaults (trace on-first-retry, screenshot only-on-failure, video…

idavidov13/agentic-playwright · 179 tokens