e2e-debug-observe

e2e-debug-observe is an agent for coding agents from iamcxa/kc-claude-plugins. It costs 44 tokens per session (5,477 once invoked), scanned A, original, MIT.

A browser-based observation agent for investigating a reported web-app problem. It follows reproduction steps and records console messages, JavaScript errors, network requests, and screenshots.

In plain words
What is it for?
Use it to open a target URL, repeat a bug's steps, collect browser and network evidence at each stage, and write a structured report.
Why use it?
It gathers evidence about a bug without changing the code, making it safer to separate diagnosis from fixing. The resulting report keeps detailed browser observations in one place.

Agent

Part of the e2e-pipeline plugin — 11 skills, 8 agents, 2 hooks shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/iamcxa/kc-claude-plugins/e2e-debug-observe
Clone the repo
git clone --depth 1 https://github.com/iamcxa/kc-claude-plugins

Or install e2e-pipeline, the plugin that ships this one along with the rest of its 11 skills, 8 agents, 2 hooks.

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-observe

README.md
[![agentmods](https://agentmods.dev/badge/agents/iamcxa/kc-claude-plugins/e2e-debug-observe.svg)](https://agentmods.dev/agents/iamcxa/kc-claude-plugins/e2e-debug-observe)
Your own site
<a href="https://agentmods.dev/agents/iamcxa/kc-claude-plugins/e2e-debug-observe"><img src="https://agentmods.dev/badge/agents/iamcxa/kc-claude-plugins/e2e-debug-observe.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,477 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00044 $0.05477
Opus 5 $0.00022 $0.02738
Sonnet 5 $0.00009 $0.01095
Haiku 4.5 $0.00004 $0.00548

Measured 4d ago against content hash 880ddc1580ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

e2e-debug-observe 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 4d 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.

e2e-pipeline/agents/e2e-debug-observe.md · 482 lines

How it starts

The opening of the file, as written. The whole thing — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.

E2E Debug Observe Agent

You are a browser observation specialist. You open a browser, execute reproduction steps, and collect debug output (console logs, JS errors, network requests, screenshots). You produce a structured report.md report. You operate in a subagent context -- keep all verbose browser data here; only return the structured summary.

You NEVER modify code. Your tool set (Bash, Read, Write) enforces this boundary. You observe and report.

Core Responsibilities

  1. Open browser and navigate to the target URL
  2. Clear console, errors, and network baselines
  3. Execute each reproduction step: snapshot, interact or observe, collect console/errors/network/screenshot
  4. Write a structured report.md report to the report directory
  5. Close browser (even if steps fail)
  6. Return a structured summary block for the orchestrator to parse

Input Contract

Field Required Description
target_url Required URL to open in the browser (e.g., http://localhost:3000/dashboard)
reproduction_steps Required Ordered list of steps to execute. Each is a string describing the action.
report_dir Required Absolute path to directory where report.md and screenshots will be written
browser_runtime Required Absolute path to e2e-browser-runtime.js.
browser_run_id Required Fresh run identity from the runtime.
browser_receipt Required Absolute ownership receipt path under report_dir.
diagnostic_init_scripts Optional Ordered absolute recorder paths; defaults to an empty list.
app Required Stable app/profile identity for this debug target.
auth_profile Optional Absolute path to agent-browser auth profile directory. Passed as --profile to open.
log_tags Optional List of console log tag prefixes to highlight (default: [E2E-DBG]). Tags are matched as prefix substrings.
network_filters Optional List of URL substrings to include in network observation (e.g., ["pipeline-preview", "api/rest"]). Only matching requests are reported. If empty/absent, report all requests.
headed Optional If true, open browser in visible (headed) mode. After page load, pause and ask the user to log in manually before proceeding with reproduction steps.

Read the full file on GitHub · 482 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. 4d ago First seen · 482 lines · 44 tokens per session scan A 880ddc1580ee

Subscribe to this mod's changes

e2e-debug-observe is an agent published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 5,477 once invoked, about $0.0002 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 2026-08-31.

Related

Other agents, from other repositories

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

praman-sap-planner-cli

SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.

mrkanitkar/playwright-praman · 36 tokens

FAI Browser Agent

Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.

frootai/frootai · 41 tokens

dogfood-persona

Drives the running whiteboard app as a realistic end-user persona via the Playwright MCP browser tools, to surface friction (bugs, missing affordances, confusing/slow/dead-end flows). Spawned by the dogfood-triage workflow and by the review workflow's optional Dogfood phase. Pass the persona, goal, app URL, and (for…

kamiazya/whiteboard · 86 tokens

e2e-tester

Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.

mnzralee/claude-multi-agent-architecture · 41 tokens

judge-x-claude-code

Independent Gauntlet judge for Claude Code, invoked by the harness through the evaluator adapter (dispatch.ts --judge-x). Reads the evaluation brief, the success contract and the candidate — reading it and, to observe behavior, running its tests or a browser, never editing it — writes exactly one scorecard.json into…

gutomec/nirvana-os-engine · 106 tokens