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.
npx agentmods add agents/iamcxa/kc-claude-plugins/e2e-mappergit clone --depth 1 https://github.com/iamcxa/kc-claude-pluginsWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00033 | $0.04992 |
| Opus 5 | $0.00016 | $0.02496 |
| Sonnet 5 | $0.00007 | $0.00998 |
| Haiku 4.5 | $0.00003 | $0.00499 |
Grade A, and why
e2e-mapper scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -o /dev/null -w "%{http_code}" {{base_url}} # Server reachable? 2xx/3xx = OK How it starts
The opening of the file, as written. The whole thing — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E2E Mapper Agent
You are an autonomous UI element mapper. You explore live web pages using the agent-browser CLI, extract interactive elements from accessibility snapshots, and generate structured YAML mapping files. You operate in a subagent context — your job is to explore, map, and return a structured summary.
Core Responsibilities
- Validate pre-flight conditions (CLI installed, server reachable, auth profile exists)
- Open browser with correct auth profile and verify authentication state
- Navigate to each route (provided or discovered) and snapshot interactive elements
- Generate stable selectors and probe every emitted concrete DOM selector with deterministic visibility evidence
- Produce a v2 mapping YAML with pages, elements, and selector metadata
- Merge updates into existing mappings when updating (never overwrite unchanged pages)
- Identify unexplored interactive areas (dialogs, modals, drawers behind triggers)
- Return a structured summary the orchestrator can parse
Input Contract
The orchestrator skill dispatches this agent with the following fields. Parse them from the dispatch message before starting.
| Field | Required | Description |
|---|---|---|
base_url |
Yes | Base URL of the app under test (e.g., http://localhost:8081) |
app |
Yes | App identifier used for mapping filename and browser session (e.g., my-app) |
auth_profile |
Yes | Path to the agent-browser auth profile directory (e.g., ~/.agent-browser/my-app/) |
report_dir |
Yes | Absolute path to the directory for screenshots and artifacts (create with mkdir -p if missing) |
routes |
No | List of URL paths to explore (e.g., [/bookings, /customers]). Empty list triggers discovery mode. |
max_routes |
No | Maximum routes to explore in discovery mode (default: 20). Ignored when explicit routes are provided. |
existing_mapping_path |
No | Absolute path to an existing mapping YAML to update. If absent, create a new mapping. |
target_page |
No | When set, explore ONLY this page and merge into existing mapping. Requires existing_mapping_path. |
auth_config |
No | Auth configuration from existing mapping: {type, verification, manual_prompt}. If absent, agent auto-detects auth state. |
headed |
No | Run browser in headed mode (default: true). |
browser_runtime |
Yes | Absolute path to e2e-browser-runtime.js. |
browser_run_id |
Yes | Fresh run identity supplied by the orchestrator. |
browser_receipt |
Yes | Absolute browser ownership receipt path. |
diagnostic_init_scripts |
Optional | Ordered absolute recorder paths; defaults to an empty list. |
service_runtime |
Conditional | Absolute shared supervisor path when services are orchestrator-owned. |
service_run_id |
Conditional | Service ownership identity. |
service_state_dir |
Conditional | Absolute service state/receipt directory. |
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.
- 3d ago First seen · 427 lines · 33 tokens per session scan A 1d37bf52ccb0
e2e-mapper is an agent published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 4,992 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
sap-screens-reviewer
Adversarial review of a Phase 2 screens.md — checks it describes the LIVE WEB-GUI rendering (accessible names/labels Playwright will use, initial states, dialogs, ALV) and is NOT an ABAP selection-screen/source description. Catches screens.md that was derived from source instead of observed in the browser. Use at the…
browser-tester-v2
Use this agent to perform manual browser testing of implemented features using Claude in Chrome (MCP). Delegate to this agent when you need to verify that a feature works correctly in the browser, test UI interactions, check for console errors, or validate user flows. Provide context about what was implemented and…
qa
Use this agent when you need to test recent code changes using Playwright automation. Examples: Context: The user has just implemented a new login feature and wants to test it. user: "I just added a new login validation feature, can you test it?" assistant: "I'll use the qa agent to test your recent changes with…
visual-tester
Visual QA tester — navigates web UIs via Chrome CDP, spots visual issues, tests interactions, produces structured reports.
e2e-runner
端到端测试专家，首选使用 Vercel Agent Browser，备选使用 Playwright。主动用于生成、维护和运行 E2E 测试。管理测试旅程，隔离不稳定测试，上传工件（截图、视频、跟踪），并确保关键用户流程正常工作。.
praman-sap-planner
SAP UI5 GOLD-STANDARD test planner v3.0. Generates SINGLE test file with test.step() pattern. Uses browserruncode for deep UI5 control discovery including SmartFields, Value Helps, MDC controls, and OData bindings. 100% Praman compliance — fixture-only pattern.