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 skills add Pawel-Kica/claude-code-100 --skill e2egit clone --depth 1 https://github.com/Pawel-Kica/claude-code-100Wrote 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.
[](https://agentmods.dev/skills/pawel-kica/claude-code-100/e2e)<a href="https://agentmods.dev/skills/pawel-kica/claude-code-100/e2e"><img src="https://agentmods.dev/badge/skills/pawel-kica/claude-code-100/e2e/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.
<a href="https://agentmods.dev/skills/pawel-kica/claude-code-100/e2e"><img src="https://agentmods.dev/badge/skills/pawel-kica/claude-code-100/e2e.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00033 | $0.03240 |
| Opus 5 | $0.00016 | $0.01620 |
| Sonnet 5 | $0.00007 | $0.00648 |
| Haiku 4.5 | $0.00003 | $0.00324 |
Grade A, and why
e2e 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 8d 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.
- No UI for the change (scheduled task, API only, webhook): drive it anyway, say that is what you did. `curl` the real endpoint on the running server first, else call the service function in the app's own shell. Assert o How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Give it a goal. Drive the real thing until you can answer whether it works. Fix what breaks, verify the fix, answer.
Scope
- Goal is whatever the user said, in prose
- Args may be a spec, PRD or plan path: read it for intent, the file is not the target
- Nothing said: scope from
git status+git diff --stat, or from the checklist you wrote earlier in the conversation
Wrong surface
The most common way this skill lies:
- green on a page you were logged out of, on the tab next to the right one, on a modal that never opened
- URL is the one you meant, and you are the user you meant to be
- assert on state you watched change, then reload and assert it survived
- what you asserted on is the feature, not a lookalike: editor source text, hidden span, the component's own progress label
- poll a count of the real result nodes. Never the absence of a spinner, never the disappearance of the previous step, an SPA keeps it mounted
- same nodes reused for a new result: poll a discriminating value, the count is green before the numbers change
- the DOM can be right while the pixels are wrong. On canvas, WebGL, maps and charts no DOM assertion proves the render, look at the screenshot
Drive
Testing is always Chrome DevTools MCP. Playwright is for artifacts, nothing else.
MCP (mcp__chrome-devtools__*), always headless. The driver for every verification run:
- clicking through by hand, reading the a11y tree, checking console and network. No script to write
- a long or fiddly flow is not a reason to switch. Click it, don't script it
- one shared browser instance. Running alongside other agents, don't touch it, they will steal each other's tab
- writes only inside its workspace roots, so it cannot save to
/tmp. A shot you keep inside a workspace root is still MCP's job
Playwright, always chromium.launch({headless: true}), never headless: false. Artifacts only:
- the recording, and the kept screenshots that go with it, when the destination is outside the MCP workspace roots
- parallel runs, where the one shared MCP instance would collide. Not a preference, the only other exit
- global install, run as
NODE_PATH=$(npm root -g) node script.js, CommonJS. Same prefix for the check:NODE_PATH=$(npm root -g) node -e "require.resolve('playwright')", barenodewon't find it, andplaywright --versioncan be the Python package - working dir from
mktemp -d /tmp/e2e-XXXXXX. Timestamps collide when agents start together
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 146 lines · 33 tokens per session scan A 8f56abb72258
e2e is a skill published in the GitHub repository Pawel-Kica/claude-code-100 (2 stars, last pushed 15d ago), licensed MIT. It adds 33 tokens to every session and 3,240 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 skills, from other repositories
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.
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…
pyats-dynamic-test
Generate and execute deterministic pyATS aetest validation scripts - interface state, OSPF neighbors, BGP paths, ping matrices, and custom compliance tests. Use when writing a network test, validating post-change state, running pass/fail checks, or building automated regression tests.
test-loop
Plan, generate, and heal an executable E2E test suite from approved acceptance criteria (web and mobile).
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…