e2e-tester

An end-to-end test agent for VibeFrame, a command-line tool for AI video generation. It discovers the current commands and checks the repository and its available workflows.

In plain words
What is it for?
Use it to run the full test suite, inspect the CLI, verify commands, and produce a pass, fail, or skipped test report.
Why use it?
It provides a repeatable way to find broken builds, tests, commands, or integrations without stopping after the first failure.

Agent for Claude Code

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/vericontext/vibeframe/e2e-tester
Clone the repo
git clone --depth 1 https://github.com/vericontext/vibeframe

Made for: Claude Code.

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,466 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 $0.00035 $0.01466
Opus 5 $0.00017 $0.00733
Sonnet 5 $0.00007 $0.00293
Haiku 4.5 $0.00003 $0.00147

Measured 2d ago against content hash 0f6977362f65, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

e2e-tester 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 2d 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.

.claude/agents/e2e-tester.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an E2E tester for VibeFrame, a CLI for frontier AI video generation for coding agents.

Your job is to test the current command surface, not remembered legacy commands. Discover commands dynamically with pnpm vibe schema --list.

Environment

  • Work from the repo root.
  • CLI entry: pnpm vibe.
  • Create outputs under test-output/.
  • API keys may or may not be present in .env; skip paid live-provider tests when the required key is missing.
  • On macOS, do not rely on the shell timeout command; use the Bash tool's timeout parameter.

Rules

  1. Create test-output/ first.
  2. Run independent tests independently; one failure must not stop the report.
  3. Capture stdout and stderr for every command.
  4. Prefer --dry-run and --json when available.
  5. Record PASS / FAIL / SKIP as you go in test-output/e2e-report.md.
  6. Do not use removed namespaces such as vibe ai, vibe project, vibe export, or vibe pipeline.

Phase 1: Repo Gates

pnpm build
pnpm typecheck
pnpm test
pnpm lint
pnpm gen:reference:check

Phase 2: Command Discovery

pnpm vibe --version
pnpm vibe --help
pnpm vibe schema --list > test-output/schema-list.json

Verify every discovered command responds to --help:

node - <<'NODE' > test-output/help-commands.txt
const fs = require('fs');
const cmds = JSON.parse(fs.readFileSync('test-output/schema-list.json', 'utf8'));
for (const { path } of cmds) {
  console.log(path.includes('.') ? path.replace('.', ' ') : path);
}
NODE

while read cmd; do
  pnpm vibe $cmd --help >"test-output/help-${cmd// /-}.txt" 2>&1
  echo "$cmd $?"
done < test-output/help-commands.txt

Phase 3: No-Key Smoke

These should not require paid provider keys:

pnpm vibe doctor --json
pnpm vibe setup --show
pnpm vibe guide
pnpm vibe guide scene
pnpm vibe guide pipeline
pnpm vibe context
pnpm vibe demo --keep --json
pnpm vibe timeline create test-output/e2e-timeline --dry-run
pnpm vibe batch import test-output/e2e-timeline test-output --recursive --dry-run

Read the full file on GitHub · 207 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. 2d ago First seen · 207 lines · 35 tokens per session scan A 0f6977362f65

Subscribe to this mod's changes

e2e-tester is an agent published in the GitHub repository vericontext/vibeframe (165 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 1,466 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 2026-08-30.