What is verify-issue?

A command for checking whether a reported GitHub or GitLab issue describes a reproducible software bug by creating and running an E2E browser test.

Use it to fetch an issue, inspect its reproduction steps, explore the affected pages, create tests for the expected behavior, run them, and examine screenshots or network logs when the test fails.

It turns a written bug report into a repeatable check. A failing test indicates that the expected behavior is broken, while a passing test means the reported problem could not be reproduced in that run.

verify-issue — Command by fastslack

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 commands/fastslack/mtw-e2e-runner/verify-issue

Clone the repo

git clone --depth 1 https://github.com/fastslack/mtw-e2e-runner

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 604 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.

Model	Per session	Once invoked
Fable 5	$0.00016	$0.00604
Opus 5	$0.00008	$0.00302
Sonnet 5	$0.00003	$0.00121
Haiku 4.5	$0.00002	$0.00060

Measured 2d ago against content hash 4467828eec94, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verify-issue 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.

.opencode/commands/verify-issue.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify Issue

Turn a GitHub or GitLab bug report into executable E2E tests to confirm or dismiss the bug.

Workflow

Check pool — Call e2e_pool_status to ensure the Chrome pool is available.
Fetch the issue — Call e2e_issue with the issue URL. Default mode: "prompt" returns issue details + a structured prompt for test creation.
Analyze the issue — Parse the issue details:
- Understand the reported bug or expected behavior
- Identify affected pages/flows
- Note any reproduction steps provided
Explore the app — Use e2e_capture to screenshot relevant pages. Use Read and Grep to check source code for related components, API endpoints, or selectors.
Design tests — Create tests that assert the correct behavior:
- If tests fail → bug is confirmed (correct behavior is not working)
- If tests pass → bug is not reproducible
Create and run — Use e2e_create_test to write the test file, then e2e_run to execute it.
Analyze results — For failures:
- Retrieve error screenshots with e2e_screenshot
- Check network logs with e2e_network_logs for API-related issues
- Determine if the failure confirms the bug
Report verdict — Clearly state:
- BUG CONFIRMED: tests failed, reproducing the issue
- NOT REPRODUCIBLE: tests passed, correct behavior works as expected
- Include evidence (screenshots, error messages, network details)

Alternative: Verify Mode

If ANTHROPIC_API_KEY is set, use e2e_issue with mode: "verify" for a fully automated flow — it generates tests via Claude API, runs them, and reports the result.

Arguments

Required: GitHub or GitLab issue URL

/verify-issue https://github.com/org/repo/issues/123

Optional flags:

--test-type api — generate API tests instead of UI tests
--verify — use verify mode (requires ANTHROPIC_API_KEY)

MCP Tools Used

e2e_pool_status — Check Chrome pool availability
e2e_issue — Fetch and parse issue details
e2e_create_test — Write test file
e2e_run — Execute tests
e2e_screenshot — View screenshots
e2e_network_logs — Inspect network requests
e2e_capture — Screenshot pages

Read the full file on GitHub · 63 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.

2d ago First seen · 63 lines · 16 tokens per session scan A 4467828eec94

Subscribe to this mod's changes

verify-issue is a command published in the GitHub repository fastslack/mtw-e2e-runner (3 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 604 once invoked, about $0.0001 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.

Debugging E2E testing Testing browser-automation browserless claude-code docker json

verify-issue

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Verify Issue

Workflow

Alternative: Verify Mode

Arguments

MCP Tools Used

What this file has done since we first saw it

Other commands, from other repositories

qa

record-workflow

verify-pr

record

verify

test-run