gh-issue-use-aws-browser

gh-issue-use-aws-browser is a command for Claude Code from skyfox675/agents-skills. It costs 104 tokens per session (1,344 once invoked), scanned A, original, MIT.

A command for investigating a reported software problem across the application, a live browser session, and AWS cloud services. AWS is Amazon’s cloud platform; the command follows a failing request through its connected layers.

In plain words
What is it for?
Use it to reproduce a symptom, capture the failed request, trace it through the edge, logs, service, and data, and file a detailed GitHub issue with the diagnosis.
Why use it?
It helps find faults that are invisible when checking only the browser or only the cloud, while reproducing the issue as the signed-in user.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Good fit Use it to reproduce a symptom, capture the failed request, trace it through the edge, logs, service, and data, and file a detailed GitHub issue with the diagnosis.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/skyfox675/agents-skills/gh-issue-use-aws-browser
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.

Clone the repo
git clone --depth 1 https://github.com/skyfox675/agents-skills

Made for: Claude Code.

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 gh-issue-use-aws-browser

README.md
[![agentmods](https://agentmods.dev/badge/commands/skyfox675/agents-skills/gh-issue-use-aws-browser/github.svg)](https://agentmods.dev/commands/skyfox675/agents-skills/gh-issue-use-aws-browser)
Your own site
<a href="https://agentmods.dev/commands/skyfox675/agents-skills/gh-issue-use-aws-browser"><img src="https://agentmods.dev/badge/commands/skyfox675/agents-skills/gh-issue-use-aws-browser/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.

agentmods 80×15 button for gh-issue-use-aws-browser

Your own site · 80×15
<a href="https://agentmods.dev/commands/skyfox675/agents-skills/gh-issue-use-aws-browser"><img src="https://agentmods.dev/badge/commands/skyfox675/agents-skills/gh-issue-use-aws-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,344 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00104 $0.01344
Opus 5 $0.00052 $0.00672
Sonnet 5 $0.00021 $0.00269
Haiku 4.5 $0.00010 $0.00134

Measured 10d ago against content hash ea992d3c2637, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

gh-issue-use-aws-browser 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 10d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/commands/gh-issue-use-aws-browser.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/gh-issue-use-aws-browser — file a groomed GitHub issue with a correlated full-stack diagnosis

Arguments: $ARGUMENTS — parsed exactly like /gh-issue (see gh-issue.md): breadcrumb first, optional model:/effort: tokens anywhere, the rest is the description. The filing flow is /gh-issue's, unchanged. The deep-dive phases and ALL their ground rules come from the two siblings and apply verbatim here:

  • gh-issue-use-browser.md (the browser-diagnosis skill) — context isolation, careful-user mutation rules, dialog hazard, residue tracking, token/cookie redaction, rabbit-hole guard, on whichever browser MCP is connected (Chrome, Playwright, or Cypress).
  • gh-issue-use-aws.md — identity-first, the read-only verb allowlist, lambda invoke is forbidden, secrets stay sealed, AccessDenied is a finding.

What this command adds is the correlation method — neither side alone finds the faults that live between layers. (Tracking work in Jira instead? Use /jira-issue-use-aws-browser.)

The correlated dive

Work the stack as one trace, in this order:

  1. Codebase recon first (per /gh-issue): map the breadcrumb to the components, the API operations they call, and the cloud resources behind them. This map tells you what to watch on both sides.

  2. Reproduce in the browser (per gh-issue-use-browser): perform the user's steps in your own tab group and capture the failing request — method, URL/operation, payload, status, response body, and above all any request/correlation IDs and the precise timestamp. A fresh repro matters because it generates evidence you can find in logs that are still hot. Record the repro GIF while you're there.

  3. Chase that exact request through AWS (per gh-issue-use-aws): take the correlation ID/timestamp into the logs of each hop the recon map predicts — edge (4xx/5xx, WAF, CDN), service (handler logs around the timestamp), then data (does the row/object/queue message the code expects actually exist, with the key shape the code queries?). CloudTrail for config drift when behavior changed without a deploy.

Read the full file on GitHub · 37 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. 10d ago First seen · 37 lines · 104 tokens per session scan A ea992d3c2637

Subscribe to this mod's changes

gh-issue-use-aws-browser is a command published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 9d ago), licensed MIT. It adds 104 tokens to every session and 1,344 once invoked, about $0.0005 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.