llmlb: Command for Claude Code

.claude/commands/gwt-pr-check.md

gwt-pr-check is a command for Claude Code from akiojin/llmlb. It costs 17 tokens per session (317 once invoked), scanned A, original, MIT.

A command that checks the current Git branch's GitHub pull request status and whether commits were added after a merge. It uses GitHub's command-line tool and reports the evidence and suggested next step.

In plain words
What is it for?
Use it to inspect pull requests for the current branch, verify merge-commit ancestry, and count later commits before deciding what to do next.
Why use it?
It avoids guessing whether a pull request was created or merged when branch history is unclear. It also keeps the check read-only, so it does not change pull requests or push code.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; reads ~/.codex paths; mentions Codex.

This is akiojin/llmlb's own configuration. It tells Claude Code how to work on llmlb itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything llmlb configures →

Reuse

Borrowing it

Nothing to install: this file belongs to akiojin/llmlb. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/akiojin/llmlb/develop/.claude/commands/gwt-pr-check.md
Clone the repo
git clone --depth 1 https://github.com/akiojin/llmlb

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 gwt-pr-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/akiojin/llmlb/gwt-pr-check/github.svg)](https://agentmods.dev/commands/akiojin/llmlb/gwt-pr-check)
Your own site
<a href="https://agentmods.dev/commands/akiojin/llmlb/gwt-pr-check"><img src="https://agentmods.dev/badge/commands/akiojin/llmlb/gwt-pr-check/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 gwt-pr-check

Your own site · 80×15
<a href="https://agentmods.dev/commands/akiojin/llmlb/gwt-pr-check"><img src="https://agentmods.dev/badge/commands/akiojin/llmlb/gwt-pr-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 317 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 $0.00017 $0.00317
Opus 5.5 $0.00007 $0.00127
Sonnet 5.5 $0.00003 $0.00063
Haiku 4.5 $0.00002 $0.00032

Measured 8d ago against content hash 928ac4dbbafb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gwt-pr-check 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 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.

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/commands/gwt-pr-check.md · 42 lines

What it actually says

GitHub PR Check Command

Use this command to inspect PR status for the current branch with the gh CLI.

Usage

/gwt:gwt-pr-check [optional context]

Steps

  1. Load .claude/skills/gwt-pr-check/SKILL.md and follow the workflow.
  2. Run python3 ".codex/skills/gwt-pr-check/scripts/check_pr_status.py" --repo ".".
  3. Ensure gh auth status succeeds before running PR checks.
  4. When all PRs for the head are merged, validate merge commit ancestry before counting post-merge commits.
  5. If the merge commit is missing or not an ancestor of HEAD, compare origin/<head>..HEAD before any base-branch fallback.
  6. If both upstream and base comparisons fail, return MANUAL CHECK instead of inferring CREATE PR.
  7. Return the human-readable summary from the script:
    • Result
    • Recommended next step
    • Why
    • Context and key evidence
  8. Append JSON only if the user explicitly asks for machine-readable output.
  9. Do not push or create/edit PRs in this command.

Examples

/gwt:gwt-pr-check
/gwt:gwt-pr-check check current branch after merge
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. 8d ago First seen · 42 lines · 17 tokens per session scan A 928ac4dbbafb

Subscribe to this mod's changes

gwt-pr-check is a command published in the GitHub repository akiojin/llmlb (10 stars, last pushed 3d ago), licensed MIT. It adds 17 tokens to every session and 317 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-21.