agentmods.dev

llmlb: Skill for Gemini CLI

.gemini/skills/gwt-pr/SKILL.md

gwt-pr is a skill for Gemini CLI from akiojin/llmlb. It costs 86 tokens per session (4,022 once invoked), scanned A, original, MIT.

A workflow for creating or updating GitHub pull requests with the `gh` command-line tool. It checks the current branch and working tree and follows rules about existing pull requests and allowed target branches.

In plain words
What is it for?
Use it to open a pull request, update an existing one, prepare its description, or decide whether only a push is appropriate.
Why use it?
It avoids creating duplicate pull requests or pushing while local changes are unreviewed, and applies the repository's branch policy consistently.

Skill for Gemini CLI

Written for Gemini CLI: installed under .gemini/. Also seen: positional $N argument.

This is akiojin/llmlb's own configuration. It tells Gemini CLI 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 →

not rated 10repo 3d ago A scan 86 tokens original MIT
View source ↗ akiojin/llmlb
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/.gemini/skills/gwt-pr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/akiojin/llmlb

Made for: Gemini CLI.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/akiojin/llmlb/gwt-pr"><img src="https://agentmods.dev/badge/skills/akiojin/llmlb/gwt-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,022 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 $0.00086 $0.04022
Opus 5.5 $0.00034 $0.01609
Sonnet 5.5 $0.00017 $0.00804
Haiku 4.5 $0.00009 $0.00402

Measured 8d ago against content hash d8e92b10d61c, 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 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.

.gemini/skills/gwt-pr/SKILL.md · 325 lines

How it starts

The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GH PR

Overview

Create or update GitHub Pull Requests with the gh CLI using a detailed body template and strict same-branch rules.

Decision rules (must follow)

  1. Do not create or switch branches. Always use the current branch as the PR head.
  2. Only develop may target main. If the base is main and the head branch is anything other than develop, refuse to create the PR and instruct the user to merge into develop first, then create a release PR from develop.
  3. Check local working tree state before push/PR operations.
    • git status --porcelain
    • If output is non-empty (tracked or untracked changes), pause and ask the user what to do.
    • Present 3 options: continue as-is, abort, or manual cleanup then rerun.
    • Do not run git stash, git commit, or git clean automatically unless explicitly requested.
  4. Check for an existing PR for the current head branch.
    • gh pr list --head <head> --state all --json number,state,mergedAt,updatedAt,url,title,mergeCommit
  5. If no PR exists → create a new PR.
  6. If any PR exists and is NOT merged (mergedAt is null) → push only and finish (do not create a new PR).
    • This applies to OPEN or CLOSED (unmerged) PRs.
    • Only update title/body/labels if the user explicitly requests changes.
  7. If all PRs for the head are merged → check for post-merge commits (see below).
  8. If multiple PRs exist for the head → use the most recently updated PR for reporting, but the create vs push decision is based on mergedAt.

Post-merge commit check (critical)

When all PRs for the head branch are merged, you must check whether there are new commits after the merge:

  1. Get the merge commit SHA of the most recent merged PR.
  2. Validate merge commit ancestry first: git merge-base --is-ancestor <merge_commit> HEAD
  3. If the merge commit is an ancestor of HEAD, count commits after the merge:
    • git rev-list --count <merge_commit>..HEAD
  4. If the merge commit is missing or not an ancestor of HEAD, fallback to the branch upstream first:
    • git rev-list --count origin/<head>..HEAD
  5. If the upstream comparison fails, fallback to the base branch comparison:
    • git rev-list --count origin/<base>..HEAD
  6. Decision:
    • If the selected count is greater than 0 → create a new PR
    • If the selected count is 0 → report "No new changes since merge" and finish
    • If both fallback comparisons fail → stop and report MANUAL CHECK

Read the full file on GitHub · 325 lines

Files

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.

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 · 325 lines · 86 tokens per session scan A d8e92b10d61c

Subscribe to this mod's changes

gwt-pr is a skill published in the GitHub repository akiojin/llmlb (10 stars, last pushed 3d ago), licensed MIT. It adds 86 tokens to every session and 4,022 once invoked, about $0.0003 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.

Code reviewGit and workflow
Related

Other skills, from other repositories

pr

Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.

Yeachan-Heo/oh-my-claudecode · 47 tokens

merge-batch

Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.

diegosouzapw/OmniRoute · 46 tokens

otto-pr-review-loop

Run Polly and OCR on a PR until all findings settle.

omnigent-ai/omnigent · 17 tokens

engram-branch-pr

PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.

Gentleman-Programming/engram · 37 tokens

github-contributor

A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.

daymade/claude-code-skills · 105 tokens

revdiff

Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…

umputun/revdiff · 248 tokens