A repository-specific workflow for preparing, creating, or updating pull requests. A pull request is a proposed code change that others review before it is merged.

It helps inspect the complete change, write an English Conventional Commits title, fill the pull request template, and update an existing pull request.

It removes the need to remember the repository's title rules, template, checklist, target branch, and required images for visible interface changes.

How chattymin/PokeTokenBar configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to chattymin/PokeTokenBar. 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/chattymin/PokeTokenBar/main/.agents/skills/prepare-pr/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/chattymin/PokeTokenBar

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/chattymin/poketokenbar/prepare-pr/github.svg)](https://agentmods.dev/skills/chattymin/poketokenbar/prepare-pr)

Your own site

<a href="https://agentmods.dev/skills/chattymin/poketokenbar/prepare-pr"><img src="https://agentmods.dev/badge/skills/chattymin/poketokenbar/prepare-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/chattymin/poketokenbar/prepare-pr"><img src="https://agentmods.dev/badge/skills/chattymin/poketokenbar/prepare-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,486 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.

Model	Per session	Once invoked
Fable 5.1	$0.00076	$0.01486
Opus 5.5	$0.00030	$0.00594
Sonnet 5.5	$0.00015	$0.00297
Haiku 4.5	$0.00008	$0.00149

Measured 23d ago against content hash efcb7980a43f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

prepare-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 23d 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.

.agents/skills/prepare-pr/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prepare a PokeTokenBar PR

Use this repository's title and template rules even when a personal PR skill is also active. The shared instructions live here; Claude Code discovers them via .claude/skills/prepare-pr, and Codex via .agents/skills/prepare-pr. Run commands from the repository root. Paths below are relative to that root.

Title and body

Read CONTRIBUTING.md and .github/PULL_REQUEST_TEMPLATE.md before preparing or updating the PR. Resolve the actual target repository and base branch, then read the complete base...HEAD diff and base..HEAD commit range. Do not summarize only the last commit or use unrelated work already on the branch as new work.

Write the title and body in English. Use a Conventional Commits title such as fix(home): retain idle usage history or docs: require UI images in PRs. Choose a type and optional scope that describe the final change; do not copy a ticket prefix or a personal skill's title convention over repository rules.

Start the body from the current template. Fill Summary, select the actual Type of change, and retain the template's checklist. Check an item only when the performed work supports it; leave tests unchecked if they were not run or added, and explain why when relevant. Report actual validation and limitations. Keep the body in a UTF-8 file and pass it with gh ... --body-file.

Mandatory UI images

Decide whether the full diff changes visible UI. Inspect changes outside Sources/PokeTokenBar/UI/ too: data, localization, resources, and settings can change what users see. A change inside that directory triggers the local image check; an outside change with visible effects needs --ui-changes. For changes inside the UI directory that have no visible effect (such as comments or an equivalent refactor), inspect the full diff and use --no-ui-changes '<reason>'. Never use this declaration to excuse missing images for a visible change.

For every affected screen or state, embed images directly in UI changes:

Read the full file on GitHub · 123 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.

23d ago First seen · 123 lines · 76 tokens per session scan A efcb7980a43f

Subscribe to this mod's changes

prepare-pr is a skill published in the GitHub repository chattymin/PokeTokenBar (531 stars, last pushed 4d ago), licensed MIT. It adds 76 tokens to every session and 1,486 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 2026-10-06.

Claude Code Code review Commits Git and workflow ai-coding codex gemini-cli macos menu-bar

autofix-pr

Watch a pull request and fix it from a worktree of its own - CI failures, review feedback from trusted authors and merge conflicts are fixed, pushed to the PR branch and answered on the PR under the user's git and gh identity. Usage - /autofix-pr [ | ] [--once] [--every ] [--no-reply] [--yes] [instructions]…

QwenLM/qwen-code · 123 tokens

work-unit-commits

Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.

Gentleman-Programming/gentle-ai · 33 tokens

review-delta

Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.

tirth8205/code-review-graph · 24 tokens

ring:generating-pr-descriptions

Generating pull request descriptions from git branch changes with automatic title generation, change-type detection, and smart analysis. Uses branch-only scope to avoid full history analysis. Use when preparing a PR for review. Skip when the PR is a single trivial commit or description already exists.

LerianStudio/ring · 61 tokens

gentle-ai-work-unit-commits