global-clean-pr-commits

global-clean-pr-commits is a skill for Claude Code from rgomezcasas/dotfiles. It costs 22 tokens per session (536 once invoked), scanned A, original, MIT.

A guide for reorganizing all changes on a Git branch into clean, logical commits that follow Conventional Commits, a standard format for commit messages.

In plain words
What is it for?
Use it to inspect a branch's changes, propose commit groups, wait for approval, and then rebuild the branch history into focused commits.
Why use it?
It makes a branch's history easier to understand, review, and release. The required approval step prevents the commit grouping from being changed without the author's agreement.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to inspect a branch's changes, propose commit groups, wait for approval, and then rebuild the branch history into focused commits.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rgomezcasas/dotfiles/global-clean-pr-commits
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.

Any agent
npx skills add rgomezcasas/dotfiles --skill global-clean-pr-commits
Clone the repo
git clone --depth 1 https://github.com/rgomezcasas/dotfiles

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 global-clean-pr-commits

README.md
[![agentmods](https://agentmods.dev/badge/skills/rgomezcasas/dotfiles/global-clean-pr-commits/github.svg)](https://agentmods.dev/skills/rgomezcasas/dotfiles/global-clean-pr-commits)
Your own site
<a href="https://agentmods.dev/skills/rgomezcasas/dotfiles/global-clean-pr-commits"><img src="https://agentmods.dev/badge/skills/rgomezcasas/dotfiles/global-clean-pr-commits/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 global-clean-pr-commits

Your own site · 80×15
<a href="https://agentmods.dev/skills/rgomezcasas/dotfiles/global-clean-pr-commits"><img src="https://agentmods.dev/badge/skills/rgomezcasas/dotfiles/global-clean-pr-commits.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 536 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00022 $0.00536
Opus 5 $0.00011 $0.00268
Sonnet 5 $0.00004 $0.00107
Haiku 4.5 $0.00002 $0.00054

Measured 9d ago against content hash 2725b783ce7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

global-clean-pr-commits 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 9d 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.

config/agents/global_skills/global-clean-pr-commits/SKILL.md · 43 lines

What it actually says

Context

  • Current git status: !git status
  • Current branch: !git branch --show-current
  • Upstream tracking: !git rev-parse --abbrev-ref HEAD@{upstream} 2>/dev/null
  • Merge base with main: !git merge-base HEAD main
  • Commits on this branch (run manually): git log --oneline <merge-base>..HEAD
  • Full diff from base (run manually): git diff <merge-base>..HEAD
  • Repository root path: !git rev-parse --show-toplevel

Conventional Commits

We use Conventional Commits specification for all commit messages.

Task

Reorganize all commits on the current branch into clean, logical commits.

Steps

  1. Analyze the full diff and existing commits to understand all changes
  2. Propose a list of final commits grouping changes logically — present this to the user as a numbered list with the commit message and which files/changes each commit includes
  3. Wait for approval — the user may request changes to the grouping, do NOT proceed until they confirm
  4. Execute once approved: a. git reset --soft $(git merge-base HEAD <base-branch>) to undo all commits while keeping changes staged b. git reset HEAD . to unstage everything c. For each proposed commit: stage the relevant files with git add and create the commit d. Run git log --oneline $(git merge-base HEAD <base-branch>)..HEAD to show the final result

Important

  • NEVER force push — that is the user's responsibility
  • If there are uncommitted changes at the start, abort and tell the user to commit or stash first
  • Preserve ALL changes — no code should be lost in the process
  • If a file has changes that belong to different commits, use git add -p or stage specific hunks
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. 9d ago First seen · 43 lines · 22 tokens per session scan A 2725b783ce7b

Subscribe to this mod's changes

global-clean-pr-commits is a skill published in the GitHub repository rgomezcasas/dotfiles (362 stars, last pushed 21d ago), licensed MIT. It adds 22 tokens to every session and 536 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 2026-08-30.