commit-to-pr

commit-to-pr is a skill for Claude Code from aj604/toolshed. It costs 55 tokens per session (1,389 once invoked), scanned C, original, MIT.

A workflow that turns local or unpushed Git changes into a branch, commit, pushed branch, and GitHub pull request. A pull request is a proposed code change that others can review before merging.

In plain words
What is it for?
Use it to commit changes, push them to GitHub, and open or update a pull request, optionally as a draft.
Why use it?
It removes the repetitive packaging work needed to share finished changes while avoiding claims that the code was tested or reviewed. It requires Git and an authenticated GitHub command-line connection for pushing and creating the request.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; mentions Codex.

Part of the workbench plugin — 5 skills, 7 agents shipped together

Good fit Use it to commit changes, push them to GitHub, and open or update a pull request, optionally as a draft.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aj604/toolshed/commit-to-pr
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 aj604/toolshed --skill commit-to-pr
Clone the repo
git clone --depth 1 https://github.com/aj604/toolshed

Made for: Claude Code.

Or install workbench, the plugin that ships this one along with the rest of its 5 skills, 7 agents.

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 commit-to-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/aj604/toolshed/commit-to-pr/github.svg)](https://agentmods.dev/skills/aj604/toolshed/commit-to-pr)
Your own site
<a href="https://agentmods.dev/skills/aj604/toolshed/commit-to-pr"><img src="https://agentmods.dev/badge/skills/aj604/toolshed/commit-to-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 commit-to-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/aj604/toolshed/commit-to-pr"><img src="https://agentmods.dev/badge/skills/aj604/toolshed/commit-to-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,389 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00055 $0.01389
Opus 5.5 $0.00022 $0.00556
Sonnet 5.5 $0.00011 $0.00278
Haiku 4.5 $0.00006 $0.00139

Measured 2d ago against content hash cff67723b209, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

commit-to-pr scanned grade C with 1 finding 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 2d 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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

- **Don't stage** credential-shaped files (`.env*`, `*.pem`, `*.key`, `id_rsa*`, `credentials.json`, `.npmrc`, `.netrc`), secret-shaped content (`PRIVATE KEY`, `sk-ant-`, `ghp_`, `github_pat_`, `AKIA…`), build output (`d
plugins/workbench/skills/commit-to-pr/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit to PR

Turn uncommitted work (or unpushed commits) into a pull request: survey → branch → stage → commit → push → PR. Requires git, plus an authenticated gh for the push and PR.

This is packaging, not verification. Don't run tests, builds, linters, or reviews — CI and reviewers own those, and a PR step that runs them is slow and duplicates their work. The one exception is pre-commit hooks, which run on their own. Because nothing here verifies the change, the PR body makes no claims about tests, coverage, or quality; if the user asks you to write "all tests pass", say this step didn't check that and leave it out. When a calling skill (such as workbench:enhance) hands you a PR body or verification it actually ran, use that as given — the rule is about not inventing claims, not about stripping evidence someone else produced.

Arguments: [commit-message] (use verbatim as the subject), [base-branch] (default: the repo's real default branch), --draft.

1. Survey

git status --porcelain=v1 --branch
git diff --stat; git diff --staged --stat
git log --no-merges -20 --format='%s'
git log -1 --format='%b'
git remote -v
gh repo view --json defaultBranchRef -q .defaultBranchRef.name

Twenty subjects, because conventions vary and a short sample misleads; the last body shows whether the repo uses trailers.

  • Nothing modified and nothing ahead of upstream → stop, nothing to ship.
  • Nothing modified but commits ahead → skip to push.
  • Detached HEAD → stop and ask where the work should live.
  • No remote → commit locally, then stop and say there's nowhere to push.

2. Branch

  • On the default branch: create a branch before staging, so nothing lands on it by accident.
  • On an auto-generated name (adoring-leakey-5e0704 style) with no upstream: rename it (git branch -m). If it has an upstream, keep it — renaming orphans the remote branch and any PR.
  • On a meaningful name: keep it.

Follow the repo's evident naming (e.g. feat/…, fix/…); otherwise change/<slug>, where the slug names the change in 2–5 kebab words. Leave claude/ and codex/ prefixes alone.

Read the full file on GitHub · 80 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. 2d ago First seen · 80 lines · 55 tokens per session scan C cff67723b209

Subscribe to this mod's changes

commit-to-pr is a skill published in the GitHub repository aj604/toolshed (1 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 1,389 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-21.

Related

Other skills, from other repositories

git-for-research-code

When the user wants to version-control optimization research code - small commits per experiment change, tags for paper result snapshots, .gitignore for solver logs, linking result tables to commit hashes, and branch strategy for risky refactors. Also use when the user mentions "git workflow," "version control…

hajibabaie/combinatorial-optimization-skills · 117 tokens

git-ops

Use when Sam asks Claude Code to create, rename, compare, commit, push, merge, promote, or clean up Git branches. Covers Sam's feature branch naming convention, safe Git pre-checks, JetBrains DontCommit handling, commit-message defaults, push and release promotion verification, branch rename upstream cleanup, branch…

codingSamss/all-my-ai-needs · 77 tokens

release

CONTRIBUTOR TOOL - Cut a plugin release: bump plugin.json version, finalize CHANGELOG, update README if needed, gate on make ci, commit, tag vX.Y.Z, and create the GitHub release. Use when shipping a new plugin version. NOT distributed.

oliver-kriska/claude-elixir-phoenix · 60 tokens

pr-review

Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.

oliver-kriska/claude-elixir-phoenix · 59 tokens

phx-pr-review

Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.

oliver-kriska/claude-elixir-phoenix · 61 tokens

signing-preflight

Before the first commit of a session, check that commit signing will work — the key is loaded and unlocked — and ask the operator to unlock it once, up front, instead of discovering it after a hundred unsigned commits. Never disables signing silently, never re-signs history without asking. Use at the start of…

avelikiy/great_cto · 105 tokens