open-pr

open-pr is a skill for Claude Code, Codex from nikeyes/stepwise-dev. It costs 33 tokens per session (693 once invoked), scanned A, original, Apache-2.0.

A workflow that pushes the current branch, opens a pull request when needed, waits for all its checks to finish, and reports the result. A pull request is a proposed change for review before merging.

In plain words
What is it for?
Use it to publish a branch, create or reuse its pull request, wait for automated checks, and see their outcome.
Why use it?
It handles the routine delivery steps while leaving files and existing pull-request text unchanged. It reports failures instead of fixing them.

Skill for Claude CodeCodex

Written for Claude Code and Codex: allowed-tools in frontmatter, but also agents/openai.yaml present. Also seen: model in frontmatter.

Part of the stepwise-git plugin — 4 skills shipped together

Good fit Use it to publish a branch, create or reuse its pull request, wait for automated checks, and see their outcome.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nikeyes/stepwise-dev/open-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 nikeyes/stepwise-dev --skill open-pr
Clone the repo
git clone --depth 1 https://github.com/nikeyes/stepwise-dev

Made for: Claude Code, Codex.

Or install stepwise-git, the plugin that ships this one along with the rest of its 4 skills.

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 open-pr

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/nikeyes/stepwise-dev/open-pr"><img src="https://agentmods.dev/badge/skills/nikeyes/stepwise-dev/open-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 693 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 $0.00033 $0.00693
Opus 5.5 $0.00013 $0.00277
Sonnet 5.5 $0.00007 $0.00139
Haiku 4.5 $0.00003 $0.00069

Measured 8d ago against content hash c4380e29006b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

open-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.

git/skills/open-pr/SKILL.md · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Open PR

Push the current branch, make sure it has a pull request, wait until every check on it has finished, and report the result. Do not ask for confirmation and do not change any file.

Rules

  • Uncommitted changes: they are not part of the PR. List them in the report and carry on with what is committed.
  • Nothing to open: if the branch has no commits ahead of the default branch and no open PR, say so and stop.
  • Branch: if you are on the repository's default branch, create type/short-description from the main commit with git switch -c; the commits come with it. Do not reset the local default branch: report that it is still ahead of its remote. On any other branch, use it as it is.
  • Push: git push -u origin <branch>. Never force-push. If the push is rejected, stop and report why.
  • Existing PR: if the branch already has an open PR, leave its title and body alone.
  • New PR: ready for review (not a draft), against the default branch.
    • Title: one Conventional Commits subject (type(scope): description) that covers the whole branch. With a single commit, use its subject. It becomes the squash commit in many repos.
    • Body: if the repo has a pull request template, fill it in. Otherwise write ## Summary (what changes and why) and ## Testing (what was run and its result; only what actually ran).
    • Never include: ticket identifiers, Claude attribution, "Generated with" lines.
  • Waiting:
    • Checks take a few seconds to register after a push. If none are reported, retry for up to 2 minutes before concluding that the repo has no checks.
    • Wait with gh pr checks <pr> --watch, in stretches shorter than your command timeout, repeating until no check is pending or 30 minutes have passed in total.
    • A check that failed, was cancelled or timed out has finished. Do not wait for reviews that are not checks.
  • Failed checks: for each one, get the end of its log with gh run view <run-id> --log-failed. If it is not a GitHub Actions run, give its details URL instead.
  • Report:
    • the PR URL, and whether you created it or it already existed
    • every check with its result
    • for each failed check, the end of its log
    • the checks still pending if the 30 minutes ran out
    • uncommitted changes you left out

Read the full file on GitHub · 35 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 · 35 lines · 33 tokens per session scan A c4380e29006b

Subscribe to this mod's changes

open-pr is a skill published in the GitHub repository nikeyes/stepwise-dev (24 stars, last pushed 6d ago), licensed Apache-2.0. It adds 33 tokens to every session and 693 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 2026-10-11.