pr

A workflow for opening a GitHub pull request from a Jujutsu revision. Jujutsu, or jj, is a version-control tool; a pull request is a request for others to review and merge code changes.

In plain words
What is it for?
Creating draft or ready pull requests for the current changes or a specified revision, including a suitable title and explanation.
Why use it?
It handles the preparation around a pull request, including pushing the changes, reviewing the complete change set, and following the repository's pull-request template.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/martinemde/dotfiles/pr
Any agent
npx skills add martinemde/dotfiles --skill pr
Clone the repo
git clone --depth 1 https://github.com/martinemde/dotfiles

Made for: Claude Code, Codex.

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 661 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00047 $0.00661
Opus 5 $0.00023 $0.00331
Sonnet 5 $0.00009 $0.00132
Haiku 4.5 $0.00005 $0.00066

Measured 2d ago against content hash 519316c879f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

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.

home/dot_claude/skills/pr/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Pull Request

  • /pr — draft PR for the current diff from trunk
  • /pr [revision] — draft PR for that revision
  • /pr [revision] ready — ready for review rather than draft

Push and get the bookmark

The command depends on what the revision already has:

jj git push --bookmark <name>                                     # remote-tracked bookmark
jj bookmark track <name>@origin && jj git push --bookmark <name>  # local-only bookmark
jj git push -c <revision>                                         # no bookmark: creates one

Take the bookmark name from the output.

Review the whole changeset

jj log -r 'trunk()..<bookmark>'                 # commits going in
jj diff --from trunk() --to <bookmark> --stat    # everything changing

A PR is easier to review as several focused commits than one large one. If the changeset is mixed, reorganize with jj split or jj squash before opening it.

Check .github/ for a PR template and follow it if one exists.

Draft the title and body

The title summarizes the whole changeset, not just the most recent commit.

The body explains why the change was made and what it affects — context and motivation, not implementation. Don't restate what the diff already shows: "added function X" and "modified file Y" earn their place only when the reasoning behind them isn't obvious. Cover user-facing impact, architectural decisions, and trade-offs, following whatever conventions the repository already uses.

Two skills help here when they're available in the session. Invoke elements-of-style:writing-clearly-and-concisely before drafting prose. Search episodic-memory:search for conversations touching the changed files, looking for design decisions and their rationale, alternatives that were considered and rejected, trade-offs, and constraints that shaped the solution — surface what you find as a "Design Decisions" section.

Attribution gets an "Assisted-by" footer, not a "Generated with Claude Code" one.

Read the full file on GitHub · 72 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 · 72 lines · 47 tokens per session scan A 519316c879f5

Subscribe to this mod's changes

pr is a skill published in the GitHub repository martinemde/dotfiles (9 stars, last pushed 1mo ago), licensed ISC. It adds 47 tokens to every session and 661 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

dotfiles-bootstrap

Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.

sebastienrousseau/dotfiles · 88 tokens

vibe

Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…

sebastienrousseau/dotfiles · 137 tokens

aiq-research

Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.

laurigates/dotfiles · 25 tokens

obsidian-bases

Obsidian Bases database feature for YAML-based interactive note views. Use when creating .base files, writing filter queries, building formulas, configuring table/card views, or working with Obsidian properties and frontmatter databases.

laurigates/dotfiles · 49 tokens

telegram

Send notifications, interactive questions, or multiple-choice polls to the user via Telegram. Use when the user asks to be notified ("ping me", "notify me on Telegram", "ask me when..."), when a long-running task finishes and the user is likely away, when an irreversible action needs out-of-band confirmation, or when…

laurigates/dotfiles · 117 tokens

chezmoi-expert

Comprehensive chezmoi dotfiles management expertise including templates, cross-platform configuration, file naming conventions, and troubleshooting. Covers source directory management, reproducible environment setup, and chezmoi templating with Go templates. Use when user mentions chezmoi, dotfiles, cross-platform…

laurigates/dotfiles · 88 tokens