pr

pr is a skill for Claude Code from bengous/claude-code-plugins. It costs 84 tokens per session (3,888 once invoked), scanned A, original, MIT.

A workflow for opening or updating the current branch's GitHub pull request, including a review summary and attached images. A pull request is a proposed code change sent to collaborators for review.

In plain words
What is it for?
Use it to create, submit, update, or rewrite a pull request, or to preview its title, base, body, and attachments without publishing.
Why use it?
It checks the branch and working tree before publishing, and gives reviewers a concise account of the change and checks performed.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the github-flow plugin — 8 skills shipped together

Good fit Use it to create, submit, update, or rewrite a pull request, or to preview its title, base, body, and attachments without publishing.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add bengous/claude-code-plugins
Claude Code
/plugin install github-flow

Made for: Claude Code.

Or install github-flow, the plugin that ships this one along with the rest of its 8 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 pr

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/bengous/claude-code-plugins/pr"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,888 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 $0.00084 $0.03888
Opus 5.5 $0.00034 $0.01555
Sonnet 5.5 $0.00017 $0.00778
Haiku 4.5 $0.00008 $0.00389

Measured 7d ago against content hash fe124fd7a7dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 7d 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.

github-flow/skills/pr/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR

Agents review the PR first. The body is for the human who opens it afterwards and wants the essential at a glance: what changed shape, what was checked, what was decided, and what is left open. Not a wall of text, not every file. The body shows the change, then says only what a picture cannot. Every view is text, so an agent reads the same facts.

Input

$ARGUMENTS

  • --dry-run: no push, no publish; print the title, the base, the body and the attachments instead.
  • Paths ending in .png, .jpg, .gif, .mp4, .mov: files to attach. Alt text may follow the path after #.
  • The rest: what the reviewer should know, kept as facts in the body.
  • Empty: everything comes from the branch.

Protocol

  1. Branch. git branch --show-current. On dev, main, the repo's default branch, or no branch: stop, show git status --short, ask for a branch name; with no user to ask, report no branch and stop. Uncommitted changes: stop and say so; the commit comes first (/git:commit).
  2. Base. dev when origin/dev exists, else gh repo view --json defaultBranchRef. gh takes that bare name; a git command or the script takes origin/<base>, since a local branch of that name may be missing or stale.
  3. Evidence. Read before citing.
    • git log --oneline origin/<base>..HEAD and git diff --stat origin/<base>...HEAD: the size, the files.
    • Tests added by the branch: git diff --stat origin/<base>...HEAD -- '*test*'.
    • The issue: Closes #N in a commit body, else the leading number of the branch name, else none. gh issue view <n> --json title,body when there is one.
    • When the issue has an Out of scope section: every file of git diff --name-only origin/<base>...HEAD that it names.
    • The repo's .claude/github-flow.json: the validate commands, and the verdict and tier commands of steps 8 and 9. Without the file, the validation commands of its AGENTS.md or CLAUDE.md. Its GLOSSARY.md or CONTEXT.md when one exists: the words that name the nodes of a view.
    • What ran this session, with its numbers.
  4. Views. Pick the smallest view that makes the key point clear, from the table under Views. A standard change gets one; a large one gets one per concern, three at most, a Before/After pair counting as one. Past three, Left open names the views left out.
    • Moved, added or deleted directories: ${CLAUDE_PLUGIN_ROOT}/scripts/tree-diff.ts origin/<base> prints the tree diff. A directory moved, added or deleted whole is one line, and a directory where more than three files changed, all of them only modified, is a count. Keep the lines the reader needs and comment each one with what it owns now.
    • A Mermaid diagram: read references/mermaid.md first. GitHub's renderer has traps a terminal never shows.
    • Worked examples of every view: references/views.md.

Read the full file on GitHub · 130 lines

Files

What ships with it

4 files 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. 7d ago Changed fe124fd7a7dc
  2. 10d ago Changed · +15 lines · +14 tokens per session 242192b94ac2
  3. 1mo ago Changed · +29 lines · +19 tokens per session a2c0a1a952f6
  4. 1mo ago Changed · +2 lines 62d1f983157e
  5. 1mo ago Changed · +8 lines 1a248cf29f67
  6. 2mo ago First seen · 76 lines · 51 tokens per session scan A 7467e0cc6027

Subscribe to this mod's changes

pr is a skill published in the GitHub repository bengous/claude-code-plugins (6 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 3,888 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 2026-09-11.

Related

pr compared with skills from other repositories

pr next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
prbengous/claude-code-pluginsSkill6yesterdayMITA84Claude Code
flow-next-landgmickel/flow-nextSkill722yesterdayMITA35Claude Code, Codex
flow-next-worktree-kitgmickel/flow-nextSkill722yesterdayMITA43Claude Code, Codex
development-workflowathola/claude-night-marketSkill350yesterdayMITA20Claude Code
share-a-libraryMoizIbnYousaf/Ai-Agent-SkillsSkill1.2k1mo agoMITA41Claude Code, Codex
stepwise-task-executionmakifbaysal/tasktrooperSkill122todayApache-2.0A33Claude Code, Codex
github-clizhinjs/zhinSkill137yesterdayMITA30Claude Code, Codex