open-pr

open-pr is a skill for Claude Code, Codex from massimoalbarello/context-use-old. It costs 65 tokens per session (1,591 once invoked), scanned A, original, MIT.

A pull-request workflow for preparing, publishing, and monitoring a GitHub pull request in a repository.

In plain words
What is it for?
Use it to inspect repository state, commit and push scoped changes, open a pull request, and follow its checks.
Why use it?
It keeps the change limited to the requested work and prevents accidental merging or unrelated files from being committed.

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/massimoalbarello/context-use-old/open-pr
Any agent
npx skills add massimoalbarello/context-use-old --skill open-pr
Clone the repo
git clone --depth 1 https://github.com/massimoalbarello/context-use-old

Made for: Claude Code, Codex.

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/massimoalbarello/context-use-old/open-pr.svg)](https://agentmods.dev/skills/massimoalbarello/context-use-old/open-pr)
Your own site
<a href="https://agentmods.dev/skills/massimoalbarello/context-use-old/open-pr"><img src="https://agentmods.dev/badge/skills/massimoalbarello/context-use-old/open-pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,591 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 $0.00065 $0.01591
Opus 5 $0.00032 $0.00796
Sonnet 5 $0.00013 $0.00318
Haiku 4.5 $0.00006 $0.00159

Measured 4d ago against content hash 4ecfdc01264c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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.

.agents/skills/open-pr/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Open Pull Request

Finish the requested work as a narrow pull request and shepherd its pre-merge checks. Treat opening a PR as authorization to commit and push only the changes in scope; do not treat it as authorization to merge.

Ground Rules

  • Preserve user work. Never stage, rewrite, revert, or clean up unrelated changes.
  • Use non-interactive git and gh commands.
  • Never commit secrets, local environment files, build output, or unrelated generated files.
  • Never push directly to main.
  • Never merge, enable auto-merge, or press a merge button unless the user explicitly asks to merge that specific PR.
  • Keep the PR narrow. Stop and ask for direction if the safe scope is materially ambiguous.
  • Do not rewrite published history or force-push unless the user explicitly requests it and the consequences are clear.

1. Establish Scope and State

Read repository instructions and inspect the worktree before changing Git state:

git status --short --branch
git diff --stat
git diff
git diff --cached
git remote -v
git symbolic-ref refs/remotes/origin/HEAD

Infer the intended file set from the current task and conversation. Treat all other modifications and untracked files as user-owned. If an intended file overlaps unrelated edits, preserve both when safe; otherwise stop and explain the conflict.

Confirm GitHub CLI access and repository metadata when needed:

gh auth status
gh repo view --json nameWithOwner,defaultBranchRef

Before creating a PR, check whether the current branch already has one. Update and shepherd the existing PR instead of opening a duplicate.

gh pr list --head "$(git branch --show-current)" --state open --json number,title,url,baseRefName,headRefName

2. Validate the Change

Run the smallest useful local checks for the touched area, then run broader CI-equivalent checks when the change affects shared code, dependencies, builds, infrastructure, or deployment.

Core repository checks are:

bun run typecheck
bun test
bun --cwd apps/server build
bun --cwd apps/web build

Read the full file on GitHub · 150 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. 4d ago First seen · 150 lines · 65 tokens per session scan A 4ecfdc01264c

Subscribe to this mod's changes

open-pr is a skill published in the GitHub repository massimoalbarello/context-use-old (2 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 1,591 once invoked, about $0.0003 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens