pr

pr is a skill for Codex from sago-cream/human-out-of-loop. It costs 42 tokens per session (897 once invoked), scanned A, original, MIT.

A workflow that reviews committed code changes and publishes a maintainer-ready draft pull request to the current writable Git repository.

In plain words
What is it for?
It is for inspecting the complete branch changes, running publication checks, reviewing UI differences when relevant, and creating a draft pull request.
Why use it?
It catches review issues and checks that the proposed change is safe to publish before opening the draft pull request.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit It is for inspecting the complete branch changes, running publication checks, reviewing UI differences when relevant, and creating a draft pull request.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sago-cream/human-out-of-loop/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 sago-cream/human-out-of-loop --skill pr
Clone the repo
git clone --depth 1 https://github.com/sago-cream/human-out-of-loop

Made for: 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 pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/sago-cream/human-out-of-loop/pr/github.svg)](https://agentmods.dev/skills/sago-cream/human-out-of-loop/pr)
Your own site
<a href="https://agentmods.dev/skills/sago-cream/human-out-of-loop/pr"><img src="https://agentmods.dev/badge/skills/sago-cream/human-out-of-loop/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/sago-cream/human-out-of-loop/pr"><img src="https://agentmods.dev/badge/skills/sago-cream/human-out-of-loop/pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 897 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 $0.00042 $0.00897
Opus 5 $0.00021 $0.00449
Sonnet 5 $0.00008 $0.00179
Haiku 4.5 $0.00004 $0.00090

Measured 11d ago against content hash e14cb7736bc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 11d 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.

skills/pr/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Preflight

  1. Treat the current branch's Git remote as the sole publication target. Never infer a repository from GitHub CLI context, follow a parent/upstream repository, create or synchronize a fork, or publish anywhere else. Require authenticated write access; otherwise stop and ask the user to run from a branch whose remote is their writable fork or repository.
  2. Run the bundled bash scripts/pr-preflight from the target worktree before review and again before publication. Never review or publish while blocked.
  3. Inspect its prospective commits and complete diff for task scope.
  4. If the branch is default or spent, rebuild from the reported base with only intended commits, then rerun preflight.
  5. If base or head changes, repeat the affected review.

Review

  1. Use the preflight base and head; verify worktree HEAD before each review.
  2. Review the complete base...head diff. Report actionable findings and stop.
  3. For every UI change, reuse supplied media or capture matched, reproducible before/after media from base and head. Capture Before from the exact base commit the PR will merge into and After from the reviewed head. On follow-ups, reuse or recapture Before from that base; never use an earlier feature-branch revision or a prior After as the new Before:
    • Use video for interaction, motion, or multiple steps; images otherwise.
    • Match viewport, state, data, and action sequence.
    • Frame screenshots with enough surrounding UI to make the changed element's location and purpose clear, including a page or section landmark and relevant adjacent controls. Prefer viewport- or section-level framing; use tight element crops only when context is genuinely unnecessary.
    • Keep media untracked through .git/info/exclude.
    • Never publish with either side missing.

Package

  • Use the repository PR template exactly when present.
  • Before writing the title and description, inspect recently merged PRs and base-branch Git history for the repository's vocabulary, scope, and level of detail.
  • Treat prospective commit subjects as inputs for change scope, not as PR title candidates.
  • Title: <type>(<scope>): <imperative summary> using the narrowest Conventional Commits type. Omit an unhelpful scope; reserve style for formatting-only changes.
  • Write a concise, human-readable title around the complete user-visible or system-visible outcome that makes the change valuable. Make it stand alone for a reviewer who has not read the description.
  • Add issue-closing syntax when the change resolves an issue.
  • Do not invent template sections or include generic command output.
  • Without a repository template, use ## Purpose, ## Solution, and ## Verification for substantive changes. Purpose states the problem or user need. Solution explains the approach and relevant trade-offs; add implementation bullets only when they help reviewers. Verification records the evidence that the change works. For a trivial change, one short paragraph may replace these sections.
  • Put both UI Before: and After: media under the best template heading; never publish a comparison with either side missing. Without a template, add ## Comparison only when visual evidence benefits from its own section.

Read the full file on GitHub · 46 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. 11d ago First seen · 46 lines · 42 tokens per session scan A e14cb7736bc3

Subscribe to this mod's changes

pr is a skill published in the GitHub repository sago-cream/human-out-of-loop (6 stars, last pushed 22d ago), licensed MIT. It adds 42 tokens to every session and 897 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

review-implement-phase

Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.

prisma/orm · 38 tokens

engram-branch-pr

PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.

Gentleman-Programming/engram · 37 tokens

verify-behavior

Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…

nicknisi/dotfiles · 68 tokens

github-contributor

End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…

daymade/claude-code-skills · 133 tokens

revdiff

Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…

umputun/revdiff · 248 tokens

oss-maintainer

Run an open-source project's issue/PR/release loop like a careful human maintainer — triage to root cause, absorb community PRs before duplicating them, gate every merge, ship honest releases, and thank the people doing your QA for free.

debpalash/VoiceStudio · 55 tokens