A workflow for opening, updating, reviewing, and merging GitHub pull requests or GitLab merge requests from the command line. It checks the branch, rebases it, runs project checks, and prepares the request details.

Use it to create or update a draft or ready-for-review request, set its base branch, labels, reviewer, and description, or merge it after the requested checks pass.

It removes the need to remember the many steps and safety checks involved in sending a code change for review. It also helps keep test results and change notes in the request.

pr-flow — Skill for Claude Code and Codex by me-cedric/agent-compass

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 me-cedric/agent-compass --skill pr-flow

Clone the repo

git clone --depth 1 https://github.com/me-cedric/agent-compass

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/me-cedric/agent-compass/pr-flow/github.svg)](https://agentmods.dev/skills/me-cedric/agent-compass/pr-flow)

Your own site

<a href="https://agentmods.dev/skills/me-cedric/agent-compass/pr-flow"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/pr-flow/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/me-cedric/agent-compass/pr-flow"><img src="https://agentmods.dev/badge/skills/me-cedric/agent-compass/pr-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,272 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.01272
Opus 5.5	$0.00000	$0.00509
Sonnet 5.5	$0.00000	$0.00254
Haiku 4.5	$0.00000	$0.00127

Measured 9d ago against content hash 100ed9b30061, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pr-flow 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 9d 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-flow/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pr-flow

Open a PR or MR only when the user asks. Opening one includes the push of its branch. The project rules in AGENTS.md win over the defaults below: base, branch name, labels, language.

Forge

Use the CLI of the origin remote: gh for GitHub, glab for GitLab (also a self-hosted GitLab). Never a forge MCP. Check the login first: gh auth status or glab auth status.

Before you open

git status --short. Commit only the files of this change.
Branch name: the project pattern, else <type>/<TICKET>-<short-kebab>. Rename a tool branch (claude/…, codex/…) before the first push.
Rebase onto the base: git fetch origin && git rebase origin/<base>. The guard blocks git merge and git pull without --rebase. Push a rebased branch with git push --force-with-lease origin <branch>, never --force. Ask the user in chat first. Claude Code and Copilot also show a permission prompt for it.
Review your own change locally with review ("Review your own change"). Post nothing. Fix the findings.
Run the gates (lint, typecheck, tests) and keep the exact counts for the body.
When a CHANGELOG.md of a touched app has ## [Unreleased], add the entry in this change.

Base

The base that the project declares. Else develop when git ls-remote --heads origin develop finds it. Else the default branch: gh repo view --json defaultBranchRef -q .defaultBranchRef.name or glab repo view -F json (.default_branch). A feature request onto the release branch is wrong. Ask first.

Title, labels, people

Title: <type>(<scope>): <subject> in the language of the project's requests, with the ticket key where the project puts it.
Labels: read them first (gh label list, glab label list). Use only labels that exist. Never ask about them.
- One type label from the commit type, for example feat → feature, fix → bugfix or fix, docs → documentation, ci/build → ci, dependency bumps → dependencies.
- Each area label whose area the diff touches.
- Never a label that states a judgement: breaking-change, critical, confirmed. A person sets those.
Assignee: yourself. Reviewer: at least one. When the user names none, ask, and list the likely ones: gh api 'repos/{owner}/{repo}/contributors' --jq '.[].login' or git shortlog -sne --since=6.months -- <changed dirs>.

Read the full file on GitHub · 89 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.

references/body.md 3.2 KB

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.

9d ago First seen · 89 lines · 0 tokens per session scan A 100ed9b30061

Subscribe to this mod's changes

pr-flow is a skill published in the GitHub repository me-cedric/agent-compass (3 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,272 tokens. 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 2026-10-19.

Git and workflow agent-skills agentic-ai ai ai-agents automation claude

pr-flow

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

pr-flow

Forge

Before you open

Base

Title, labels, people

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

release-announcement

github-pr-workflow

agent-release-manager

agent-release-swarm

agent-repo-architect

agent-github-modes