A workflow for creating a pull request on GitHub or a merge request on GitLab from the current Git branch. It prepares the title and description after checking the repository state and required tests.

Verifying a branch, running the project’s pre-review checks, pushing commits, and opening a request against the chosen base branch.

It catches failed checks or unsuitable branch states before changes are pushed for review.

create-pr — Skill for Claude Code and Codex by desplega-ai

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 desplega-ai/agent-swarm --skill create-pr

Clone the repo

git clone --depth 1 https://github.com/desplega-ai/agent-swarm

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/desplega-ai/agent-swarm/create-pr.svg)](https://agentmods.dev/skills/desplega-ai/agent-swarm/create-pr)

Your own site

<a href="https://agentmods.dev/skills/desplega-ai/agent-swarm/create-pr"><img src="https://agentmods.dev/badge/skills/desplega-ai/agent-swarm/create-pr.svg" alt="Measured on agentmods" height="20"></a>

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 510 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00022	$0.00510
Opus 5	$0.00011	$0.00255
Sonnet 5	$0.00004	$0.00102
Haiku 4.5	$0.00002	$0.00051

Measured 8d ago against content hash d7520f1f6215, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

create-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 8d 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.

plugin/pi-skills/create-pr/SKILL.md · 40 lines

What it actually says

Create Pull Request / Merge Request

Create a PR (GitHub) or MR (GitLab) from the current branch with an auto-generated title and description.

Provider detection: Check the remote URL:

If github.com → use gh CLI
If gitlab.com or gitlab. → use glab CLI

Arguments

base-branch (optional): Branch to merge into (defaults to main or repo default)

Prerequisites

You should be working in a repository cloned to /workspace/personal/<repo-name>.

Workflow

Verify state — confirm you're in a git repo, not on main/master, and have commits to push.
Run PR checks (MANDATORY) — Run ALL checks listed in the "PR Checks" section of your Repository Guidelines. Run each command/task sequentially. If ANY check fails, fix the issue and re-run until all pass. If no guidelines are defined, check the project's CLAUDE.md for a pre-PR checklist and run those. Do NOT proceed until all checks pass.
Push the branch — git push -u origin HEAD
Gather context — review commit messages and changed files since diverging from base.
Generate title and description:
- Title: Concise summary (conventional commit style if the repo uses it)
- Description: Summary of changes, notable items, testing done, related issues
Create the PR/MR using gh pr create or glab mr create.
Check CI status — After creating the PR, wait ~30 seconds, then check CI with gh pr checks <pr-number> (GitHub) or glab mr view --json pipelines (GitLab). If any check is failing, investigate the failure, fix it, push the fix, and re-check. Repeat until CI is green.
Report the PR/MR URL and CI status.

Tips

Link related issues using Fixes #123 or Closes #123 in the description
Keep PRs focused — one logical change per PR
If the branch has many commits, summarize the overall change rather than listing each commit

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.

8d ago First seen · 40 lines · 22 tokens per session scan A d7520f1f6215

Subscribe to this mod's changes

create-pr is a skill published in the GitHub repository desplega-ai/agent-swarm (754 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 510 once invoked, about $0.0001 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 2026-08-30.

Git and workflow agentic agentic-framework agentic-os ai-agents ai-memory-system harness-execution-layer

symlink-manager

Create, audit, repair, and document cross-platform symlinks that work correctly on both Windows and macOS/Linux. Use this skill whenever the user mentions symlinks, symbolic links, junction points, .gitconfig symlinks, broken links after git pull, cross-platform path issues, or needs help with ln -s equivalents on…

richfrem/agent-plugins-skills · 180 tokens

github-issue-backlog-agent

Bridge skill for escalating ephemeral local task scratchpad items (tasks/.md) into durable, taxonomy-validated, evidence-rich GitHub Issues. USE ONLY when promoting a single-session local task into durable repository backlog. DO NOT USE for managing local kanban boards (use task-agent instead) or directly…

richfrem/agent-plugins-skills · 83 tokens

issue-pr-lifecycle-agent

Skill for orchestrating the end-to-end GitHub issue lifecycle flow: Issue -> Worktree -> Implementation -> PR Creation -> Resolution Closure. USE ONLY when running or dry-running full lifecycle orchestration for resolving an issue with a PR. DO NOT USE for isolated worktree management only (use issue-worktree-agent)…

richfrem/agent-plugins-skills · 81 tokens

issue-worktree-agent

Skill for creating and managing isolated git worktrees (.worktrees/issue-NNN) for issue execution branches. USE ONLY when setting up or cleaning up isolated git worktrees for specific issue execution. DO NOT USE for managing local task files (use task-agent) or escalating tasks to issues (use…

richfrem/agent-plugins-skills · 75 tokens

github-issue-prioritizer

Automatically ranks GitHub issues (P0-P3) based on friction tier, frequency, and blockages, synchronizing priority labels and GitHub Projects v2 custom fields.

richfrem/agent-plugins-skills · 43 tokens

github-issue-agent

Agent skill for safe, dry-run-first, deduplicated, root-cause-consolidated, evidence-validated, and secret-redacted logging of repository execution friction into GitHub Issues. USE ONLY for durable repository bugs, execution friction (T1-T3), map debt, and architectural improvements. DO NOT USE for temporary…

richfrem/agent-plugins-skills · 80 tokens