ss-create-pr

ss-create-pr is a skill for Claude Code, Codex from lbk-open/super-spec. It costs 113 tokens per session (3,360 once invoked), scanned A, original, Apache-2.0.

A final delivery workflow that checks completed code, cleans up the change, rebases it onto the target branch, and opens a GitHub pull request or GitLab merge request. Rebasing updates the work with the latest target-branch history.

In plain words
What is it for?
Use it after coding and review are finished, when the change is ready to submit or land in a Git repository.
Why use it?
It catches failing tests, debug leftovers, conflicts, and other problems before review. If a request cannot be opened, it can instead leave a clean commit history and written summary.

Skill for Claude CodeCodex

Part of the super-spec plugin — 20 skills shipped together

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/lbk-open/super-spec/ss-create-pr
Any agent
npx skills add lbk-open/super-spec --skill ss-create-pr
Clone the repo
git clone --depth 1 https://github.com/lbk-open/super-spec

Made for: Claude Code, Codex.

Or install super-spec, the plugin that ships this one along with the rest of its 20 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 ss-create-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/lbk-open/super-spec/ss-create-pr.svg)](https://agentmods.dev/skills/lbk-open/super-spec/ss-create-pr)
Your own site
<a href="https://agentmods.dev/skills/lbk-open/super-spec/ss-create-pr"><img src="https://agentmods.dev/badge/skills/lbk-open/super-spec/ss-create-pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,360 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 $0.00113 $0.03360
Opus 5 $0.00056 $0.01680
Sonnet 5 $0.00023 $0.00672
Haiku 4.5 $0.00011 $0.00336

Measured 3d ago against content hash 50e8ccdc3f3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ss-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 3d 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/ss-create-pr/SKILL.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Pull/Merge Request

Finalize development work once coding and review are done: run pre-flight checks, clean up, rebase, and open a PR/MR — or, if that's not possible, land the work with a clean conventional-commit history and a written summary instead.

Core principle: archive specs → verify → clean → rebase → verify again → ship. Never open a PR/MR with failing tests, debug artifacts, unresolved conflicts, or an unarchived delta spec. Avoid redundant test runs — if a prior coding step already verified tests at the current commit, trust that result.

This is the last step of a development workflow. It assumes implementation is complete (e.g., via the ss-coding skill or manual work) and review is done (e.g., via the ss-code-review skill or manual review), with all review issues addressed.

Inputs

  • Target branch (optional — defaults to the remote's detected default branch).
  • --draft to open the PR/MR as a draft.
  • Delivery mode, if this skill is running standalone rather than as part of a larger workflow: full (the normal case — this skill actually opens a PR/MR) or lite (the calling workflow already decided to skip PR creation and land changes locally; if so, skip straight to "Local fallback" below).

Ground rules

  1. Tests must pass before opening a PR/MR. If they haven't been verified at the current commit, run them; if they fail, stop and fix first. Don't re-run tests already verified at the same commit.
  2. No debug artifacts — stray console.log, debugger statements, TODO/HACK markers, disabled test selectors, secrets — must be removed first.
  3. Rebase, never merge the target branch into the feature branch.
  4. Verify again after rebase only if the rebase actually changed code. A no-op rebase (already up to date) needs no re-verification.
  5. Never force-push without explicit consent. A first-time push never needs force.
  6. The PR/MR description must be substantive — auto-generate one from the commit history if the user doesn't supply one.
  7. Archive any active delta spec first — run the ss-archive skill; it's idempotent and no-ops when there's no active delta.

Read the full file on GitHub · 257 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. 3d ago First seen · 257 lines · 113 tokens per session scan A 50e8ccdc3f3e

Subscribe to this mod's changes

ss-create-pr is a skill published in the GitHub repository lbk-open/super-spec (1 stars, last pushed 12d ago), licensed Apache-2.0. It adds 113 tokens to every session and 3,360 once invoked, about $0.0006 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

amazon-reviews-api-skill

This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…

browser-act/skills · 124 tokens

amazon-competitor-analyzer

Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.

browser-act/skills · 48 tokens

muapi-media-editing

Edit and enhance images and videos with AI via muapi.ai — prompt-based editing, upscaling, background removal, face swap, lipsync, video effects, and more.

SamurAIGPT/Generative-Media-Skills · 41 tokens

ctf-malware

Provides malware analysis and network traffic techniques for CTF challenges. Use when analyzing obfuscated scripts, malicious packages, custom crypto protocols, C2 traffic, PE/.NET binaries, RC4/AES encrypted communications, YARA rules, shellcode analysis, memory forensics for malware (Volatility malfind, process…

ljagiello/ctf-skills · 101 tokens

research

Conduct preliminary research on a topic and generate research outline. For academic research, benchmark research, technology selection, etc.

Weizhena/Deep-Research-skills · 25 tokens

ecommerce-landing-page

Audit and optimize e-commerce landing pages for conversion. CTA placement, trust signals, page structure, copy optimization, and A/B testing strategy for product pages, collection pages, and campaign landing pages.

nexscope-ai/eCommerce-Skills · 45 tokens