create-pr

A workflow for committing relevant changes and opening a templated draft pull request, then checking that the repository's review requirements are met. A pull request is a proposed code change submitted for review before merging.

In plain words
What is it for?
Use it with the repository's `/create-pr` command to inspect changes, run the required gate, create a branch or commit when needed, open a draft pull request, fix relevant CI issues, and mark the request ready for review.
Why use it?
It reduces missed checks and incomplete pull-request details. It also keeps the submitted changes focused, avoids empty commits, and handles repository-specific branch and stack rules.

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/frostney/gocciascript/create-pr
Any agent
npx skills add frostney/GocciaScript --skill create-pr
Clone the repo
git clone --depth 1 https://github.com/frostney/GocciaScript

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 954 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 $0.00043 $0.00954
Opus 5 $0.00022 $0.00477
Sonnet 5 $0.00009 $0.00191
Haiku 4.5 $0.00004 $0.00095

Measured 2d ago against content hash 14b0c456b037, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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/create-pr/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create PR

The request authorizes the repository's declared gates, relevant fixes and commits, PR metadata updates, one ordinary draft pull request or the confirmed native stack layers owned by the change, and their transitions to ready for review. It does not authorize unrelated changes.

When the branch belongs to a native GitHub stack, read ../git-workflow/references/github-stacks.md. The request then authorizes submission and metadata reconciliation for the confirmed stack layers owned by the current change, not unrelated branches.

  1. Inspect the working tree, staged diff, recent commits, and remote default branch.
  2. Stop if there are no relevant changes or commits ahead of the remote base. Continue without an empty commit when the work is already committed.
  3. If currently on the base branch, create a focused branch named from the issue or change.
  4. Run the repository's declared pre-PR gate unless it already passed on the unchanged current diff. Never claim an unobserved result.
  5. Stage only relevant files, excluding secrets and unrelated local work.
  6. Commit uncommitted work with a concise Conventional Commit subject. Never amend and never skip hooks.
  7. For an ordinary branch, push normally and set its upstream when needed. For a verified native stack, use gh stack submit; only its guarded official stack operations may rebase or push with force-with-lease.
  8. Title each pull request with a Conventional Commit subject covering the whole change, since the squash merge makes that title the commit subject on the base branch. Fill the matching PR template for each submitted layer, preserving its structure. If none exists, use Summary, Testing, and Linked issues. Keep the body proportional to the change. Put each closing keyword on its own line: Closes #N, and only on the layer that completes that issue.
  9. Open one draft PR against the remote default for an ordinary branch. For a stack, preserve bottom-to-top native topology and keep each new layer draft until that layer satisfies the remaining gates.
  10. Find the nearest applicable DEFINITION_OF_READY.md. If it exists, compare every criterion with the actual PR diff, tests, documentation, linked work, metadata, and validation evidence to identify anything the PR is missing. If absent after a real search, use this workflow's built-in gates.
  11. Fill every in-scope readiness gap. Add missing implementation, tests, documentation, or artifacts, or correct the PR body and links. For repository changes, validate, create a new commit, and push normally; metadata-only fixes require no commit. Never mark a criterion satisfied without observed evidence.
  12. Invoke delivery-wait's foreground wait checks-terminal operation with the repository, exact head, checkpoint, absolute deadline, and --json; the harness passively awaits it without model heartbeats. When it returns, inspect any unsuccessful logs, fix the in-scope root cause without weakening the gate, run the relevant local checks, create a new commit, push normally, and wait on the new exact head. If the host cannot passively await a subprocess, report the unsupported capability instead of polling through model turns.
  13. Keep the PR in draft while any readiness criterion or CI check is pending or failing. Continue monitoring pending checks; if they cannot reach a terminal result during the run, report their current state. Stop and report the exact blocker when satisfying it requires a material product decision, unrelated work, unavailable external service, or a change that cannot be validated safely.
  14. Once a PR is missing nothing required by the Definition of Ready and all applicable CI is observed green for its exact head, mark that PR ready for review. Return every affected URL, native stack order when applicable, final states, fixes made, and observed readiness and CI evidence.

Read the full file on GitHub · 75 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. 2d ago First seen · 75 lines · 43 tokens per session scan A 14b0c456b037

Subscribe to this mod's changes

create-pr is a skill published in the GitHub repository frostney/GocciaScript (20 stars, last pushed 6d ago), licensed MIT. It adds 43 tokens to every session and 954 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 2026-08-30.

Related

Other skills, from other repositories

qcad

Use when editing DXF files with a professional open-source 2D CAD application — CAM output, part libraries, isometric projection. QCAD: open-source 2D CAD with DXF as native format, scriptable via ECMAScript.

znlgis/opengis-skills · 53 tokens

oxc-docs

Comprehensive reference for the JavaScript Oxidation Compiler (Oxc) — a collection of high-performance JavaScript tools written in Rust. Covers parser design (lexer, AST, parser, errors, semantic analysis), architecture (parser, linter, test infrastructure, AST tools), ECMAScript specification and grammar, performance…

pledgeandgrow/pledge-skills · 131 tokens

git-step-commit

Analyze Git changes, split them into coherent commits, infer message language and format, optionally close supplied GitHub issues, and execute safely. Manage persistent global or repository preferences for review versus direct submission and automatic or specified commit-message language through native Git config.…

bosens-China/tc39-atlas · 134 tokens

manage-prd-docs

Automatically manage product requirements across current decisions in docs/PRD.md and docs/prd/, mature future plans under docs/plans/, and active implementation under docs/work/. Use whenever the conversation discusses, clarifies, versions, plans, implements, completes, splits, or migrates a product requirement or…

bosens-China/tc39-atlas · 132 tokens

modernize-ecmascript

当 Agent 编写或修改 JavaScript、TypeScript,用户要求按指定环境、输出版本、ES20xx 或具体语法编写代码,询问某项 ECMAScript 语法、标准内置 API 或提案能否采用,或者要求审查仓库中可简化、可现代化的写法时,应使用本 Skill。围绕目标文件真实经过的解析器、转换器和输出目标判断新语法能否安全采用,并按需读取 TC39 Atlas 的提案阶段、官方仓库、polyfill 与实现线索。.

bosens-China/tc39-atlas · 130 tokens

codebase-audit

Audits the current repository for systemic correctness, architecture, churn, simplification, clarity, test value, and operational risks using current source and reproducible probes. It can delegate evidence gathering across bounded capability and perspective lanes. Use when the user runs /codebase-audit or asks for an…

frostney/pascal-mcp-sdk · 70 tokens