AICodingFlow: Skill for Claude Code

.agents/skills/create-pr/SKILL.md

create-pr is a skill for Claude Code, Codex from Terry-Mao/AICodingFlow. It costs 18 tokens per session (617 once invoked), scanned A, original, MIT.

A workflow for creating or updating a GitHub pull request, which is a request for others to review and merge code changes. It prepares the request from the current branch and its complete difference from the target branch.

In plain words
What is it for?
Use it to check the branch and target, review the full change set, handle needed base-branch updates, and prepare the pull request title, description, validation notes, and issue link.
Why use it?
It reduces the chance that a pull request contains accidental files, secrets, unresolved conflicts, or missing validation. It also keeps an existing open request updated instead of creating a duplicate.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is Terry-Mao/AICodingFlow's own configuration. It tells Claude Code and Codex how to work on AICodingFlow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AICodingFlow configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Terry-Mao/AICodingFlow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Terry-Mao/AICodingFlow/main/.agents/skills/create-pr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Terry-Mao/AICodingFlow

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.

agentmods badge for create-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/terry-mao/aicodingflow/create-pr/github.svg)](https://agentmods.dev/skills/terry-mao/aicodingflow/create-pr)
Your own site
<a href="https://agentmods.dev/skills/terry-mao/aicodingflow/create-pr"><img src="https://agentmods.dev/badge/skills/terry-mao/aicodingflow/create-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 create-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/terry-mao/aicodingflow/create-pr"><img src="https://agentmods.dev/badge/skills/terry-mao/aicodingflow/create-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 617 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.00617
Opus 5.5 $0.00007 $0.00247
Sonnet 5.5 $0.00004 $0.00123
Haiku 4.5 $0.00002 $0.00062

Measured today against content hash 4b35529e19f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 today.

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 · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

create-pr

Use this after git-push when the user asks to create, update, or open a pull request. It prepares PR metadata; it does not implement code, commit, push, or modify issues.

Prepare

Inspect the current branch, worktree, and repository default PR base. A dirty worktree must be intentionally excluded before continuing. Review the complete base-to-head diff for accidental files, secrets, conflict markers, generated churn, and missing validation. Sync the base into the branch when needed; if that creates conflicts, resolve, validate, commit, and push the resolution.

Build a concise title and body from the issue, branch, commits, or user request. Use a Conventional Commit title for the PR: <type>[(scope)]: <description>. Choose the type from the actual change (for example, feat, fix, docs, refactor, test, or chore); include a scope only when it clarifies the change. Keep the description in the repository's prose language, for example fix(ci): 修复审查分发. When updating a PR, keep an existing title if it follows this format and still describes the complete diff; otherwise revise it. Include ## Summary, ## Testing, ## Risk, and ## How to revert, plus a known issue link (Closes, Fixes, or Refs). State actual test results, the relevant risk and a concrete rollback action; never invent results or an issue ID. Preserve any manually written sections when updating an open PR. Before submitting, save the exact body and run python3 .github/scripts/validate_pr_body.py <body-file>.

Create or update

First check only for an open PR from the current branch. Do not use gh pr view as the existence check because it may resolve a previously merged or closed PR:

pr_url="$(gh pr list --state open --head "$branch" --json url --jq '.[0].url' --limit 1)"

If an open PR exists, read its current body, preserve manual content, and update it:

gh pr edit "$pr_url" --title "$title" --body-file "$body_file"

Otherwise create a new PR. A merged or closed PR with the same branch name is not reusable:

Read the full file on GitHub · 60 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. today Changed · +6 lines 4b35529e19f9
  2. yesterday Changed · +4 lines 40b32ebdbac6
  3. 1mo ago First seen · 50 lines · 18 tokens per session scan A f0b495ec0c08

Subscribe to this mod's changes

create-pr is a skill published in the GitHub repository Terry-Mao/AICodingFlow (169 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 617 once invoked, about $0.0001 per session on Opus 5.5. 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

pr

Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.

Yeachan-Heo/oh-my-claudecode · 47 tokens

merge-batch

Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.

diegosouzapw/OmniRoute · 46 tokens

otto-pr-review-loop

Run Polly and OCR on a PR until all findings settle.

omnigent-ai/omnigent · 17 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

github-contributor

A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.

daymade/claude-code-skills · 105 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