github-workflow

A workflow guide for managing GitHub pull requests, including stacked pull requests, reviews, and automated checks. A pull request is a proposed change awaiting review before it is merged.

In plain words
What is it for?
Use it when creating or updating pull requests, maintaining a stack of related pull requests, replying to review comments, resolving discussions, or checking CI results.
Why use it?
It gives the agent repository-specific rules and commands for branching, checking changes, handling review feedback, and working with GitHub Actions or CircleCI.

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/kyleve/stuff/github-workflow
Any agent
npx skills add kyleve/Stuff --skill github-workflow
Clone the repo
git clone --depth 1 https://github.com/kyleve/Stuff

Made for: Claude Code, Codex.

Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,091 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 $0.00074 $0.04091
Opus 5 $0.00037 $0.02046
Sonnet 5 $0.00015 $0.00818
Haiku 4.5 $0.00007 $0.00409

Measured yesterday against content hash 65ae6f32707d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-workflow 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 yesterday.

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/github-workflow/SKILL.md · 329 lines

How it starts

The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub workflow for this repo. Read root AGENTS.md first for always-on commit and test invariants. This skill assumes those.

Prerequisites

  • Never commit on main. Branch first and keep every commit for one piece of work on that one branch.
  • Run checks in proportion to risk. Pure documentation or comment-only changes can skip checks that cannot exercise them. Record skipped checks in the PR. Never push a known-red tree.

Tools

Job Tool
Read PRs, checks, comments, issues gh
Download CircleCI failure artifacts ./circleci-artifacts <job-uuid-or-url>
Create or update a PR ManagePullRequest when available; otherwise gh pr create / gh pr edit
Create, update, sync, or merge a PR stack gh stack
Reply on a review thread ManagePullRequest post_comment with in_reply_to, or gh api
Resolve a review thread ManagePullRequest resolve_comment when asked

Cloud agents: use ManagePullRequest for create/update/reply — not gh pr create / gh pr edit. Local sessions can use gh throughout.

Stacked PRs are the exception: use gh stack in every environment for stack topology and lifecycle. ManagePullRequest and gh pr edit can refine an individual PR's title or body after submission. They must not manually wire base branches or substitute for gh stack.

Unsolicited top-level PR comments (not review replies) still need an explicit user request. Review feedback is different: when the user asks you to address comments (PTAL, address review, fix the feedback), that authorizes replies on the threads you fix, decline, or defer — see Review comments.

Branch, push, and plan handoff

  • Multi-step work lands one commit per step, so history stays bisectable and can land piecewise — including pure-groundwork steps, which say so in the body.
  • Commit completed work eagerly. Once a coherent change is verified, commit it unless the user explicitly asks to keep it uncommitted.
  • Push the branch as commits land. Do not accumulate unpushed work or wait for the user to ask.
  • Plan-driven work finishes with a PR. After executing an approved plan (all steps verified), push the branch and open a ready-for-review PR before handing back — or update the existing PR if one is already open. Never leave finished plan work local-only, unpushed, or without a PR the user can review.
  • Any finished task on a feature branch follows the same push habit. Open or update the PR when the branch carries reviewable work, not only after formal plans.

Read the full file on GitHub · 329 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. yesterday First seen · 329 lines · 74 tokens per session scan A 65ae6f32707d

Subscribe to this mod's changes

github-workflow is a skill published in the GitHub repository kyleve/Stuff (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 74 tokens to every session and 4,091 once invoked, about $0.0004 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens