pr-workflow

A workflow for preparing a Git branch and pull request for human review. A branch is an isolated line of changes, and a pull request is a proposal to merge those changes into another branch.

In plain words
What is it for?
Use it before opening a pull request or when asked to submit work for review. It covers pre-flight checks, commit cleanup, pushing the branch, writing the request, self-review, and handling feedback.
Why use it?
It turns working code into a clean, understandable review package. It checks tests and scope, keeps commits organized, and provides a structured explanation for reviewers.

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/andreaswasita/copilot-agents-dojo/pr-workflow
Any agent
npx skills add andreaswasita/copilot-agents-dojo --skill pr-workflow
Clone the repo
git clone --depth 1 https://github.com/andreaswasita/copilot-agents-dojo

Made for: Claude Code, Codex.

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,089 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 $0.00017 $0.01089
Opus 5 $0.00009 $0.00544
Sonnet 5 $0.00003 $0.00218
Haiku 4.5 $0.00002 $0.00109

Measured yesterday against content hash ccff4e00a396, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pr-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.

skills/pr-workflow/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Workflow Skill

Takes a working branch from "the code works" to "this is ready for a human reviewer": pre-flight checks, clean commits, a real description, self-review, and disciplined handling of feedback. Does NOT create draft "WIP" PRs that sit open for days.

When to Use

  • Preparing a feature branch for review.
  • Opening a pull request.
  • Writing or rewriting a PR description.
  • Restructuring commits before review.
  • The user says "submit this" or "get this ready for review".

Prerequisites

  • git configured with author identity.
  • gh CLI authenticated for PR creation (or web access to the host).
  • The powershell tool to run git, the test suite, and scripts/verify.sh.
  • A green test suite on the branch.

How to Run

1. Pre-flight: tests green, working tree clean, scope reviewed.
2. Clean up commits with interactive rebase if needed.
3. Push the branch.
4. Open the PR with a structured description.
5. Self-review the diff (use the `code-review` skill).
6. Address feedback in new commits — do not force-push during active review.

Quick Reference

Step Command (run via powershell) Notes
Pre-flight tests npm test / pytest / go test ./... Must exit 0
Dojo gate bash scripts/verify.sh --check Must exit 0
Clean tree git status --porcelain Empty
Review scope git diff main --stat Matches plan
Tidy history git rebase -i main Optional, before push
Push git push -u origin <branch> First push of branch
Open PR gh pr create --fill then edit body Or use the GitHub UI

Procedure

Step 1: Pre-Flight

Run via the powershell tool:

bash scripts/verify.sh --check
git status --porcelain
git diff main --stat

If anything fails, fix it before proceeding. A PR opened on a red branch wastes reviewer time.

Step 2: Clean Up Commits

Interactive rebase if the history is noisy:

git rebase -i main

Squash fixups. Reword unclear messages. Aim for a sequence that reads like a story:

Read the full file on GitHub · 146 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 · 146 lines · 17 tokens per session scan A ccff4e00a396

Subscribe to this mod's changes

pr-workflow is a skill published in the GitHub repository andreaswasita/copilot-agents-dojo (51 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 1,089 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.

Related

Other skills, from other repositories

pr-triage

PR triage: audit open PRs, deep review selected ones, draft and post review comments. Args: "all" to review all, PR numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French.

rtk-ai/rtk · 64 tokens

decision-ledger

Use throughout a session to track open decision threads and draft them to .governance/claims/ when they close. 会话全程使用:跟踪开放的决策线程,线程闭合时起草到账本。Records what was decided and why, at the moment it is decided, so the reasoning survives a lost account, a deleted transcript or a compaction. Drafting is automatic and free…

johnrucnapier-sketch/ACGM-for-Claude-Code · 99 tokens

governance-bootstrap

Use when setting up this governance system from zero in a project that has none. 在一个尚无治理的项目里从零建治理时调用。This is a HUMAN-DRIVEN, multi-session guided checklist — NOT an autonomous action. 这是人驱动的多会话引导清单,非自主执行。Walks the 8-step bootstrap recipe — audit, constitution, rewrite root rules, ADR log, snapshot + drift scripts…

johnrucnapier-sketch/ACGM-for-Claude-Code · 107 tokens

session-grounding

Use at the START of every new, resumed, cleared or compacted session, and when picking up half-done work in a governed project — before taking ANY action. 在每个新开/续接/clear/compact 后的 Session,以及接手半截工作时,动手前先走此流程。Read current truth sources, identify track and scope, report five items and WAIT for human confirmation. A…

johnrucnapier-sketch/ACGM-for-Claude-Code · 105 tokens

docx

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of "Word doc", "word document", ".docx", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…

AndreasKarz/Vibe-Coding-Dev-Setup · 168 tokens

prompt-creator

Expert guide for crafting high-quality, production-grade prompts and system prompts for LLMs. Use when a user wants to create, improve, debug, or evaluate a prompt — whether for Claude, GPT, or any other LLM. Triggers on create prompt, write prompt, improve prompt, system prompt, prompt engineering, prompt template…

AndreasKarz/Vibe-Coding-Dev-Setup · 106 tokens