pr-hygiene

pr-hygiene is a skill for Claude Code, Codex from iCodeCraft/anti-slop. It costs 57 tokens per session (414 once invoked), scanned A, original, MIT.

A pull request, or PR, is a proposed code change sent for review before it is merged. PR hygiene is a checklist and writing guide for making that change focused, understandable, and ready to review.

In plain words
What is it for?
It helps inspect the branch, remove temporary code, check staged files and scope, choose a clear title, and write the summary, test plan, risks, and follow-ups.
Why use it?
It catches debug leftovers, unrelated edits, missing test notes, exposed local files, and unclear descriptions before reviewers see the PR.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps inspect the branch, remove temporary code, check staged files and scope, choose a clear title, and write the summary, test plan, risks, and follow-ups.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/icodecraft/anti-slop/pr-hygiene
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.

Any agent
npx skills add iCodeCraft/anti-slop --skill pr-hygiene
Clone the repo
git clone --depth 1 https://github.com/iCodeCraft/anti-slop

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 pr-hygiene

README.md
[![agentmods](https://agentmods.dev/badge/skills/icodecraft/anti-slop/pr-hygiene/github.svg)](https://agentmods.dev/skills/icodecraft/anti-slop/pr-hygiene)
Your own site
<a href="https://agentmods.dev/skills/icodecraft/anti-slop/pr-hygiene"><img src="https://agentmods.dev/badge/skills/icodecraft/anti-slop/pr-hygiene/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 pr-hygiene

Your own site · 80×15
<a href="https://agentmods.dev/skills/icodecraft/anti-slop/pr-hygiene"><img src="https://agentmods.dev/badge/skills/icodecraft/anti-slop/pr-hygiene.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 414 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.
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 $0.00057 $0.00414
Opus 5 $0.00028 $0.00207
Sonnet 5 $0.00011 $0.00083
Haiku 4.5 $0.00006 $0.00041

Measured 11d ago against content hash c64d6f6c2160, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pr-hygiene 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 11d 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/pr-hygiene/SKILL.md · 59 lines

What it actually says

PR Hygiene

Turn the current work into a PR a human can review in one pass.

Before opening

  • Branch contains one logical change (or clearly labeled stacked commits)
  • No leftover console.log, debugger, TODO: temp, commented-out blocks you added
  • No unrelated formatting-only churn
  • Secrets, .env, and local-only files are not staged
  • Diff matches the stated goal — nothing "extra helpful"

Description template

Use this structure (adapt section names to the host: GitHub/GitLab):

## Summary
<1–3 bullets: what and why>

## Test plan
- [ ] <how you verified>
- [ ] <edge case worth checking>

## Notes
<risks, follow-ups, screenshots if UI>

Commit / PR title

  • Imperative, specific: fix checkout: reject expired discount codes
  • Not: update stuff, fix, WIP, address comments

Reviewer empathy

Call out:

  • Files that look scary but are mechanical (renames, generated)
  • Behavior that changed for callers/API consumers
  • Anything you are unsure about

Anti-patterns

  • NEVER mix refactor + feature + dependency bump in one PR unless required
  • NEVER force-push shared branches without warning
  • NEVER open a PR with "tests TBD" and no plan
  • NEVER bury breaking changes in the middle of the description

If asked to open the PR

  1. Summarize the diff in your own words first
  2. Draft title + body with the template
  3. List residual risks in one short section
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. 11d ago First seen · 59 lines · 57 tokens per session scan A c64d6f6c2160

Subscribe to this mod's changes

pr-hygiene is a skill published in the GitHub repository iCodeCraft/anti-slop (27 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 414 once invoked, about $0.0003 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