pr-conventions

pr-conventions is a skill for Claude Code, Codex from PrabhdeepSingh/claude-plugins. It costs 80 tokens per session (4,084 once invoked), scanned A, original, MIT.

A set of rules for writing and maintaining pull request descriptions and responding to review comments. A pull request is a proposed code change submitted for review before it is merged.

In plain words
What is it for?
Use it when opening or updating a pull request, replying to reviewers, or shipping changes through the related workflow. It helps select the repository's template and keep review information current.
Why use it?
It keeps the description matched to the kind of change, linked to the relevant issue, and updated when fixes are made. It also defines how to handle human and automated review threads.

Skill for Claude CodeCodex

Part of the sonu plugin — 26 skills, 3 commands shipped together

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/prabhdeepsingh/claude-plugins/pr-conventions
Any agent
npx skills add PrabhdeepSingh/claude-plugins --skill pr-conventions
Clone the repo
git clone --depth 1 https://github.com/PrabhdeepSingh/claude-plugins

Made for: Claude Code, Codex.

Or install sonu, the plugin that ships this one along with the rest of its 26 skills, 3 commands.

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-conventions

README.md
[![agentmods](https://agentmods.dev/badge/skills/prabhdeepsingh/claude-plugins/pr-conventions.svg)](https://agentmods.dev/skills/prabhdeepsingh/claude-plugins/pr-conventions)
Your own site
<a href="https://agentmods.dev/skills/prabhdeepsingh/claude-plugins/pr-conventions"><img src="https://agentmods.dev/badge/skills/prabhdeepsingh/claude-plugins/pr-conventions.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,084 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 $0.00080 $0.04084
Opus 5 $0.00040 $0.02042
Sonnet 5 $0.00016 $0.00817
Haiku 4.5 $0.00008 $0.00408

Measured 4d ago against content hash 71d2e6a6cf32, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pr-conventions 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 4d 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.

sonu/skills/pr-conventions/SKILL.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR conventions — right template, living description, honest replies

A PR body is the reviewer's briefing: it should match the change type so reviewers apply the right lens, stay accurate as fixes land, and every thread should get a reply that closes the loop. This skill handles all three.

When to apply this

  • Opening a PR (/sonu:ship Phase 1) — scan for a team template, classify the change type, fill the matching built-in template, embed the RISKS list in the risk section (Section A → B).
  • After fixes land (after /sonu:ship Phase 4 push, and within each Phase 6 re-review cycle) — re-render the description in place (Section C).
  • Responding to reviewer comments (/sonu:ship Phase 5, or standalone) — reply to every open inline thread with the right wording; resolve bot threads but leave human threads for the reviewer to resolve (Section D).

A — Discover the team template first

Before reaching for a built-in template, scan for the repo's own PR template. The team standard wins.

# Single-file locations take precedence over multi-template directories.
# Check files first; only look for a directory if no file is found.
# GitHub supports the template in .github/, the repo root, or docs/, in either case spelling —
# on a case-sensitive filesystem (Linux, dev containers) both spellings must be checked explicitly.
TEMPLATE_FOUND=""
for f in \
  ".github/PULL_REQUEST_TEMPLATE.md" ".github/pull_request_template.md" \
  ".github/PULL_REQUEST_TEMPLATE.txt" ".github/pull_request_template.txt" \
  ".github/PULL_REQUEST_TEMPLATE" ".github/pull_request_template" \
  "PULL_REQUEST_TEMPLATE.md" "pull_request_template.md" \
  "PULL_REQUEST_TEMPLATE.txt" "pull_request_template.txt" \
  "PULL_REQUEST_TEMPLATE" "pull_request_template" \
  "docs/PULL_REQUEST_TEMPLATE.md" "docs/pull_request_template.md" \
  "docs/PULL_REQUEST_TEMPLATE.txt" "docs/pull_request_template.txt" \
  "docs/PULL_REQUEST_TEMPLATE" "docs/pull_request_template"; do
  [ -f "$f" ] && { TEMPLATE_FOUND="SINGLE:$f"; break; }   # -f: extension-less names (GitHub allows them) only match files, so the dir scan below is unaffected
done
if [ -z "$TEMPLATE_FOUND" ]; then
  for d in ".github/PULL_REQUEST_TEMPLATE" ".github/pull_request_template" \
            "PULL_REQUEST_TEMPLATE" "pull_request_template" \
            "docs/PULL_REQUEST_TEMPLATE" "docs/pull_request_template"; do
    [ -d "$d" ] && { TEMPLATE_FOUND="MULTI:$d"; break; }
  done
fi
echo "$TEMPLATE_FOUND"

Read the full file on GitHub · 232 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 232 lines · 80 tokens per session scan A 71d2e6a6cf32

Subscribe to this mod's changes

pr-conventions is a skill published in the GitHub repository PrabhdeepSingh/claude-plugins (3 stars, last pushed 5d ago), licensed MIT. It adds 80 tokens to every session and 4,084 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

top-design

Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…

wondelai/skills · 113 tokens

design-everyday-things

Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…

wondelai/skills · 132 tokens

traction-eos

Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…

wondelai/skills · 147 tokens

watch

File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…

SethGammon/Citadel · 70 tokens

pr-watch

Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.

SethGammon/Citadel · 46 tokens

review

5-pass structured code review — correctness, security, performance, readability, consistency.

SethGammon/Citadel · 17 tokens