pr-scribe

pr-scribe is a skill for Claude Code, Codex from mdelapenya/coding-skills. It costs 82 tokens per session (1,896 once invoked), scanned A, original, MIT.

A tool for writing a concise pull request description and a Conventional Commits title from a pull request's code changes. A pull request is a proposed set of changes for review, and Conventional Commits is a shared format for commit titles.

In plain words
What is it for?
Summarizing pull request changes, filling in a pull request body, and updating titles and descriptions on GitHub or GitLab.
Why use it?
It turns a code diff into review text and can apply the result to the pull request, while following an existing template when available.

Skill for Claude CodeCodex

Part of the coding-skills plugin — 5 skills, 5 agents 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/mdelapenya/coding-skills/pr-scribe
Any agent
npx skills add mdelapenya/coding-skills --skill pr-scribe
Clone the repo
git clone --depth 1 https://github.com/mdelapenya/coding-skills

Made for: Claude Code, Codex.

Or install coding-skills, the plugin that ships this one along with the rest of its 5 skills, 5 agents.

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-scribe

README.md
[![agentmods](https://agentmods.dev/badge/skills/mdelapenya/coding-skills/pr-scribe.svg)](https://agentmods.dev/skills/mdelapenya/coding-skills/pr-scribe)
Your own site
<a href="https://agentmods.dev/skills/mdelapenya/coding-skills/pr-scribe"><img src="https://agentmods.dev/badge/skills/mdelapenya/coding-skills/pr-scribe.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,896 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 $0.00082 $0.01896
Opus 5 $0.00041 $0.00948
Sonnet 5 $0.00016 $0.00379
Haiku 4.5 $0.00008 $0.00190

Measured 4d ago against content hash 02669731be83, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pr-scribe 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.

skills/pr-scribe/SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Scribe

Generate a concise description for a pull request by analyzing its diff.

Supported Platforms

This skill supports multiple code hosting platforms. Each platform has its own reference file under references/ with platform-specific commands.

Currently supported:

  • GitHub — see references/github.md
  • GitLab — see references/gitlab.md
  • biomelab — see references/biomelab.md (special context: writes outputs to .biomelab/ files instead of updating PRs remotely)

Planned:

  • Bitbucket

When invoked, first detect the platform from git remote -v and check for biomelab context (.biomelab/ directory), then load the corresponding reference file for platform-specific commands.

Workflow

Step 1: Detect platform and biomelab context

Check if .biomelab/ directory exists in the repository root. If yes, load .biomelab/topic.md (which defines biomelab-specific instructions and naming conventions).

Then detect the platform from git remote -v and parse unique org/repo pairs from fetch URLs. Detect the platform (GitHub, GitLab, etc.) from the URL and load the matching reference file.

  • Single remote: use it automatically.
  • Multiple remotes: use AskUserQuestion to prompt with a numbered list, default to the first:

    Multiple remotes found:

    1. origin → org/repo
    2. upstream → org/repo Which remote? [1]

If the platform is not yet supported, inform the user and stop.

Step 2: Determine the PR number

If $ARGUMENTS contains a number, use it. Otherwise use AskUserQuestion to ask:

PR number:

Step 3: Fetch PR metadata and diff

Using the platform-specific commands from the loaded reference, fetch the PR metadata (title, body, base/head branches, commits) and the full diff.

Keep the full response — commit messages are reused in Step 5.

Step 4: Check for a PR template

Using the platform-specific template paths from the loaded reference, look for a PR template.

If found, use its structure (headings, sections, checkboxes) as the skeleton. Fill each section from the diff analysis. Preserve checkbox items from the template.

Read the full file on GitHub · 169 lines

Files

What ships with it

3 files 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 · 169 lines · 82 tokens per session scan A 02669731be83

Subscribe to this mod's changes

pr-scribe is a skill published in the GitHub repository mdelapenya/coding-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 1,896 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.