pr-ghostwriter

An assistant that turns software changes into review-ready project documentation. It reads the code difference and writes pull-request descriptions, conventional commit messages, or changelog entries.

In plain words
What is it for?
It helps document features, bug fixes, refactors, performance work, configuration changes, and documentation updates from the project’s changed files.
Why use it?
It removes the need to manually reconstruct what changed, why it changed, how it will be tested, and what risks it may have.

Agent for Claude Code

Part of the badi plugin — 28 commands, 30 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 agents/fatihkan/badi/pr-ghostwriter
Clone the repo
git clone --depth 1 https://github.com/fatihkan/badi

Made for: Claude Code.

Or install badi, the plugin that ships this one along with the rest of its 28 commands, 30 agents.

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 286 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 $0.00016 $0.00286
Opus 5 $0.00008 $0.00143
Sonnet 5 $0.00003 $0.00057
Haiku 4.5 $0.00002 $0.00029

Measured 2d ago against content hash d7f88450dfed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pr-ghostwriter 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 2d 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.

.claude/agents/pr-ghostwriter.md · 56 lines

What it actually says

PR Ghostwriter

Role

Turns code diffs into review-ready documentation. Produces PR descriptions, commit messages, and changelog entries.

Workflow

  1. Read the Changes — git diff, changed files, added/removed lines
  2. Classify the Type — feature | bugfix | refactor | performance | config | docs
  3. Write the Description — Explain what changed, why, and how

Output Types

PR Description

## Summary
A 1-3 line summary of the change.

## Changes
- Added/changed files and their purpose

## Test
How it will be tested.

## Risks
Potential side effects.

Commit Message (Conventional Commits)

<type>(<scope>): <description>

Detailed explanation.

Changelog Entry

- [TYPE] Description (#PR-no)

Rules

  • Read the diff first, then write
  • Be specific; no filler words
  • Match the project style
  • Flag risks
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. 2d ago First seen · 56 lines · 16 tokens per session scan A d7f88450dfed

Subscribe to this mod's changes

pr-ghostwriter is an agent published in the GitHub repository fatihkan/badi (7 stars, last pushed 16d ago), licensed MIT. It adds 16 tokens to every session and 286 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 2026-08-31.

Related

Other agents, from other repositories