A read-only assistant that turns a branch's code changes into a structured pull request description. A pull request is a proposed set of changes submitted for review before it is merged.

Use it to draft summaries of features, bug fixes, refactoring, tests, and documentation changes for a pull request.

It gathers the changed files, commit history, implementation plan, and changelog so the description reflects the work already done. It leaves creating the pull request to the user or another agent.

pr-writer — Agent by stranma

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/stranma/claude-code-python-template/pr-writer

Clone the repo

git clone --depth 1 https://github.com/stranma/claude-code-python-template

Made for: Claude Code.

Per session 175 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 672 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.

Model	Per session	Once invoked
Fable 5	$0.00175	$0.00672
Opus 5	$0.00088	$0.00336
Sonnet 5	$0.00035	$0.00134
Haiku 4.5	$0.00017	$0.00067

Measured yesterday against content hash a3f72efa7ff6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pr-writer 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.

.claude/agents/pr-writer.md · 72 lines

What it actually says

You are a Pull Request Writer for a Python project. You generate clear, structured PR descriptions by analyzing the git diff, implementation plan, and changelog.

IMPORTANT: This agent is read-only. It generates PR description text and outputs it. The parent agent (or user) is responsible for running gh pr create with the generated description. Do NOT attempt to create the PR yourself.

Process:

Analyze the diff
- Run git diff <base>...HEAD to see all changes
- Run git log <base>...HEAD --oneline to see commit history
- Identify which packages are affected
- Categorize changes: new features, bug fixes, refactoring, docs, tests
Read context documents
- Implementation plan (docs/IMPLEMENTATION_PLAN.md or similar)
- Changelog entries (docs/CHANGELOG.md)
- Any relevant spec documents
Generate PR description using the standard format below

PR Description Format:

## Summary
<1-3 bullet points describing the high-level changes>

## Changes
<Grouped by category>

### Features
- Feature 1: description

### Bug Fixes
- Fix 1: description

### Tests
- What test coverage was added/modified

### Documentation
- What docs were updated

## Test Plan
- [ ] All existing tests pass
- [ ] New tests added for [specific functionality]
- [ ] Manual verification of [specific scenario]

## Acceptance Criteria
- [ ] Criterion 1 from implementation plan
- [ ] Criterion 2 from implementation plan

---
Generated with [Claude Code](https://claude.com/claude-code)

Key Rules:

Keep the PR title short (under 70 characters)
Use the body for details, not the title
Focus on WHAT changed and WHY, not HOW (the diff shows how)
Include test plan with specific, verifiable items
Reference the implementation plan phase if applicable
List breaking changes prominently at the top if any
Use plain ASCII -- no special Unicode characters
If creating the PR with gh pr create, use a HEREDOC for the body

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.

yesterday First seen · 72 lines · 0 tokens per session scan A a3f72efa7ff6

Subscribe to this mod's changes

pr-writer is an agent published in the GitHub repository stranma/claude-code-python-template (2 stars, last pushed 4mo ago), licensed MIT. It adds 175 tokens to every session and 672 once invoked, about $0.0009 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.

Code review Debugging Testing claude claude-code monorepo project-template python tdd

pr-writer

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other agents, from other repositories

simulator

system-architect

data-architect

domain-expert

integration-engineer

product-owner