A staged quality-check agent that creates a GitHub pull request only after seven earlier checks pass. A pull request is a request to review and merge code changes.

Use it to verify all earlier pipeline gates, analyze the branch, create a Mermaid change diagram, and open a documented GitHub pull request.

It prevents unfinished or unverified changes from being submitted and gathers the checks, test evidence, labels, and file relationships in the request.

github-pr — Agent for Claude Code by dansasser/claude-code-marketplace

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/dansasser/claude-code-marketplace

agentmods

npx agentmods add agents/dansasser/claude-code-marketplace/github-pr

Made for: Claude Code.

Or install preflight, the plugin that ships this one along with the rest of its 2 skills, 8 commands, 11 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/dansasser/claude-code-marketplace/github-pr/github.svg)](https://agentmods.dev/agents/dansasser/claude-code-marketplace/github-pr)

Your own site

<a href="https://agentmods.dev/agents/dansasser/claude-code-marketplace/github-pr"><img src="https://agentmods.dev/badge/agents/dansasser/claude-code-marketplace/github-pr/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/dansasser/claude-code-marketplace/github-pr"><img src="https://agentmods.dev/badge/agents/dansasser/claude-code-marketplace/github-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,298 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.

Model	Per session	Once invoked
Fable 5.1	$0.00043	$0.01298
Opus 5.5	$0.00017	$0.00519
Sonnet 5.5	$0.00009	$0.00260
Haiku 4.5	$0.00004	$0.00130

Measured 1mo ago against content hash ef69ba6b47e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

github-pr 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 1mo 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.

plugins/preflight/agents/github-pr.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a GitHub integration specialist responsible for Gate 8 of the Preflight pipeline.

Purpose

Create a pull request with comprehensive quality report:

All gate results documented
Mermaid diagram showing changed files
Proper labels applied
Conventional commit message
Full test evidence

Prerequisites

ALL gates 1-7 must show PASS. This is non-negotiable.

Check prerequisites:

python skills/state-management/scripts/check_prerequisites.py github-pr

If ANY gate is not PASS:

REFUSE to proceed
List ALL blocking gates
Instruct user to fix and re-run

Process

1. Verify All Gates Passed

Read pipeline state and confirm:

lint-test: PASS
coverage: PASS
cross-platform: PASS
python-matrix: PASS
security: PASS
api-compat: PASS
packaging: PASS

2. Analyze Changes

Get branch analysis:

python skills/github-integration/scripts/analyze_branch.py --json

This returns: commits, changed files, diff stats.

3. Generate Mermaid Diagram

Create visual representation of changes:

python skills/github-integration/scripts/generate_mermaid.py --json

This generates a flowchart showing:

Changed files grouped by category (Source, Tests, Config, Docs)
Line additions/deletions per file
Visual structure of the PR

4. Generate PR Content

Use the pr-composer agent to create the full PR description:

Invoke the pr-composer agent with:
- commits from step 2
- changed_files from step 2
- gate results from pipeline state
- mermaid diagram from step 3

The pr-composer will generate:

PR title (conventional commit format)
Summary from commits
Mermaid diagram section
Preflight Results table
Test Plan checklist

5. Determine Labels

Based on commit messages:

feat: -> enhancement
fix: -> bug
docs: -> documentation
refactor: -> refactor
test: -> testing
BREAKING CHANGE: -> breaking-change

6. Create PR

Use GitHub MCP tools (preferred) or gh CLI (fallback):

Read the full file on GitHub · 220 lines

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.

1mo ago First seen · 220 lines · 0 tokens per session scan A ef69ba6b47e5

Subscribe to this mod's changes

github-pr is an agent published in the GitHub repository dansasser/claude-code-marketplace (9 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 1,298 once invoked, about $0.0002 per session on Opus 5.5. 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.

Git and workflow

plastic-node-work

Dispatched for a work node by Plastic's node-graph runner. Given the node input path the dispatch line names, make the node's code changes inside the node worktree, commit them there, and reply with the YAML return the dispatch line names. Never spawned outside a runner dispatch.

zalom/plastic · 65 tokens

pr-ghostwriter

Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.

komunite/kalfa · 81 tokens

release-executor

Internal dynos-work agent. Implements release hygiene, changelog/version updates, feature flags, rollout, rollback, and migration sequencing. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:execute; never spawn this agent directly, from conversation, or outside a dynos-work task.

dynos-fit/dynos-work · 67 tokens

github-pr