A command for preparing and opening a pull request, which is a request for teammates to review and merge code into a shared repository.

Use it after finishing changes on a feature branch to run the quality gate, check for possible leaked identifiers, push the branch, and create the pull request.

It checks that work is on a separate branch, passes the project's quality checks, and follows its pull-request and release rules before opening the request.

How ribeirogab/zeno-agent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ribeirogab/zeno-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ribeirogab/zeno-agent/main/.agents/commands/new-pr.md

Clone the repo

git clone --depth 1 https://github.com/ribeirogab/zeno-agent

Made for: Claude Code.

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/commands/ribeirogab/zeno-agent/new-pr/github.svg)](https://agentmods.dev/commands/ribeirogab/zeno-agent/new-pr)

Your own site

<a href="https://agentmods.dev/commands/ribeirogab/zeno-agent/new-pr"><img src="https://agentmods.dev/badge/commands/ribeirogab/zeno-agent/new-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/commands/ribeirogab/zeno-agent/new-pr"><img src="https://agentmods.dev/badge/commands/ribeirogab/zeno-agent/new-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,154 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	$0.00000	$0.01154
Opus 5.5	$0.00000	$0.00462
Sonnet 5.5	$0.00000	$0.00231
Haiku 4.5	$0.00000	$0.00115

Measured 1mo ago against content hash df49aabd7e8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

new-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.

.agents/commands/new-pr.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

New PR

Draft and open a pull request against this repo, following the project's PR template, sanitization rule, and release flow.

When to invoke

The user (or another agent) types /new-pr from Claude Code. Optional argument: a one-line PR title or summary hint.

Steps

Branch check. Run git branch --show-current. Refuse to proceed if on main (the project's flow is "branch → PR → squash-merge into main"; opening a PR from main into main is incoherent). If on a feature branch, continue.
Quality gate. Run:
```
pnpm run quality-gate
```
Abort with the gate's error output if it fails. The user's job is to fix the issue and re-invoke /new-pr.
Sanitization heuristic check. Diff the branch against main and grep for known leak patterns (the maintainer's known real identifiers, common employer slugs, real-looking emails, GitHub installation IDs longer than 12345678):
```
git diff main...HEAD | grep -iE 'gabriel|gblosr|@gmail\.com|installation_id.*[0-9]{7,}'
```
If there are matches, list them to the user and ask: "These look like they might violate the sanitization rule. Continue anyway?" If the user says yes, proceed. If no, abort.

Push the branch if not already pushed:

if ! git ls-remote --heads origin "$(git branch --show-current)" | grep -q .; then
  git push -u origin "$(git branch --show-current)"
fi

Draft the PR title in Conventional Commits format. Suggest one based on the most recent commits on the branch; let the user edit.

Draft the PR body matching .github/PULL_REQUEST_TEMPLATE.md's shape. Spec and issue references MUST be real markdown links pointing at the branch on origin (https://github.com/<owner>/<repo>/blob/<branch>/<path>), not bare backticked paths — outsiders reading the PR cannot click a backticked path:

## Summary

<1–3 bullets describing what changes and why>

-

## Spec / issue

Spec: [<path-or-title>](https://github.com/<owner>/<repo>/blob/<branch>/.vault/specs/<slug>/spec.md)
Closes: #<N>

## Test plan

<bulleted markdown checklist of how to verify>

- [ ]

## Sanitization

- [x] No real identifiers introduced in this diff (per [`.vault/rules/sanitization.md`](../.vault/rules/sanitization.md)).

## Quality gate

- [x] `pnpm run quality-gate` is green locally.

Read the full file on GitHub · 100 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 · 100 lines · 0 tokens per session scan A df49aabd7e8c

Subscribe to this mod's changes

new-pr is a command published in the GitHub repository ribeirogab/zeno-agent (10 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,154 tokens. 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.

Claude Code Code review Commits Git and workflow ai ai-agent anthropic automation claude

ship

Branch, commit, open PR, gather Claude + every enabled AI reviewer (Copilot, CodeRabbit, etc.), fix/justify/resolve every finding, loop until clean, then merge. Run only when implementation is finished AND the owner has said to ship (e.g. "ship it") — never self-invoke just because the work looks done. To design and…

PrabhdeepSingh/claude-plugins · 86 tokens

align

Context-aware alignment. In plan mode it audits the active plan and folds the amendments in. Otherwise it reviews the branch, a named branch, or a pull request against Ion's principles, authors a fix plan, and after approval implements and commits the fixes.

dsswift/ion · 51 tokens

zeno-agent: Command for Claude Code